{"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.11.13"},"kaggle":{"accelerator":"none","dataSources":[],"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false},"papermill":{"default_parameters":{},"duration":443.236597,"end_time":"2026-01-11T03:21:01.244396","environment_variables":{},"exception":null,"input_path":"__notebook__.ipynb","output_path":"__notebook__.ipynb","parameters":{},"start_time":"2026-01-11T03:13:38.007799","version":"2.6.0"},"widgets":{"application/vnd.jupyter.widget-state+json":{"state":{"04c8c6d965674c078298509623ebc9fb":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"0d1ee7ae0030412dae52cffcb379966d":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HBoxModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_1b668978be774fa2b660414b04344c1a","IPY_MODEL_5c4d105c76a84aed9bdef21a14f22e69","IPY_MODEL_9ca08dbc4d664f49859a75db4493ac98"],"layout":"IPY_MODEL_197dd02bf62342799eab3a1375b803fb","tabbable":null,"tooltip":null}},"0f85b9b05fa44473b0f0adadf96736dd":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"1181374d90994962b12c3904668eb1d3":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"1371e74c3eba4d3ca53359f4749298a4":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"13cf2bbf18c648b7b024e9885d55a622":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"13e31358f5944f53989cfaaaebbf08e4":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HTMLView","description":"","description_allow_html":false,"layout":"IPY_MODEL_6ac48f4a962a420cb60d066523a616ee","placeholder":"​","style":"IPY_MODEL_16603b3104a54e57a2e0e25f58bf140b","tabbable":null,"tooltip":null,"value":"DINO3 TTA 1: 100%"}},"16603b3104a54e57a2e0e25f58bf140b":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","background":null,"description_width":"","font_size":null,"text_color":null}},"1803a1dde3f9406f9a7baf2da16b46dd":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"194ee77804b44fe4929f9989d3e12762":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"ProgressView","bar_style":"success","description":"","description_allow_html":false,"layout":"IPY_MODEL_98480358ddef4c20830f9f1687dda55f","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_73a60cff2af2423f80559b4fe72dec1e","tabbable":null,"tooltip":null,"value":1}},"197dd02bf62342799eab3a1375b803fb":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"1b668978be774fa2b660414b04344c1a":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HTMLView","description":"","description_allow_html":false,"layout":"IPY_MODEL_2af42452f66148769e80d633885dc313","placeholder":"​","style":"IPY_MODEL_b71e7e417192473aa2b76de7bcc07f9c","tabbable":null,"tooltip":null,"value":"ConvNext View 3/4: 100%"}},"21e8e63af64941528fffb31ad46a6731":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HBoxModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_ec49b7dcc69e4092919fc7b289b60529","IPY_MODEL_609fa140f2714c08afbee2cbcc62f186","IPY_MODEL_6f4dc50f832d42b3be52f6480c7ea1e5"],"layout":"IPY_MODEL_882c175646264ef6a9f42d34252e8e07","tabbable":null,"tooltip":null}},"26f2de52610445928e60ed55f4b37f2e":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HTMLView","description":"","description_allow_html":false,"layout":"IPY_MODEL_c1cda1770b9349e88855a4c73384107e","placeholder":"​","style":"IPY_MODEL_63817b807eb1490cb92e2f2ea14dc041","tabbable":null,"tooltip":null,"value":" 1/1 [00:01<00:00,  1.97s/it]"}},"2af42452f66148769e80d633885dc313":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"2bb037ce55494d708f25783584746a88":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","background":null,"description_width":"","font_size":null,"text_color":null}},"2bd1290835cc4db7ae5c7a0db4818935":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"350c1e60d5f247e981e226603031460c":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HTMLView","description":"","description_allow_html":false,"layout":"IPY_MODEL_13cf2bbf18c648b7b024e9885d55a622","placeholder":"​","style":"IPY_MODEL_9419299993ef4e9282baf3a5891a098f","tabbable":null,"tooltip":null,"value":" 1/1 [00:04<00:00,  4.01s/it]"}},"378b49cad0984c0dabed08f1ff90a21e":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HTMLView","description":"","description_allow_html":false,"layout":"IPY_MODEL_d330605166534712aca317937691995f","placeholder":"​","style":"IPY_MODEL_51a2ba17d846466bbcfdc1bcd0489334","tabbable":null,"tooltip":null,"value":"ConvNext View 1/4: 100%"}},"3a36116fb52745319c78a030d900dbca":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"3e9bce9eddf04b1194e37e5b239176a4":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"ProgressView","bar_style":"success","description":"","description_allow_html":false,"layout":"IPY_MODEL_b385a7869d5f4297baec8b062d399187","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_1371e74c3eba4d3ca53359f4749298a4","tabbable":null,"tooltip":null,"value":1}},"3fdc20517b4b4e71b3b8510c68ea1f9a":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"51a2ba17d846466bbcfdc1bcd0489334":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","background":null,"description_width":"","font_size":null,"text_color":null}},"52a66169eaa3442c84060351547b867f":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"ProgressView","bar_style":"success","description":"","description_allow_html":false,"layout":"IPY_MODEL_fc1f7e72c61f49e0a76eee37ea39d770","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_d4b6ad5706994a3f90fe6886c5ec3519","tabbable":null,"tooltip":null,"value":1}},"5597be508fca4331b4bf7561b03df682":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","background":null,"description_width":"","font_size":null,"text_color":null}},"5c4d105c76a84aed9bdef21a14f22e69":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"ProgressView","bar_style":"success","description":"","description_allow_html":false,"layout":"IPY_MODEL_04c8c6d965674c078298509623ebc9fb","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_b836a82fad234cc48f635e5e9d6fb2da","tabbable":null,"tooltip":null,"value":1}},"609fa140f2714c08afbee2cbcc62f186":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"ProgressView","bar_style":"success","description":"","description_allow_html":false,"layout":"IPY_MODEL_1803a1dde3f9406f9a7baf2da16b46dd","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_9ebd2e5aeead431da47f075533ce6c36","tabbable":null,"tooltip":null,"value":1}},"62dd2abcb9c342c4929dba7c70dbc483":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HTMLView","description":"","description_allow_html":false,"layout":"IPY_MODEL_1181374d90994962b12c3904668eb1d3","placeholder":"​","style":"IPY_MODEL_82f0bb69bfcc4077a4ff08efeac8888e","tabbable":null,"tooltip":null,"value":"ConvNext View 2/4: 100%"}},"63817b807eb1490cb92e2f2ea14dc041":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","background":null,"description_width":"","font_size":null,"text_color":null}},"64c049b38b7d4b759444ebaa94645e27":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"6ac48f4a962a420cb60d066523a616ee":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"6d34a6de2a874a77b7412193a5ecbec6":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","background":null,"description_width":"","font_size":null,"text_color":null}},"6f4dc50f832d42b3be52f6480c7ea1e5":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HTMLView","description":"","description_allow_html":false,"layout":"IPY_MODEL_b8455b148ae44a52a1fc95317dbf2401","placeholder":"​","style":"IPY_MODEL_a5012889b2a34b5bbbb441593e2e2d5e","tabbable":null,"tooltip":null,"value":" 1/1 [00:00<00:00,  1.26it/s]"}},"72f80c5c309a416fadf56f232bfe657b":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HTMLView","description":"","description_allow_html":false,"layout":"IPY_MODEL_bdd64a607a0f4ee3918a9aec7619859b","placeholder":"​","style":"IPY_MODEL_ff8f9f54b0f84bd6989ac5710a147133","tabbable":null,"tooltip":null,"value":" 1/1 [00:01<00:00,  1.19s/it]"}},"73a60cff2af2423f80559b4fe72dec1e":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"7ccacb000627459fbc717cfdb0456695":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HBoxModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_f86df6cb49834fc087826c8d18485170","IPY_MODEL_52a66169eaa3442c84060351547b867f","IPY_MODEL_d1af0bacf69c44e7ae9dc682079fe516"],"layout":"IPY_MODEL_2bd1290835cc4db7ae5c7a0db4818935","tabbable":null,"tooltip":null}},"82f0bb69bfcc4077a4ff08efeac8888e":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","background":null,"description_width":"","font_size":null,"text_color":null}},"84227b2fb68740bf9f2e5a797bf9cc0c":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HTMLView","description":"","description_allow_html":false,"layout":"IPY_MODEL_91c5b2c9193f4a298d7f35093d11795c","placeholder":"​","style":"IPY_MODEL_c05c644cc80945a580e91b5f1da6189b","tabbable":null,"tooltip":null,"value":"100%"}},"882c175646264ef6a9f42d34252e8e07":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"91c5b2c9193f4a298d7f35093d11795c":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"932102e4e223471badcf55bb3575c8a4":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"9419299993ef4e9282baf3a5891a098f":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","background":null,"description_width":"","font_size":null,"text_color":null}},"97491afee3d5431aaf187d693683dee4":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"98480358ddef4c20830f9f1687dda55f":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"999f421fd6b94648b258315f3350fbc3":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"9ca08dbc4d664f49859a75db4493ac98":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HTMLView","description":"","description_allow_html":false,"layout":"IPY_MODEL_97491afee3d5431aaf187d693683dee4","placeholder":"​","style":"IPY_MODEL_5597be508fca4331b4bf7561b03df682","tabbable":null,"tooltip":null,"value":" 1/1 [00:00<00:00,  1.33it/s]"}},"9ebd2e5aeead431da47f075533ce6c36":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"9f6553972e54415487805cb0f0aa24ab":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"ProgressView","bar_style":"success","description":"","description_allow_html":false,"layout":"IPY_MODEL_a95558ef7e004364bff42c6754ddc08b","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_64c049b38b7d4b759444ebaa94645e27","tabbable":null,"tooltip":null,"value":1}},"a5012889b2a34b5bbbb441593e2e2d5e":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","background":null,"description_width":"","font_size":null,"text_color":null}},"a95558ef7e004364bff42c6754ddc08b":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"af38616f3a6d471b8a9549fc801c12b7":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HBoxModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_62dd2abcb9c342c4929dba7c70dbc483","IPY_MODEL_3e9bce9eddf04b1194e37e5b239176a4","IPY_MODEL_72f80c5c309a416fadf56f232bfe657b"],"layout":"IPY_MODEL_3a36116fb52745319c78a030d900dbca","tabbable":null,"tooltip":null}},"b385a7869d5f4297baec8b062d399187":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"b3b9886482584dd1bc94708c4708b1b3":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"b71e7e417192473aa2b76de7bcc07f9c":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","background":null,"description_width":"","font_size":null,"text_color":null}},"b836a82fad234cc48f635e5e9d6fb2da":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"b8455b148ae44a52a1fc95317dbf2401":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"bc410fba9d3543499c88a0ffbb9c9b3b":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","background":null,"description_width":"","font_size":null,"text_color":null}},"bdd64a607a0f4ee3918a9aec7619859b":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"c05c644cc80945a580e91b5f1da6189b":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","background":null,"description_width":"","font_size":null,"text_color":null}},"c1cda1770b9349e88855a4c73384107e":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"c86fdfd496094146b3c4480c517e7ecf":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HBoxModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_378b49cad0984c0dabed08f1ff90a21e","IPY_MODEL_d1f897356eaa4c529537fe04d4a612d0","IPY_MODEL_fde155db57cf42ef9762858b33797379"],"layout":"IPY_MODEL_932102e4e223471badcf55bb3575c8a4","tabbable":null,"tooltip":null}},"c94109708f8b4396b9148701a021d29f":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"c96d6ec1bd4f40d8a9e3e0296f552e37":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HBoxModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_13e31358f5944f53989cfaaaebbf08e4","IPY_MODEL_194ee77804b44fe4929f9989d3e12762","IPY_MODEL_350c1e60d5f247e981e226603031460c"],"layout":"IPY_MODEL_999f421fd6b94648b258315f3350fbc3","tabbable":null,"tooltip":null}},"ce9c666db9f9413cabb9662afb0c7b74":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HBoxModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_84227b2fb68740bf9f2e5a797bf9cc0c","IPY_MODEL_9f6553972e54415487805cb0f0aa24ab","IPY_MODEL_26f2de52610445928e60ed55f4b37f2e"],"layout":"IPY_MODEL_ee9a380e1e57464e841a4c1e89123e15","tabbable":null,"tooltip":null}},"d1af0bacf69c44e7ae9dc682079fe516":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HTMLView","description":"","description_allow_html":false,"layout":"IPY_MODEL_b3b9886482584dd1bc94708c4708b1b3","placeholder":"​","style":"IPY_MODEL_6d34a6de2a874a77b7412193a5ecbec6","tabbable":null,"tooltip":null,"value":" 1/1 [00:03<00:00,  3.97s/it]"}},"d1f897356eaa4c529537fe04d4a612d0":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"FloatProgressModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"ProgressView","bar_style":"success","description":"","description_allow_html":false,"layout":"IPY_MODEL_dc4a8be7a5314e96a8056489a6c3a9cf","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_c94109708f8b4396b9148701a021d29f","tabbable":null,"tooltip":null,"value":1}},"d330605166534712aca317937691995f":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"d4b6ad5706994a3f90fe6886c5ec3519":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"ProgressStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"d51a52e4dd994e83880de8ce903a46c4":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","background":null,"description_width":"","font_size":null,"text_color":null}},"dbb940b3362442e793195b5a6783b1d4":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"dc4a8be7a5314e96a8056489a6c3a9cf":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"ec49b7dcc69e4092919fc7b289b60529":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HTMLView","description":"","description_allow_html":false,"layout":"IPY_MODEL_3fdc20517b4b4e71b3b8510c68ea1f9a","placeholder":"​","style":"IPY_MODEL_d51a52e4dd994e83880de8ce903a46c4","tabbable":null,"tooltip":null,"value":"ConvNext View 4/4: 100%"}},"ee9a380e1e57464e841a4c1e89123e15":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"f86df6cb49834fc087826c8d18485170":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HTMLView","description":"","description_allow_html":false,"layout":"IPY_MODEL_0f85b9b05fa44473b0f0adadf96736dd","placeholder":"​","style":"IPY_MODEL_bc410fba9d3543499c88a0ffbb9c9b3b","tabbable":null,"tooltip":null,"value":"DINO3 TTA 2: 100%"}},"fc1f7e72c61f49e0a76eee37ea39d770":{"model_module":"@jupyter-widgets/base","model_module_version":"2.0.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"2.0.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border_bottom":null,"border_left":null,"border_right":null,"border_top":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"fde155db57cf42ef9762858b33797379":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"2.0.0","_view_name":"HTMLView","description":"","description_allow_html":false,"layout":"IPY_MODEL_dbb940b3362442e793195b5a6783b1d4","placeholder":"​","style":"IPY_MODEL_2bb037ce55494d708f25783584746a88","tabbable":null,"tooltip":null,"value":" 1/1 [01:15<00:00, 75.59s/it]"}},"ff8f9f54b0f84bd6989ac5710a147133":{"model_module":"@jupyter-widgets/controls","model_module_version":"2.0.0","model_name":"HTMLStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"2.0.0","_model_name":"HTMLStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"2.0.0","_view_name":"StyleView","background":null,"description_width":"","font_size":null,"text_color":null}}},"version_major":2,"version_minor":0}}},"nbformat_minor":4,"nbformat":4,"cells":[{"id":"0f74563d","cell_type":"markdown","source":"## Model 1 EVA02","metadata":{"papermill":{"duration":0.006335,"end_time":"2026-01-11T03:13:43.160436","exception":false,"start_time":"2026-01-11T03:13:43.154101","status":"completed"},"tags":[]}},{"id":"90dc4344","cell_type":"code","source":"# ====================================================================================\n# [Part 1 Optimized] EVA02 Inference with Multi-Scale TTA\n# ====================================================================================\nimport os\nimport gc\nimport cv2\nimport numpy as np\nimport pandas as pd\nimport torch\nimport torch.nn as nn\nimport timm\nimport albumentations as A\nfrom albumentations.pytorch import ToTensorV2\nfrom tqdm.auto import tqdm\n\n# class ConfigEVA:\n# data_dir = '/kaggle/input/csiro-biomass/test'\n# # 确保路径正确，如果不正确请修改\n# model_path = '/kaggle/input/model-0-65/best_model_fold_4.pth'\n# base_size = 448\n# # 新增：多尺度列表\n# scales = [448, 448] \n# device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n\n# class BiomassModelEVA(nn.Module):\n# def regression_head(self, name, in_features: int, dropout: float):\n# return nn.Sequential(\n# nn.Linear(in_features, in_features // 2),\n# nn.ReLU(),\n# nn.Dropout(dropout),\n# nn.Linear(in_features // 2, 1)\n# )\n# def __init__(self, model_name, dropout = 0.0):\n# super().__init__()\n# self.backbone = timm.create_model(model_name, pretrained=False, num_classes=0, global_pool='avg')\n# n_features = self.backbone.num_features * 2\n# self.head_total = self.regression_head('dry_total', n_features, dropout)\n# self.head_gdm = self.regression_head('dry_gdm', n_features, dropout)\n# self.head_green = self.regression_head('dry_green', n_features, dropout)\n\n# def forward(self, img_left, img_right):\n# fl = self.backbone(img_left)\n# fr = self.backbone(img_right)\n# img_feat = torch.cat([fl, fr], dim=1)\n# return self.head_total(img_feat), self.head_gdm(img_feat), self.head_green(img_feat)\n\n# def get_transforms(img_size):\n# return A.Compose([\n# A.Resize(img_size, img_size),\n# A.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),\n# ToTensorV2()\n# ])\n\n# def run_eva_inference_optimized():\n# print(f\"🚀 Starting EVA02 Optimized Inference (Scales: {ConfigEVA.scales})...\")\n \n# if not os.path.exists(ConfigEVA.model_path):\n# print(f\"❌ Error: Model not found at {ConfigEVA.model_path}\")\n# return\n\n# ckpt = torch.load(ConfigEVA.model_path, map_location=ConfigEVA.device)\n# model_name = ckpt.get('model_name', 'eva02_large_patch14_448.mim_m38m_ft_in22k_in1k')\n \n# model = BiomassModelEVA(model_name=model_name)\n# model.load_state_dict(ckpt['model_state_dict'])\n# model.eval()\n# model.to(ConfigEVA.device)\n \n# image_files = [f for f in os.listdir(ConfigEVA.data_dir) if f.lower().endswith(('.png', '.jpg'))]\n# results = []\n \n# # 定义两个尺度的 TTA\n# tf_base = get_transforms(ConfigEVA.scales[0])\n# tf_large = get_transforms(ConfigEVA.scales[1])\n \n# # 简单的 Batch 处理 TTA (Resize + Flip)\n# # TTA 策略: [Size1, Size1_Flip, Size2] (共3次推理)\n \n# for img_file in tqdm(image_files, desc=\"EVA02 Scale Predicting\"):\n# img_path = os.path.join(ConfigEVA.data_dir, img_file)\n# image = cv2.imread(img_path)\n# if image is None: continue\n# image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n# h, w, _ = image.shape\n \n# img_l = image[:, :w//2]\n# img_r = image[:, w//2:]\n \n# # 准备 TTA 输入\n# inputs_l, inputs_r = [], []\n \n# # 1. Base Scale (Normal)\n# inputs_l.append(tf_base(image=img_l)['image'])\n# inputs_r.append(tf_base(image=img_r)['image'])\n \n# # 2. Base Scale (HFlip)\n# inputs_l.append(tf_base(image=cv2.flip(img_l, 1))['image'])\n# inputs_r.append(tf_base(image=cv2.flip(img_r, 1))['image'])\n \n# # 3. Large Scale (Normal) - 增加细节捕捉\n# inputs_l.append(tf_large(image=img_l)['image'])\n# inputs_r.append(tf_large(image=img_r)['image'])\n \n# # Stack & Infer\n# tensor_l = torch.stack(inputs_l).to(ConfigEVA.device)\n# tensor_r = torch.stack(inputs_r).to(ConfigEVA.device)\n \n# with torch.inference_mode():\n# p_tot, p_gdm, p_green = model(tensor_l, tensor_r)\n \n# # 融合 TTA 结果 (加权：大尺度给予 0.4 权重，Base给予 0.6)\n# # raw preds shape: (3, 1) -> (3,)\n# preds_tot = p_tot.cpu().numpy().flatten()\n# preds_gdm = p_gdm.cpu().numpy().flatten()\n# preds_grn = p_green.cpu().numpy().flatten()\n \n# # 加权平均：0.35(Base) + 0.35(Flip) + 0.30(Large)\n# w = np.array([0.35, 0.35, 0.30])\n# val_tot = np.dot(preds_tot, w)\n# val_gdm = np.dot(preds_gdm, w)\n# val_grn = np.dot(preds_grn, w)\n \n# results.append({\n# 'base_id': os.path.splitext(img_file)[0],\n# 'Dry_Total_g': max(0, val_tot),\n# 'GDM_g': max(0, val_gdm),\n# 'Dry_Green_g': max(0, val_grn)\n# })\n\n# df = pd.DataFrame(results)\n# df.to_csv('preds_eva02_wide.csv', index=False)\n# print(f\"✅ EVA02 Optimized Predictions Saved! (Rows: {len(df)})\")\n \n# del model, tensor_l, tensor_r\n# gc.collect()\n# torch.cuda.empty_cache()\n\n# if __name__ == \"__main__\":\n# run_eva_inference_optimized()","metadata":{"execution":{"iopub.execute_input":"2026-01-11T03:13:43.17161Z","iopub.status.busy":"2026-01-11T03:13:43.171325Z","iopub.status.idle":"2026-01-11T03:14:36.572629Z","shell.execute_reply":"2026-01-11T03:14:36.57185Z"},"papermill":{"duration":53.412618,"end_time":"2026-01-11T03:14:36.578193","exception":false,"start_time":"2026-01-11T03:13:43.165575","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"e454ba77","cell_type":"markdown","source":"## Model 2 DINOv2 Giant Mamba","metadata":{"papermill":{"duration":0.004437,"end_time":"2026-01-11T03:14:36.587258","exception":false,"start_time":"2026-01-11T03:14:36.582821","status":"completed"},"tags":[]}},{"id":"36a969f0","cell_type":"code","source":"# =============================================================================\n# CSIRO Image2Biomass - v4 CrossPVT T2T Mamba Inference (Self-contained)\n# =============================================================================\n\nimport os\nimport gc\nimport math\nimport argparse\nimport logging\nimport random # 新增 import\nfrom dataclasses import dataclass, field\nfrom typing import List, Tuple, Dict, Optional\n\nimport cv2\nimport timm\nimport numpy as np\nimport pandas as pd\nfrom pathlib import Path\nfrom tqdm import tqdm\n\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nfrom torch.utils.data import Dataset, DataLoader\n\nimport albumentations as A\nfrom albumentations.pytorch import ToTensorV2\n\n# =============================================================================\n# Logger\n# =============================================================================\nLOGGER = logging.getLogger(\"csiro_infer_v4\")\nif not LOGGER.handlers:\n LOGGER.addHandler(logging.StreamHandler())\nLOGGER.setLevel(logging.INFO)\n\n# =============================================================================\n# 新增：固定随机种子\n# =============================================================================\ndef seed_everything(seed=43):\n random.seed(seed)\n os.environ['PYTHONHASHSEED'] = str(seed)\n np.random.seed(seed)\n torch.manual_seed(seed)\n torch.cuda.manual_seed(seed)\n torch.cuda.manual_seed_all(seed)\n torch.backends.cudnn.deterministic = True\n torch.backends.cudnn.benchmark = False\n print(f\"🔒 Seed set to {seed}\")\n\n# =============================================================================\n# 训练时使用的配置（会被 checkpoint 中的 cfg 覆盖）\n# =============================================================================\n@dataclass\nclass TrainCFG:\n dropout: float = 0.1\n hidden_ratio: float = 0.35\n\n # DINO backbone 相关\n dino_candidates: Tuple[str, ...] = (\n \"vit_base_patch14_dinov2\",\n \"vit_base_patch14_reg4_dinov2\",\n \"vit_small_patch14_dinov2\",\n )\n small_grid: Tuple[int, int] = (4, 4)\n big_grid: Tuple[int, int] = (2, 2)\n t2t_depth: int = 2\n cross_layers: int = 2\n cross_heads: int = 6\n\n # Pyramid + Mamba\n pyramid_dims: Tuple[int, int, int] = (384, 512, 640)\n mobilevit_heads: int = 4\n mobilevit_depth: int = 2\n sra_heads: int = 8\n sra_ratio: int = 2\n mamba_depth: int = 3\n mamba_kernel: int = 5\n aux_head: bool = True\n aux_loss_weight: float = 0.4\n\n # 目标列（用于辅助头 / 5 目标打包）\n ALL_TARGET_COLS: Tuple[str, ...] = (\n \"Dry_Green_g\",\n \"Dry_Dead_g\",\n \"Dry_Clover_g\",\n \"GDM_g\",\n \"Dry_Total_g\",\n )\n\n\nCFG = TrainCFG()\n\n\ndef update_cfg_from_checkpoint(cfg_dict: dict):\n \"\"\"\n 用 checkpoint 中保存的 cfg 覆盖当前 CFG 的同名字段，\n 确保推理结构与训练完全一致。\n \"\"\"\n global CFG\n if not cfg_dict:\n return\n for k, v in cfg_dict.items():\n if hasattr(CFG, k):\n setattr(CFG, k, v)\n\n\n# =============================================================================\n# Model blocks（与 train.py 保持一致的简化实现）\n# =============================================================================\nclass FeedForward(nn.Module):\n def __init__(self, dim, mlp_ratio=4.0, dropout=0.0):\n super().__init__()\n hid = int(dim * mlp_ratio)\n self.net = nn.Sequential(\n nn.Linear(dim, hid),\n nn.GELU(),\n nn.Dropout(dropout),\n nn.Linear(hid, dim),\n nn.Dropout(dropout),\n )\n\n def forward(self, x):\n return self.net(x)\n\n\nclass AttentionBlock(nn.Module):\n def __init__(self, dim, heads=8, dropout=0.0, mlp_ratio=4.0):\n super().__init__()\n self.norm1 = nn.LayerNorm(dim)\n self.attn = nn.MultiheadAttention(dim, heads, dropout=dropout, batch_first=True)\n self.norm2 = nn.LayerNorm(dim)\n self.ff = FeedForward(dim, mlp_ratio=mlp_ratio, dropout=dropout)\n\n def forward(self, x):\n h = self.norm1(x)\n attn_out, _ = self.attn(h, h, h, need_weights=False)\n x = x + attn_out\n x = x + self.ff(self.norm2(x))\n return x\n\n\nclass MobileViTBlock(nn.Module):\n \"\"\"\n 轻量 MobileViT：局部 CNN + 小型 Transformer（token 化和 fold back）\n \"\"\"\n\n def __init__(self, dim, heads=4, depth=2, patch=(2, 2), dropout=0.0):\n super().__init__()\n self.local = nn.Sequential(\n nn.Conv2d(dim, dim, 3, padding=1, groups=dim),\n nn.Conv2d(dim, dim, 1),\n nn.GELU(),\n )\n self.patch = patch\n self.transformer = nn.ModuleList(\n [AttentionBlock(dim, heads=heads, dropout=dropout, mlp_ratio=2.0) for _ in range(depth)]\n )\n self.fuse = nn.Conv2d(dim * 2, dim, kernel_size=1)\n\n def forward(self, x: torch.Tensor):\n local_feat = self.local(x)\n B, C, H, W = local_feat.shape\n ph, pw = self.patch\n new_h = math.ceil(H / ph) * ph\n new_w = math.ceil(W / pw) * pw\n if new_h != H or new_w != W:\n local_feat = F.interpolate(local_feat, size=(new_h, new_w), mode=\"bilinear\", align_corners=False)\n H, W = new_h, new_w\n\n tokens = local_feat.unfold(2, ph, ph).unfold(3, pw, pw) # B,C,nh,nw,ph,pw\n tokens = tokens.contiguous().view(B, C, -1, ph, pw)\n tokens = tokens.permute(0, 2, 3, 4, 1).reshape(B, -1, C)\n\n for blk in self.transformer:\n tokens = blk(tokens)\n\n feat = tokens.view(B, -1, ph * pw, C).permute(0, 3, 1, 2)\n nh = H // ph\n nw = W // pw\n feat = feat.view(B, C, nh, nw, ph, pw).permute(0, 1, 2, 4, 3, 5)\n feat = feat.reshape(B, C, H, W)\n\n if feat.shape[-2:] != x.shape[-2:]:\n feat = F.interpolate(feat, size=x.shape[-2:], mode=\"bilinear\", align_corners=False)\n\n out = self.fuse(torch.cat([x, feat], dim=1))\n return out\n\n\nclass SpatialReductionAttention(nn.Module):\n def __init__(self, dim, heads=8, sr_ratio=2, dropout=0.0):\n super().__init__()\n self.heads = heads\n self.scale = (dim // heads) ** -0.5\n self.q = nn.Linear(dim, dim)\n self.kv = nn.Linear(dim, dim * 2)\n self.sr_ratio = sr_ratio\n if sr_ratio > 1:\n self.sr = nn.Conv2d(dim, dim, kernel_size=sr_ratio, stride=sr_ratio)\n self.norm = nn.LayerNorm(dim)\n else:\n self.sr = None\n self.proj = nn.Linear(dim, dim)\n self.drop = nn.Dropout(dropout)\n\n def forward(self, x, hw: Tuple[int, int]):\n B, N, C = x.shape\n q = self.q(x).reshape(B, N, self.heads, C // self.heads).permute(0, 2, 1, 3)\n\n if self.sr is not None:\n H, W = hw\n feat = x.transpose(1, 2).reshape(B, C, H, W)\n feat = self.sr(feat)\n feat = feat.reshape(B, C, -1).transpose(1, 2)\n feat = self.norm(feat)\n else:\n feat = x\n\n kv = self.kv(feat)\n k, v = kv.chunk(2, dim=-1)\n k = k.reshape(B, -1, self.heads, C // self.heads).permute(0, 2, 3, 1)\n v = v.reshape(B, -1, self.heads, C // self.heads).permute(0, 2, 1, 3)\n\n attn = torch.matmul(q, k) * self.scale\n attn = attn.softmax(dim=-1)\n attn = self.drop(attn)\n out = torch.matmul(attn, v).permute(0, 2, 1, 3).reshape(B, N, C)\n out = self.proj(out)\n return out\n\n\nclass PVTBlock(nn.Module):\n def __init__(self, dim, heads=8, sr_ratio=2, dropout=0.0, mlp_ratio=4.0):\n super().__init__()\n self.norm1 = nn.LayerNorm(dim)\n self.sra = SpatialReductionAttention(dim, heads=heads, sr_ratio=sr_ratio, dropout=dropout)\n self.norm2 = nn.LayerNorm(dim)\n self.ff = FeedForward(dim, mlp_ratio=mlp_ratio, dropout=dropout)\n\n def forward(self, x, hw: Tuple[int, int]):\n x = x + self.sra(self.norm1(x), hw)\n x = x + self.ff(self.norm2(x))\n return x\n\n\nclass LocalMambaBlock(nn.Module):\n \"\"\"\n 简化版 local Mamba：DW-Conv + gating + 线性映射\n \"\"\"\n\n def __init__(self, dim, kernel_size=5, dropout=0.0):\n super().__init__()\n self.norm = nn.LayerNorm(dim)\n self.dwconv = nn.Conv1d(dim, dim, kernel_size=kernel_size, padding=kernel_size // 2, groups=dim)\n self.gate = nn.Linear(dim, dim)\n self.proj = nn.Linear(dim, dim)\n self.drop = nn.Dropout(dropout)\n\n def forward(self, x):\n shortcut = x\n x = self.norm(x)\n g = torch.sigmoid(self.gate(x))\n x = (x * g).transpose(1, 2) # B, C, N\n x = self.dwconv(x).transpose(1, 2)\n x = self.proj(x)\n x = self.drop(x)\n return shortcut + x\n\n\nclass T2TRetokenizer(nn.Module):\n \"\"\"\n 将 4x4 tile token 做局部 attention + 下采样到 2x2\n \"\"\"\n\n def __init__(self, dim, depth=2, heads=4, dropout=0.0):\n super().__init__()\n self.blocks = nn.ModuleList(\n [AttentionBlock(dim, heads=heads, dropout=dropout, mlp_ratio=2.0) for _ in range(depth)]\n )\n\n def forward(self, tokens: torch.Tensor, grid_hw: Tuple[int, int]):\n B, T, C = tokens.shape\n H, W = grid_hw\n feat_map = tokens.transpose(1, 2).reshape(B, C, H, W)\n seq = feat_map.flatten(2).transpose(1, 2)\n for blk in self.blocks:\n seq = blk(seq)\n seq_map = seq.transpose(1, 2).reshape(B, C, H, W)\n pooled = F.adaptive_avg_pool2d(seq_map, (2, 2))\n retokens = pooled.flatten(2).transpose(1, 2)\n return retokens, seq_map\n\n\nclass CrossScaleFusion(nn.Module):\n def __init__(self, dim, heads=6, dropout=0.0, layers=2):\n super().__init__()\n self.layers_s = nn.ModuleList(\n [AttentionBlock(dim, heads=heads, dropout=dropout, mlp_ratio=2.0) for _ in range(layers)]\n )\n self.layers_b = nn.ModuleList(\n [AttentionBlock(dim, heads=heads, dropout=dropout, mlp_ratio=2.0) for _ in range(layers)]\n )\n self.cross_s = nn.ModuleList(\n [\n nn.MultiheadAttention(dim, heads, dropout=dropout, batch_first=True, kdim=dim, vdim=dim)\n for _ in range(layers)\n ]\n )\n self.cross_b = nn.ModuleList(\n [\n nn.MultiheadAttention(dim, heads, dropout=dropout, batch_first=True, kdim=dim, vdim=dim)\n for _ in range(layers)\n ]\n )\n self.norm_s = nn.LayerNorm(dim)\n self.norm_b = nn.LayerNorm(dim)\n\n def forward(self, tok_s: torch.Tensor, tok_b: torch.Tensor):\n B, Ts, C = tok_s.shape\n Tb = tok_b.shape[1]\n cls_s = tok_s.new_zeros(B, 1, C)\n cls_b = tok_b.new_zeros(B, 1, C)\n tok_s = torch.cat([cls_s, tok_s], dim=1)\n tok_b = torch.cat([cls_b, tok_b], dim=1)\n\n for ls, lb, cs, cb in zip(self.layers_s, self.layers_b, self.cross_s, self.cross_b):\n tok_s = ls(tok_s)\n tok_b = lb(tok_b)\n q_s = self.norm_s(tok_s[:, :1])\n q_b = self.norm_b(tok_b[:, :1])\n cls_s_upd, _ = cs(\n q_s,\n torch.cat([tok_b, q_b], dim=1),\n torch.cat([tok_b, q_b], dim=1),\n need_weights=False,\n )\n cls_b_upd, _ = cb(\n q_b,\n torch.cat([tok_s, q_s], dim=1),\n torch.cat([tok_s, q_s], dim=1),\n need_weights=False,\n )\n tok_s = torch.cat([tok_s[:, :1] + cls_s_upd, tok_s[:, 1:]], dim=1)\n tok_b = torch.cat([tok_b[:, :1] + cls_b_upd, tok_b[:, 1:]], dim=1)\n\n tokens = torch.cat([tok_s[:, :1], tok_b[:, :1], tok_s[:, 1:], tok_b[:, 1:]], dim=1)\n return tokens # shape ~ (B, 2 + Ts + Tb, C)\n\n\nclass TileEncoder(nn.Module):\n def __init__(self, backbone: nn.Module, input_res: int):\n super().__init__()\n self.backbone = backbone\n self.input_res = input_res\n\n def forward(self, x: torch.Tensor, grid: Tuple[int, int]):\n B, C, H, W = x.shape\n r, c = grid\n hs = torch.linspace(0, H, steps=r + 1, device=x.device).round().long()\n ws = torch.linspace(0, W, steps=c + 1, device=x.device).round().long()\n tiles = []\n for i in range(r):\n for j in range(c):\n rs, re = hs[i].item(), hs[i + 1].item()\n cs, ce = ws[j].item(), ws[j + 1].item()\n xt = x[:, :, rs:re, cs:ce]\n if xt.shape[-2:] != (self.input_res, self.input_res):\n xt = F.interpolate(xt, size=(self.input_res, self.input_res), mode=\"bilinear\", align_corners=False)\n tiles.append(xt)\n tiles = torch.stack(tiles, dim=1) # (B, T, C, H, W)\n flat = tiles.view(-1, C, self.input_res, self.input_res)\n feats = self.backbone(flat)\n feats = feats.view(B, -1, feats.shape[-1])\n return feats\n\n\nclass PyramidMixer(nn.Module):\n def __init__(\n self,\n dim_in: int,\n dims: Tuple[int, int, int],\n mobilevit_heads: int = 4,\n mobilevit_depth: int = 2,\n sra_heads: int = 6,\n sra_ratio: int = 2,\n mamba_depth: int = 3,\n mamba_kernel: int = 5,\n dropout: float = 0.0,\n ):\n super().__init__()\n c1, c2, c3 = dims\n self.proj1 = nn.Linear(dim_in, c1)\n self.mobilevit = MobileViTBlock(c1, heads=mobilevit_heads, depth=mobilevit_depth, dropout=dropout)\n self.proj2 = nn.Linear(c1, c2)\n self.pvt = PVTBlock(c2, heads=sra_heads, sr_ratio=sra_ratio, dropout=dropout, mlp_ratio=3.0)\n self.mamba_local = LocalMambaBlock(c2, kernel_size=mamba_kernel, dropout=dropout)\n self.proj3 = nn.Linear(c2, c3)\n self.mamba_global = nn.ModuleList(\n [LocalMambaBlock(c3, kernel_size=mamba_kernel, dropout=dropout) for _ in range(mamba_depth)]\n )\n self.final_attn = AttentionBlock(c3, heads=min(8, c3 // 64 + 1), dropout=dropout, mlp_ratio=2.0)\n\n def _tokens_to_map(self, tokens: torch.Tensor, target_hw: Tuple[int, int]):\n B, N, C = tokens.shape\n H, W = target_hw\n need = H * W\n if N < need:\n pad = tokens.new_zeros(B, need - N, C)\n tokens = torch.cat([tokens, pad], dim=1)\n tokens = tokens[:, :need, :]\n feat_map = tokens.transpose(1, 2).reshape(B, C, H, W)\n return feat_map\n\n @staticmethod\n def _fit_hw(n_tokens: int) -> Tuple[int, int]:\n \"\"\"选择一个接近方形、满足 h*w>=n_tokens 的网格。\"\"\"\n h = int(math.sqrt(n_tokens))\n w = h\n while h * w < n_tokens:\n w += 1\n if h * w < n_tokens:\n h += 1\n return h, w\n\n def forward(self, tokens: torch.Tensor):\n # 约 10 tokens -> 3x4 map\n B, N, C = tokens.shape\n map_hw = (3, 4)\n feat_map = self._tokens_to_map(tokens, map_hw)\n\n t1 = self.proj1(tokens)\n m1 = self._tokens_to_map(t1, map_hw)\n m1 = self.mobilevit(m1)\n t1_out = m1.flatten(2).transpose(1, 2)[:, :N]\n\n # Stage2: 下采样 token 数量（平均池化）\n t2 = self.proj2(t1_out)\n new_len = max(4, N // 2)\n t2 = t2[:, :new_len] + F.adaptive_avg_pool1d(t2.transpose(1, 2), new_len).transpose(1, 2)\n hw2 = self._fit_hw(t2.size(1))\n if t2.size(1) < hw2[0] * hw2[1]:\n pad = t2.new_zeros(B, hw2[0] * hw2[1] - t2.size(1), t2.size(2))\n t2 = torch.cat([t2, pad], dim=1)\n t2 = self.pvt(t2, hw2)\n t2 = self.mamba_local(t2)\n\n # Stage3: 全局\n t3 = self.proj3(t2)\n pooled = torch.stack([t3.mean(dim=1), t3.max(dim=1).values], dim=1) # (B,2,C)\n t3 = pooled\n for blk in self.mamba_global:\n t3 = blk(t3)\n t3 = self.final_attn(t3)\n global_feat = t3.mean(dim=1)\n return global_feat, {\"stage1_map\": m1.detach(), \"stage2_tokens\": t2.detach(), \"stage3_tokens\": t3.detach()}\n\n\nclass CrossPVT_T2T_MambaDINO(nn.Module):\n def __init__(self, dropout: float = 0.1, hidden_ratio: float = 0.35):\n super().__init__()\n self.backbone, self.feat_dim, self.backbone_name, self.input_res = self._build_dino_backbone()\n self.tile_encoder = TileEncoder(self.backbone, self.input_res)\n self.t2t = T2TRetokenizer(self.feat_dim, depth=CFG.t2t_depth, heads=CFG.cross_heads, dropout=dropout)\n self.cross = CrossScaleFusion(\n self.feat_dim, heads=CFG.cross_heads, dropout=dropout, layers=CFG.cross_layers\n )\n self.pyramid = PyramidMixer(\n dim_in=self.feat_dim,\n dims=CFG.pyramid_dims,\n mobilevit_heads=CFG.mobilevit_heads,\n mobilevit_depth=CFG.mobilevit_depth,\n sra_heads=CFG.sra_heads,\n sra_ratio=CFG.sra_ratio,\n mamba_depth=CFG.mamba_depth,\n mamba_kernel=CFG.mamba_kernel,\n dropout=dropout,\n )\n\n combined = CFG.pyramid_dims[-1] * 2\n self.combined_dim = combined\n hidden = max(32, int(combined * hidden_ratio))\n\n def head():\n return nn.Sequential(\n nn.Linear(combined, hidden),\n nn.GELU(),\n nn.Dropout(dropout),\n nn.Linear(hidden, 1),\n )\n\n self.head_green = head()\n self.head_clover = head()\n self.head_dead = head()\n self.score_head = nn.Sequential(nn.LayerNorm(combined), nn.Linear(combined, 1))\n self.aux_head = (\n nn.Sequential(nn.LayerNorm(CFG.pyramid_dims[1]), nn.Linear(CFG.pyramid_dims[1], 5))\n if CFG.aux_head\n else None\n )\n self.softplus = nn.Softplus(beta=1.0)\n\n self.cross_gate_left = nn.Linear(CFG.pyramid_dims[-1], CFG.pyramid_dims[-1])\n self.cross_gate_right = nn.Linear(CFG.pyramid_dims[-1], CFG.pyramid_dims[-1])\n\n def _build_dino_backbone(self):\n \"\"\"\n 只创建骨干结构，不加载预训练权重（pretrained=False），\n 避免在 Kaggle 无网环境下下载；权重由 checkpoint 提供。\n \"\"\"\n last_err = None\n for name in CFG.dino_candidates:\n for gp in [\"token\", \"avg\", \"__default__\"]:\n try:\n if gp == \"__default__\":\n m = timm.create_model(name, pretrained=False, num_classes=0)\n gp_str = \"default\"\n else:\n m = timm.create_model(name, pretrained=False, num_classes=0, global_pool=gp)\n gp_str = gp\n feat = m.num_features\n input_res = self._infer_input_res(m)\n LOGGER.info(\n f\"✅ 使用 DINO 主干: {name} | global_pool={gp_str} | \"\n f\"feat_dim={feat} | input_res={input_res}\"\n )\n if hasattr(m, \"set_grad_checkpointing\"):\n m.set_grad_checkpointing(True)\n return m, feat, name, int(input_res)\n except Exception as e:\n last_err = e\n continue\n raise RuntimeError(f\"无法创建任何 DINO 主干。最后错误: {last_err}\")\n\n @staticmethod\n def _infer_input_res(m) -> int:\n if hasattr(m, \"patch_embed\") and hasattr(m.patch_embed, \"img_size\"):\n isz = m.patch_embed.img_size\n return int(isz if isinstance(isz, (int, float)) else isz[0])\n if hasattr(m, \"img_size\"):\n isz = m.img_size\n return int(isz if isinstance(isz, (int, float)) else isz[0])\n dc = getattr(m, \"default_cfg\", {}) or {}\n ins = dc.get(\"input_size\", None)\n if ins:\n if isinstance(ins, (tuple, list)) and len(ins) >= 2:\n return int(ins[1])\n return int(ins if isinstance(ins, (int, float)) else 224)\n return 518\n\n def _half_forward(self, x_half: torch.Tensor):\n tiles_small = self.tile_encoder(x_half, CFG.small_grid)\n tiles_big = self.tile_encoder(x_half, CFG.big_grid)\n t2, stage1_map = self.t2t(tiles_small, CFG.small_grid)\n fused = self.cross(t2, tiles_big)\n feat, feat_maps = self.pyramid(fused)\n feat_maps[\"stage1_map\"] = stage1_map\n return feat, feat_maps\n\n def _merge_heads(self, f_l: torch.Tensor, f_r: torch.Tensor):\n g_l = torch.sigmoid(self.cross_gate_left(f_r))\n g_r = torch.sigmoid(self.cross_gate_right(f_l))\n f_l = f_l * g_l\n f_r = f_r * g_r\n f = torch.cat([f_l, f_r], dim=1)\n green_pos = self.softplus(self.head_green(f))\n clover_pos = self.softplus(self.head_clover(f))\n dead_pos = self.softplus(self.head_dead(f))\n gdm = green_pos + clover_pos\n total = gdm + dead_pos\n return total, gdm, green_pos, f\n\n def _param_device_dtype(self):\n try:\n ref = next(self.parameters())\n return ref.device, ref.dtype\n except StopIteration:\n return torch.device(\"cpu\"), torch.float32\n\n def _empty_forward_output(self, device=None, dtype=None, return_features: bool = False):\n if device is None or dtype is None:\n device_p, dtype_p = self._param_device_dtype()\n if device is None:\n device = device_p\n if dtype is None:\n dtype = dtype_p\n\n zero = torch.zeros(0, 1, device=device, dtype=dtype)\n out = {\n \"total\": zero,\n \"gdm\": zero,\n \"green\": zero,\n \"score_feat\": torch.zeros(0, self.combined_dim, device=device, dtype=dtype),\n }\n if self.aux_head is not None:\n out[\"aux\"] = torch.zeros(0, len(CFG.ALL_TARGET_COLS), device=device, dtype=dtype)\n if return_features:\n out[\"feature_maps\"] = {}\n return out\n\n def forward(self, *inputs, x_left=None, x_right=None, return_features: bool = False):\n # 兼容 DataParallel 传参方式（单 tensor / 元组）\n if inputs:\n if len(inputs) == 1:\n first = inputs[0]\n if isinstance(first, (tuple, list)):\n if len(first) >= 1:\n x_left = first[0]\n if len(first) >= 2:\n x_right = first[1]\n else:\n x_left = first\n else:\n x_left = inputs[0]\n x_right = inputs[1]\n\n if x_left is None:\n return self._empty_forward_output(return_features=return_features)\n if isinstance(x_left, torch.Tensor) and x_left.shape[0] == 0:\n return self._empty_forward_output(return_features=return_features)\n\n if x_right is None:\n if isinstance(x_left, torch.Tensor):\n if x_left.shape[1] % 2 != 0:\n raise ValueError(\"无法从单个张量推断左右分支，请显式提供 x_right。\")\n x_left, x_right = torch.chunk(x_left, 2, dim=1)\n else:\n raise ValueError(\"缺少 x_right 输入。\")\n\n feat_l, feats_l = self._half_forward(x_left)\n feat_r, feats_r = self._half_forward(x_right)\n total, gdm, green, f_concat = self._merge_heads(feat_l, feat_r)\n\n out = {\n \"total\": total,\n \"gdm\": gdm,\n \"green\": green,\n \"score_feat\": f_concat,\n }\n if self.aux_head is not None:\n aux_tokens = torch.cat([feats_l[\"stage2_tokens\"], feats_r[\"stage2_tokens\"]], dim=1)\n aux_pred = self.softplus(self.aux_head(aux_tokens.mean(dim=1)))\n out[\"aux\"] = aux_pred # 顺序与 CFG.ALL_TARGET_COLS 对齐\n if return_features:\n out[\"feature_maps\"] = {\n \"stage1_left\": feats_l.get(\"stage1_map\"),\n \"stage1_right\": feats_r.get(\"stage1_map\"),\n \"stage3_left\": feats_l.get(\"stage3_tokens\"),\n \"stage3_right\": feats_r.get(\"stage3_tokens\"),\n }\n return out\n\n\n# =============================================================================\n# 推理配置 (Modified)\n# =============================================================================\nclass INF_CFG:\n # 数据路径（Kaggle 默认，本地测试可修改）\n BASE_PATH = \"/kaggle/input/csiro-biomass\"\n TEST_CSV = os.path.join(BASE_PATH, \"test.csv\")\n TEST_IMAGE_DIR = os.path.join(BASE_PATH, \"test\")\n\n # [修改] 实验目录（你的权重所在目录）\n EXPERIMENT_DIR = \"/kaggle/input/csiro/pytorch/default/12\"\n\n # Checkpoint 路径（5-fold）\n CKPT_PATTERN_FOLD_X = os.path.join(\n EXPERIMENT_DIR, \"fold_{fold}\", \"checkpoints\", \"best_wr2.pt\"\n )\n CKPT_PATTERN_FOLDX = os.path.join(\n EXPERIMENT_DIR, \"fold{fold}\", \"checkpoints\", \"best_wr2.pt\"\n )\n N_FOLDS = 5\n\n # [修改] 输出文件名称\n SUBMISSION_FILE = \"preds_dino_wide.csv\"\n\n # 推理设置\n DEVICE = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n BATCH_SIZE = 1\n NUM_WORKERS = 0\n MIXED_PRECISION = True\n\n # TTA 设置\n USE_TTA = True\n TTA_TRANSFORMS = [\"original\", \"hflip\", \"vflip\"]\n\n # 目标列顺序（与训练一致）\n ALL_TARGET_COLS = [\"Dry_Green_g\", \"Dry_Dead_g\", \"Dry_Clover_g\", \"GDM_g\", \"Dry_Total_g\"]\n\n\nprint(f\"Device: {INF_CFG.DEVICE}\")\nprint(f\"Experiment Dir: {INF_CFG.EXPERIMENT_DIR}\")\n\n\n# =============================================================================\n# 数据集\n# =============================================================================\nclass TestBiomassDataset(Dataset):\n \"\"\"测试数据集：左右两路输入\"\"\"\n\n def __init__(self, df: pd.DataFrame, transform, image_dir: str):\n self.df = df.reset_index(drop=True)\n self.transform = transform\n self.image_dir = image_dir\n self.paths = self.df[\"image_path\"].values\n\n def __len__(self):\n return len(self.df)\n\n def __getitem__(self, idx):\n filename = os.path.basename(self.paths[idx])\n full_path = os.path.join(self.image_dir, filename)\n\n img = cv2.imread(full_path)\n if img is None:\n # 容错：若读图失败，用黑图占位\n img = np.zeros((1000, 2000, 3), dtype=np.uint8)\n else:\n img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n\n # 左右切半（与训练一致）\n h, w, _ = img.shape\n mid = w // 2\n left = img[:, :mid]\n right = img[:, mid:]\n\n left_t = self.transform(image=left)[\"image\"]\n right_t = self.transform(image=right)[\"image\"]\n\n return left_t, right_t\n\n\n# =============================================================================\n# TTA 变换\n# =============================================================================\ndef get_tta_transforms(img_size: int) -> List[A.Compose]:\n \"\"\"生成 TTA 变换列表\"\"\"\n base = [\n A.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),\n ToTensorV2(),\n ]\n\n transforms = []\n\n # 原图\n transforms.append(\n A.Compose([\n A.Resize(img_size, img_size, interpolation=cv2.INTER_AREA),\n *base,\n ])\n )\n\n # 水平翻转\n transforms.append(\n A.Compose([\n A.HorizontalFlip(p=1.0),\n A.Resize(img_size, img_size, interpolation=cv2.INTER_AREA),\n *base,\n ])\n )\n\n # 垂直翻转\n transforms.append(\n A.Compose([\n A.VerticalFlip(p=1.0),\n A.Resize(img_size, img_size, interpolation=cv2.INTER_AREA),\n *base,\n ])\n )\n\n return transforms\n\n\n# =============================================================================\n# 权重加载\n# =============================================================================\ndef strip_module_prefix(state_dict: dict) -> dict:\n \"\"\"移除 DataParallel 的 module. 前缀\"\"\"\n if not state_dict:\n return state_dict\n\n keys = list(state_dict.keys())\n if all(k.startswith(\"module.\") for k in keys):\n return {k[len(\"module.\"):]: v for k, v in state_dict.items()}\n return state_dict\n\n\ndef load_checkpoint(path: str) -> dict:\n \"\"\"加载 checkpoint\"\"\"\n if not os.path.exists(path):\n raise FileNotFoundError(f\"Checkpoint not found: {path}\")\n\n try:\n state = torch.load(path, map_location=\"cpu\", weights_only=False)\n except TypeError:\n state = torch.load(path, map_location=\"cpu\")\n\n return state\n\n\ndef load_model_from_checkpoint(ckpt_path: str) -> nn.Module:\n \"\"\"从 checkpoint 加载模型\"\"\"\n print(f\"\\n加载 checkpoint: {os.path.basename(ckpt_path)}\")\n\n state = load_checkpoint(ckpt_path)\n\n # 用 checkpoint 中的 cfg 覆盖当前 CFG（保证结构对应）\n cfg_dict = state.get(\"cfg\", {})\n update_cfg_from_checkpoint(cfg_dict)\n\n dropout = cfg_dict.get(\"dropout\", CFG.dropout)\n hidden_ratio = cfg_dict.get(\"hidden_ratio\", CFG.hidden_ratio)\n\n # 创建模型（结构与训练一致）\n model = CrossPVT_T2T_MambaDINO(dropout=dropout, hidden_ratio=hidden_ratio)\n\n # 提取模型状态\n model_state = state.get(\"model_state\")\n if model_state is None:\n # 如果 checkpoint 直接是 state_dict\n model_state = state\n\n # 移除 module. 前缀\n model_state = strip_module_prefix(model_state)\n\n # 加载权重\n missing_keys, unexpected_keys = model.load_state_dict(model_state, strict=False)\n\n if missing_keys:\n print(f\" ⚠️ 缺失的键: {len(missing_keys)} 个\")\n if len(missing_keys) <= 10:\n for k in missing_keys[:10]:\n print(f\" - {k}\")\n\n if unexpected_keys:\n print(f\" ⚠️ 意外的键: {len(unexpected_keys)} 个\")\n if len(unexpected_keys) <= 10:\n for k in unexpected_keys[:10]:\n print(f\" - {k}\")\n\n model.to(INF_CFG.DEVICE)\n model.eval()\n\n # 获取输入分辨率\n input_res = getattr(model, \"input_res\", 518)\n backbone_name = getattr(model, \"backbone_name\", \"unknown\")\n\n print(f\" ✓ 模型加载成功 | backbone={backbone_name} | input_res={input_res}\")\n\n return model\n\n\n# =============================================================================\n# 推理\n# =============================================================================\ndef pack5_targets(total: torch.Tensor, gdm: torch.Tensor, green: torch.Tensor) -> torch.Tensor:\n \"\"\"将 total, gdm, green 打包为 5 个目标\"\"\"\n clover = gdm - green\n dead = total - gdm\n return torch.cat([green, dead, clover, gdm, total], dim=1)\n\n\n@torch.no_grad()\ndef predict_one_view(models: List[nn.Module], loader: DataLoader) -> np.ndarray:\n \"\"\"对单个 TTA 视角进行预测\"\"\"\n preds_list = []\n amp_dtype = \"cuda\" if INF_CFG.DEVICE.type == \"cuda\" else \"cpu\"\n\n for xl, xr in tqdm(loader, desc=\" Predicting\", leave=False):\n xl = xl.to(INF_CFG.DEVICE, non_blocking=True)\n xr = xr.to(INF_CFG.DEVICE, non_blocking=True)\n\n # 拼接为单 tensor（与训练时的 DataParallel 调用方式一致）\n x_cat = torch.cat([xl, xr], dim=1)\n\n per_model_preds = []\n\n with torch.amp.autocast(amp_dtype, enabled=INF_CFG.MIXED_PRECISION):\n for model in models:\n out = model(x_cat, return_features=False)\n\n total = out[\"total\"]\n gdm = out[\"gdm\"]\n green = out[\"green\"]\n\n # 打包为 5 个目标\n five = pack5_targets(total, gdm, green)\n\n # 非负约束\n five = torch.clamp(five, min=0.0)\n\n per_model_preds.append(five.float().cpu())\n\n # 5-fold ensemble 平均\n stacked = torch.mean(torch.stack(per_model_preds, dim=0), dim=0)\n preds_list.append(stacked.numpy())\n\n return np.concatenate(preds_list, axis=0)\n\n\ndef run_inference(test_df: pd.DataFrame, image_dir: str) -> np.ndarray:\n \"\"\"运行完整推理流程（5-fold ensemble + TTA）\"\"\"\n print(\"\\n\" + \"=\" * 80)\n print(\"开始推理\")\n print(\"=\" * 80)\n\n # 加载所有 fold 的模型\n print(\"\\n加载模型 (5-fold)...\")\n models = []\n input_res = None\n\n for fold in range(INF_CFG.N_FOLDS):\n ckpt_path = INF_CFG.CKPT_PATTERN_FOLD_X.format(fold=fold)\n if not os.path.exists(ckpt_path):\n ckpt_path = INF_CFG.CKPT_PATTERN_FOLDX.format(fold=fold)\n\n if not os.path.exists(ckpt_path):\n print(f\" ⚠️ Fold {fold} checkpoint 不存在，尝试路径:\")\n print(f\" - {INF_CFG.CKPT_PATTERN_FOLD_X.format(fold=fold)}\")\n print(f\" - {INF_CFG.CKPT_PATTERN_FOLDX.format(fold=fold)}\")\n continue\n\n model = load_model_from_checkpoint(ckpt_path)\n models.append(model)\n\n if input_res is None:\n input_res = getattr(model, \"input_res\", 518)\n print(f\" 输入分辨率: {input_res}\")\n\n if len(models) == 0:\n print(\"\\n❌ 错误：没有找到任何可用的 checkpoint！\")\n print(f\" 请检查实验目录: {INF_CFG.EXPERIMENT_DIR}\")\n for fold in range(INF_CFG.N_FOLDS):\n print(f\" - {INF_CFG.CKPT_PATTERN_FOLD_X.format(fold=fold)}\")\n print(f\" - {INF_CFG.CKPT_PATTERN_FOLDX.format(fold=fold)}\")\n raise RuntimeError(\"没有找到任何可用的 checkpoint！\")\n\n print(f\"\\n✓ 成功加载 {len(models)} 个模型\")\n\n # TTA 推理\n if INF_CFG.USE_TTA:\n tta_transforms = get_tta_transforms(input_res)\n print(f\"\\n使用 TTA: {len(tta_transforms)} 个视角\")\n\n per_view_preds = []\n\n for i, transform in enumerate(tta_transforms):\n view_name = INF_CFG.TTA_TRANSFORMS[i] if i < len(INF_CFG.TTA_TRANSFORMS) else f\"view_{i+1}\"\n print(f\"\\n--- TTA 视角 {i+1}/{len(tta_transforms)}: {view_name} ---\")\n\n ds = TestBiomassDataset(test_df, transform, image_dir)\n dl = DataLoader(\n ds,\n batch_size=INF_CFG.BATCH_SIZE,\n shuffle=False,\n num_workers=INF_CFG.NUM_WORKERS,\n pin_memory=True,\n )\n\n view_pred = predict_one_view(models, dl)\n per_view_preds.append(view_pred)\n\n final_pred = np.mean(per_view_preds, axis=0)\n print(f\"\\n✓ TTA 完成，最终预测形状: {final_pred.shape}\")\n else:\n transform = get_tta_transforms(input_res)[0]\n ds = TestBiomassDataset(test_df, transform, image_dir)\n dl = DataLoader(\n ds,\n batch_size=INF_CFG.BATCH_SIZE,\n shuffle=False,\n num_workers=INF_CFG.NUM_WORKERS,\n pin_memory=True,\n )\n final_pred = predict_one_view(models, dl)\n\n return final_pred\n\n\n# =============================================================================\n# 生成提交文件 (Modified for Wide Format)\n# =============================================================================\ndef create_submission(final_pred: np.ndarray, test_long: pd.DataFrame, test_unique: pd.DataFrame) -> pd.DataFrame:\n \"\"\"生成宽格式输出文件 (用于集成)\"\"\"\n print(\"\\n\" + \"=\" * 80)\n print(\"生成集成用宽格式文件\")\n print(\"=\" * 80)\n\n # 提取各目标 (对应 pack5_targets 的顺序: green, dead, clover, gdm, total)\n green = final_pred[:, 0]\n dead = final_pred[:, 1]\n clover = final_pred[:, 2]\n gdm = final_pred[:, 3]\n total = final_pred[:, 4]\n\n # 非负 & NaN/Inf 处理\n def clean(x):\n x = np.nan_to_num(x, nan=0.0, posinf=0.0, neginf=0.0)\n return np.maximum(0, x)\n\n green, dead, clover, gdm, total = map(clean, [green, dead, clover, gdm, total])\n\n # 构造 Wide DataFrame\n wide = pd.DataFrame(\n {\n \"image_path\": test_unique[\"image_path\"],\n \"Dry_Green_g\": green,\n \"Dry_Dead_g\": dead,\n \"Dry_Clover_g\": clover,\n \"GDM_g\": gdm,\n \"Dry_Total_g\": total,\n }\n )\n\n # 提取 base_id 用于后续集成索引\n wide['base_id'] = wide['image_path'].apply(lambda x: os.path.splitext(os.path.basename(x))[0])\n\n # 调整列顺序，确保 base_id 在前，且包含所有必要的列\n output_cols = ['base_id', 'Dry_Total_g', 'GDM_g', 'Dry_Green_g', 'Dry_Dead_g', 'Dry_Clover_g']\n final_df = wide[output_cols]\n\n # 保存文件\n final_df.to_csv(INF_CFG.SUBMISSION_FILE, index=False)\n\n print(f\"\\n✓ 宽格式文件已保存: {INF_CFG.SUBMISSION_FILE}\")\n print(f\" 行数: {len(final_df)}\")\n print(f\"\\n前 5 行预览:\")\n print(final_df.head(5).to_string())\n return final_df\n\n\n# =============================================================================\n# 主函数（使用 parse_known_args 避免 SystemExit:2）\n# =============================================================================\ndef parse_args():\n parser = argparse.ArgumentParser(description=\"CSIRO v4 CrossPVT T2T Mamba Inference\")\n\n parser.add_argument(\n \"--test-csv\",\n type=str,\n default=None,\n help=\"测试集 CSV 路径（默认: INF_CFG.TEST_CSV）\",\n )\n parser.add_argument(\n \"--test-image-dir\",\n type=str,\n default=None,\n help=\"测试图像目录（默认: INF_CFG.TEST_IMAGE_DIR）\",\n )\n parser.add_argument(\n \"--experiment-dir\",\n type=str,\n default=None,\n help=\"实验目录（checkpoint 所在位置，默认: INF_CFG.EXPERIMENT_DIR）\",\n )\n parser.add_argument(\n \"--output\",\n type=str,\n default=None,\n help=\"输出文件路径（默认: INF_CFG.SUBMISSION_FILE）\",\n )\n parser.add_argument(\n \"--batch-size\",\n type=int,\n default=None,\n help=\"批次大小（默认: INF_CFG.BATCH_SIZE）\",\n )\n parser.add_argument(\n \"--no-tta\",\n action=\"store_true\",\n help=\"禁用 TTA\",\n )\n\n # 关键修改：用 parse_known_args 吞掉 Kaggle/Colab 多余参数（如 -f /tmp/xxx.json）\n args, _ = parser.parse_known_args()\n return args\n\n\ndef main():\n # [新增] 设置随机种子\n seed_everything(43)\n\n args = parse_args()\n\n # 更新配置\n if args.test_csv:\n INF_CFG.TEST_CSV = args.test_csv\n if args.test_image_dir:\n INF_CFG.TEST_IMAGE_DIR = args.test_image_dir\n if args.experiment_dir:\n INF_CFG.EXPERIMENT_DIR = args.experiment_dir\n INF_CFG.CKPT_PATTERN_FOLD_X = os.path.join(\n INF_CFG.EXPERIMENT_DIR, \"fold_{fold}\", \"checkpoints\", \"best_wr2.pt\"\n )\n INF_CFG.CKPT_PATTERN_FOLDX = os.path.join(\n INF_CFG.EXPERIMENT_DIR, \"fold{fold}\", \"checkpoints\", \"best_wr2.pt\"\n )\n if args.output:\n INF_CFG.SUBMISSION_FILE = args.output\n if args.batch_size:\n INF_CFG.BATCH_SIZE = args.batch_size\n if args.no_tta:\n INF_CFG.USE_TTA = False\n\n print(\"=\" * 80)\n print(\"CSIRO Image2Biomass - v4 CrossPVT T2T Mamba Inference\")\n print(\"=\" * 80)\n print(f\"测试 CSV: {INF_CFG.TEST_CSV}\")\n print(f\"测试图像目录: {INF_CFG.TEST_IMAGE_DIR}\")\n print(f\"实验目录: {INF_CFG.EXPERIMENT_DIR}\")\n print(f\"输出文件: {INF_CFG.SUBMISSION_FILE}\")\n print(f\"批次大小: {INF_CFG.BATCH_SIZE}\")\n print(f\"使用 TTA: {INF_CFG.USE_TTA}\")\n\n # 加载测试数据\n print(\"\\n加载测试数据...\")\n if not os.path.exists(INF_CFG.TEST_CSV):\n raise FileNotFoundError(f\"测试 CSV 不存在: {INF_CFG.TEST_CSV}\")\n\n test_long = pd.read_csv(INF_CFG.TEST_CSV)\n test_unique = test_long.drop_duplicates(subset=[\"image_path\"]).reset_index(drop=True)\n print(f\"✓ 找到 {len(test_unique)} 张独立测试图像\")\n print(f\" 总测试样本数: {len(test_long)}\")\n\n # 运行推理\n final_pred = run_inference(test_unique, INF_CFG.TEST_IMAGE_DIR)\n\n # 生成宽格式提交文件\n submission = create_submission(final_pred, test_long, test_unique)\n\n print(\"\\n\" + \"=\" * 80)\n print(\"推理完成！\")\n print(\"=\" * 80)\n\n # 清理\n gc.collect()\n if torch.cuda.is_available():\n torch.cuda.empty_cache()\n\n\nif __name__ == \"__main__\":\n main()","metadata":{"execution":{"iopub.execute_input":"2026-01-11T03:14:36.598051Z","iopub.status.busy":"2026-01-11T03:14:36.597593Z","iopub.status.idle":"2026-01-11T03:15:56.81812Z","shell.execute_reply":"2026-01-11T03:15:56.817548Z"},"papermill":{"duration":80.227802,"end_time":"2026-01-11T03:15:56.819361","exception":false,"start_time":"2026-01-11T03:14:36.591559","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"697c2dc4","cell_type":"markdown","source":"## Model 3 ConvNext Small","metadata":{"papermill":{"duration":0.005231,"end_time":"2026-01-11T03:15:56.830483","exception":false,"start_time":"2026-01-11T03:15:56.825252","status":"completed"},"tags":[]}},{"id":"41003ed7","cell_type":"code","source":"# ====================================================================================\n# [ConvNext Small 优化版] - 增强TTA + 后处理 + 速度优化\n# ====================================================================================\nimport os\nimport gc\nimport cv2\nimport numpy as np\nimport pandas as pd\nimport torch\nimport torch.nn as nn\nfrom torch.utils.data import DataLoader, Dataset\nimport albumentations as A\nfrom albumentations.pytorch import ToTensorV2\nfrom tqdm.auto import tqdm\nfrom pathlib import Path\nimport timm\n\ndef run_convnext_inference():\n import random\n SEED = 43\n # Python原生随机种子\n random.seed(SEED)\n # Numpy随机种子（ShiftScaleRotate依赖）\n np.random.seed(SEED)\n # PyTorch CPU/GPU种子\n torch.manual_seed(SEED)\n torch.cuda.manual_seed(SEED)\n torch.cuda.manual_seed_all(SEED)\n # 强制CUDA算子确定性\n torch.backends.cudnn.deterministic = True\n torch.backends.cudnn.benchmark = False\n # Python哈希种子\n os.environ['PYTHONHASHSEED'] = str(SEED)\n \n print(\"🚀 Starting ConvNext Inference...\")\n \n # Configuration\n model_dir = Path('/kaggle/input/csiro-exp3/convnext_exp3') \n img_size = 1000\n device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\n \n # Model Definition\n class BiomassModelConv(nn.Module):\n def __init__(self, model_name='convnext_small', pretrained=False):\n super().__init__()\n self.backbone = timm.create_model(model_name, pretrained=pretrained, num_classes=0, global_pool='avg')\n n_combined = self.backbone.num_features * 2\n self.head_total = nn.Sequential(nn.Linear(n_combined, n_combined//2), nn.GELU(), nn.Dropout(0.3), nn.Linear(n_combined//2, 1))\n self.head_gdm = nn.Sequential(nn.Linear(n_combined, n_combined//2), nn.GELU(), nn.Dropout(0.3), nn.Linear(n_combined//2, 1))\n self.head_green = nn.Sequential(nn.Linear(n_combined, n_combined//2), nn.GELU(), nn.Dropout(0.3), nn.Linear(n_combined//2, 1))\n\n self.softplus = nn.Softplus(beta=1.0)\n\n def forward(self, img_left, img_right):\n l, r = self.backbone(img_left), self.backbone(img_right)\n combined = torch.cat([l, r], dim=1)\n return (\n self.softplus(self.head_total(combined)),\n self.softplus(self.head_gdm(combined)),\n self.softplus(self.head_green(combined))\n )\n\n # Load Models\n models = []\n for fold in range(5):\n p = model_dir / f'best_model_fold{fold}.pth'\n if p.exists():\n try:\n m = BiomassModelConv()\n st = torch.load(p, map_location=device)\n st = {k.replace('module.', ''): v for k, v in st.items()}\n m.load_state_dict(st)\n m.eval().to(device)\n \n # PyTorch 2.0+ 加速推理\n if hasattr(torch, 'compile'):\n m = torch.compile(m, mode='max-autotune')\n \n models.append(m)\n print(f\" ✅ Loaded ConvNext Fold {fold}\")\n except Exception as e:\n print(f\" ❌ Error loading fold {fold}: {e}\")\n \n if not models:\n print(\"⚠️ No ConvNext models found. Saving dummy file.\")\n pd.DataFrame(columns=['base_id', 'Dry_Total_g', 'GDM_g', 'Dry_Green_g']).to_csv('preds_convnext_wide.csv', index=False)\n return\n\n # Dataset\n class TestDataset(Dataset):\n def __init__(self, img_dir, tf):\n self.paths = [os.path.join(img_dir, f) for f in os.listdir(img_dir) if f.lower().endswith(('.png', '.jpg'))]\n self.tf = tf\n def __len__(self): return len(self.paths)\n def __getitem__(self, idx):\n p = self.paths[idx]\n try:\n img = cv2.imread(p)\n if img is None: raise ValueError(\"Image not found\")\n img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n # 增加随机旋转增强（TTA多样性）\n if self.tf and len(self.tf.transforms) > 1:\n img = self.tf(image=img)['image']\n except:\n img = np.zeros((img_size, img_size*2, 3), dtype=np.uint8)\n if self.tf:\n img = self.tf(image=img)['image']\n \n h, w, _ = img.shape\n l = img[:, :w//2]\n r = img[:, w//2:]\n return l, r, os.path.splitext(os.path.basename(p))[0]\n\n # Inference with TTA\n # 增加更多样化的TTA策略\n tf_list = [\n A.Compose([A.Resize(img_size, img_size, interpolation=cv2.INTER_AREA), A.Normalize(), ToTensorV2()]),\n A.Compose([A.HorizontalFlip(p=1), A.Resize(img_size, img_size, interpolation=cv2.INTER_AREA), A.Normalize(), ToTensorV2()]),\n A.Compose([A.VerticalFlip(p=1), A.Resize(img_size, img_size, interpolation=cv2.INTER_AREA), A.Normalize(), ToTensorV2()]),\n A.Compose([A.ShiftScaleRotate(shift_limit=0.1, scale_limit=0.1, rotate_limit=15, p=1), \n A.Resize(img_size, img_size, interpolation=cv2.INTER_AREA), A.Normalize(), ToTensorV2()]),\n ]\n \n test_dir = '/kaggle/input/csiro-biomass/test'\n final_results = {}\n \n for tf_idx, tf in enumerate(tf_list):\n ds = TestDataset(test_dir, tf)\n dl = DataLoader(ds, batch_size=4, num_workers=0, shuffle=False, pin_memory=True) # 启用pin_memory加速\n \n with torch.no_grad():\n for l, r, ids in tqdm(dl, desc=f\"ConvNext View {tf_idx+1}/{len(tf_list)}\"):\n l, r = l.to(device, non_blocking=True), r.to(device, non_blocking=True)\n \n # Ensemble over folds\n batch_preds = []\n for m in models:\n t, g, gr = m(l, r)\n pred_tensor = torch.cat([t, g, gr], dim=1)\n batch_preds.append(pred_tensor.cpu().numpy())\n \n # Mean over folds\n avg_preds = np.mean(batch_preds, axis=0)\n \n for i, bid in enumerate(ids):\n if bid not in final_results: final_results[bid] = []\n final_results[bid].append(avg_preds[i])\n \n # 主动清理缓存\n if torch.cuda.is_available():\n torch.cuda.empty_cache()\n\n # TTA Average & Format\n rows = []\n for bid, preds_list in final_results.items():\n # 加权平均：原图权重更高\n if len(preds_list) == 4:\n weights = np.array([0.4, 0.2, 0.2, 0.2]) # 原图权重40%，其余各20%\n else:\n weights = np.ones(len(preds_list)) / len(preds_list)\n \n final_p = np.average(preds_list, axis=0, weights=weights)\n final_p = np.maximum(final_p, 0)\n rows.append({\n 'base_id': bid, \n 'Dry_Total_g': final_p[0], \n 'GDM_g': final_p[1], \n 'Dry_Green_g': final_p[2]\n })\n \n df_out = pd.DataFrame(rows)\n \n # 生物学约束后处理\n # 约束1: GDM >= Dry_Green\n df_out['GDM_g'] = np.maximum(df_out['GDM_g'], df_out['Dry_Green_g'] * 1.05)\n \n # 约束2: 极端值clip\n for col in ['Dry_Total_g', 'GDM_g', 'Dry_Green_g']:\n p01, p99 = df_out[col].quantile([0.01, 0.99])\n df_out[col] = df_out[col].clip(p01 * 0.8, p99 * 1.2)\n \n df_out.to_csv('preds_convnext_wide.csv', index=False)\n print(f\"✅ ConvNext predictions saved. (Processed {len(rows)} images)\")\n \n # 清理内存\n del models, dl, ds\n gc.collect()\n if torch.cuda.is_available():\n torch.cuda.empty_cache()\n\nif __name__ == \"__main__\":\n run_convnext_inference()","metadata":{"execution":{"iopub.execute_input":"2026-01-11T03:15:56.842482Z","iopub.status.busy":"2026-01-11T03:15:56.842162Z","iopub.status.idle":"2026-01-11T03:17:32.45826Z","shell.execute_reply":"2026-01-11T03:17:32.457696Z"},"papermill":{"duration":95.623698,"end_time":"2026-01-11T03:17:32.459397","exception":false,"start_time":"2026-01-11T03:15:56.835699","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"4108763c","cell_type":"markdown","source":"## Model 4 Dino3","metadata":{"papermill":{"duration":0.005959,"end_time":"2026-01-11T03:17:32.471932","exception":false,"start_time":"2026-01-11T03:17:32.465973","status":"completed"},"tags":[]}},{"id":"93b0d5a1","cell_type":"code","source":"# ====================================================================================\n# [Part 4] ViT DINO3 Tiled Inference (Score ~0.65)\n# ====================================================================================\nimport os\nimport cv2\nimport timm\nimport torch\nimport numpy as np\nimport pandas as pd\nimport torch.nn as nn\nimport albumentations as A\nimport torch.nn.functional as F\nfrom tqdm.auto import tqdm\nfrom albumentations.pytorch import ToTensorV2\nfrom torch.utils.data import Dataset, DataLoader\nimport gc\n\n# --- 1. Model Definitions (Tiled FiLM DINO) ---\ndef get_input_size(model):\n # Helper to guess input size from timm model\n if hasattr(model, \"patch_embed\") and hasattr(model.patch_embed, \"img_size\"):\n return model.patch_embed.img_size[0]\n return 518 # Default for DINOv2/v3\n\nclass FiLM(nn.Module):\n def __init__(self, feat_dim):\n super().__init__()\n hidden = max(32, feat_dim // 2)\n self.mlp = nn.Sequential(\n nn.Linear(feat_dim, hidden), nn.ReLU(inplace=True), nn.Linear(hidden, feat_dim * 2)\n )\n def forward(self, context):\n gamma_beta = self.mlp(context)\n return torch.chunk(gamma_beta, 2, dim=1)\n\nclass BaseDINO(nn.Module):\n def __init__(self, backbone_name):\n super().__init__()\n self.backbone = timm.create_model(backbone_name, pretrained=False, num_classes=0)\n self.feat_dim = self.backbone.num_features\n self.input_size = int(get_input_size(self.backbone))\n if isinstance(self.input_size, tuple): self.input_size = self.input_size[0]\n \n self.combined_dim = self.feat_dim * 2\n hidden_size = max(8, int(self.combined_dim * 0.25))\n dropout = 0.30\n\n def make_head():\n return nn.Sequential(\n nn.Linear(self.combined_dim, hidden_size),\n nn.ReLU(inplace=True),\n nn.Dropout(dropout),\n nn.Linear(hidden_size, 1),\n )\n self.head_green = make_head()\n self.head_clover = make_head()\n self.head_dead = make_head()\n self.softplus = nn.Softplus(beta=1.0)\n\n def merge_features(self, left_feat, right_feat):\n combined = torch.cat([left_feat, right_feat], dim=1)\n green = self.softplus(self.head_green(combined))\n clover = self.softplus(self.head_clover(combined))\n dead = self.softplus(self.head_dead(combined))\n gdm = green + clover\n total = gdm + dead\n return total, gdm, green\n\ndef split_dimension(length, parts):\n step = length // parts\n segments = []\n start = 0\n for _ in range(parts - 1):\n segments.append((start, start + step))\n start += step\n segments.append((start, length))\n return segments\n\nclass TiledFiLMDINO(BaseDINO):\n def __init__(self, backbone_name):\n super().__init__(backbone_name)\n self.grid = (2, 2)\n self.film_left = FiLM(self.feat_dim)\n self.film_right = FiLM(self.feat_dim)\n\n def extract_tile_features(self, x):\n B, C, H, W = x.shape\n rows, cols = self.grid\n row_segments = split_dimension(H, rows)\n col_segments = split_dimension(W, cols)\n features = []\n for (rs, re) in row_segments:\n for (cs, ce) in col_segments:\n tile = x[:, :, rs:re, cs:ce]\n # Dynamic resize if needed\n if tile.shape[-2:] != (self.input_size, self.input_size):\n tile = F.interpolate(tile, size=(self.input_size, self.input_size), mode=\"bilinear\")\n feat = self.backbone(tile)\n features.append(feat)\n return torch.stack(features, dim=0).permute(1, 0, 2)\n\n def process_stream(self, x, film_layer):\n tiles = self.extract_tile_features(x)\n context = tiles.mean(dim=1)\n gamma, beta = film_layer(context)\n modulated = tiles * (1 + gamma.unsqueeze(1)) + beta.unsqueeze(1)\n return modulated.mean(dim=1)\n\n def forward(self, left_img, right_img):\n left_feat = self.process_stream(left_img, self.film_left)\n right_feat = self.process_stream(right_img, self.film_right)\n return self.merge_features(left_feat, right_feat)\n\n# --- 2. Inference Logic ---\ndef run_dino3_inference():\n print(\"🚀 Starting Part 4: ViT DINO3 Inference...\")\n DEVICE = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n \n # 路径设置\n model_dir = \"/kaggle/input/csiro-mvp-models\" # 你的新模型存放路径\n test_dir = '/kaggle/input/csiro-biomass/test' # 比赛测试集图片路径\n \n # 查找模型权重\n if not os.path.exists(model_dir):\n print(\"⚠️ Model dir not found. Creating dummy output.\")\n pd.DataFrame(columns=['base_id', 'Dry_Total_g', 'GDM_g', 'Dry_Green_g']).to_csv('preds_dino3_wide.csv', index=False)\n return\n\n model_paths = [os.path.join(model_dir, f\"model{i}.pth\") for i in range(1, 11)]\n model_paths = [p for p in model_paths if os.path.exists(p)]\n # 限制模型数量以防超时 (例如只用前5个fold)\n model_paths = model_paths[:5] \n \n if not model_paths:\n print(\"⚠️ No .pth files found in dir. Creating dummy output.\")\n pd.DataFrame(columns=['base_id', 'Dry_Total_g', 'GDM_g', 'Dry_Green_g']).to_csv('preds_dino3_wide.csv', index=False)\n return\n\n # 尝试匹配架构\n backbones = [\n \"vit_base_patch14_reg4_dinov3\", \"vit_base_patch14_dinov3\", \n \"vit_small_patch14_dinov3\", \"vit_base_patch14_reg4_dinov2\"\n ]\n\n # 加载模型\n models = []\n print(f\" Found {len(model_paths)} checkpoints.\")\n \n for path in model_paths:\n try:\n ckpt = torch.load(path, map_location=DEVICE)\n # Clean state dict keys\n st = ckpt['state_dict'] if 'state_dict' in ckpt else ckpt\n st = {k.replace('module.', '').replace('student.', ''): v for k,v in st.items()}\n \n loaded = False\n for bb in backbones:\n try:\n m = TiledFiLMDINO(bb)\n # Use strict=False to ignore minor mismatches if any\n m.load_state_dict(st, strict=False) \n m.to(DEVICE).eval()\n models.append(m)\n loaded = True\n # print(f\" Loaded {os.path.basename(path)} as {bb}\")\n break\n except:\n continue\n if not loaded: print(f\" Could not match architecture for {path}\")\n except Exception as e:\n print(f\" Error loading {path}: {e}\")\n\n if not models:\n print(\"⚠️ Failed to load any models.\")\n return\n\n # 准备数据集\n input_size = models[0].input_size\n print(f\" Input size inferred: {input_size}\")\n\n class SimpleTestDataset(Dataset):\n def __init__(self, img_dir, tf):\n self.files = [f for f in os.listdir(img_dir) if f.lower().endswith(('.png', '.jpg'))]\n self.img_dir = img_dir\n self.tf = tf\n def __len__(self): return len(self.files)\n def __getitem__(self, idx):\n f = self.files[idx]\n path = os.path.join(self.img_dir, f)\n img = cv2.imread(path)\n if img is None: img = np.zeros((1000, 2000, 3), dtype=np.uint8)\n else: img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n \n h, w, _ = img.shape\n l = self.tf(image=img[:, :w//2])['image']\n r = self.tf(image=img[:, w//2:])['image']\n return l, r, os.path.splitext(f)[0]\n\n # TTA Transforms\n norm = [A.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]), ToTensorV2()]\n ttas = [\n A.Compose([A.Resize(input_size, input_size, interpolation=cv2.INTER_AREA), *norm]),\n A.Compose([A.HorizontalFlip(p=1), A.Resize(input_size, input_size, interpolation=cv2.INTER_AREA), *norm]),\n ]\n \n # Inference\n final_results = {} # id -> list of [total, gdm, green]\n\n for tta_idx, tf in enumerate(ttas):\n ds = SimpleTestDataset(test_dir, tf)\n dl = DataLoader(ds, batch_size=4, num_workers=0, shuffle=False)\n \n with torch.no_grad():\n for l_img, r_img, ids in tqdm(dl, desc=f\"DINO3 TTA {tta_idx+1}\"):\n l_img, r_img = l_img.to(DEVICE), r_img.to(DEVICE)\n \n # Stack preds from all loaded fold models\n fold_preds = []\n for m in models:\n p_tot, p_gdm, p_grn = m(l_img, r_img)\n # Stack: (B, 3)\n pred = torch.stack([p_tot, p_gdm, p_grn], dim=1).squeeze(-1) \n fold_preds.append(pred.cpu().numpy())\n \n # Average over folds\n avg_folds = np.mean(fold_preds, axis=0) # (B, 3)\n \n for i, base_id in enumerate(ids):\n if base_id not in final_results: final_results[base_id] = []\n final_results[base_id].append(avg_folds[i])\n\n # Aggregate TTA and Format\n rows = []\n for bid, preds_list in final_results.items():\n # Average over TTA\n p = np.mean(preds_list, axis=0)\n p = np.maximum(p, 0)\n rows.append({\n 'base_id': bid,\n 'Dry_Total_g': p[0],\n 'GDM_g': p[1],\n 'Dry_Green_g': p[2]\n })\n \n df = pd.DataFrame(rows)\n df.to_csv('preds_dino3_wide.csv', index=False)\n print(f\"✅ DINO3 predictions saved. Shape: {df.shape}\")\n \n # Cleanup\n del models, dl, ds\n gc.collect()\n torch.cuda.empty_cache()\n\nif __name__ == \"__main__\":\n run_dino3_inference()","metadata":{"execution":{"iopub.execute_input":"2026-01-11T03:17:32.485144Z","iopub.status.busy":"2026-01-11T03:17:32.484932Z","iopub.status.idle":"2026-01-11T03:18:02.610642Z","shell.execute_reply":"2026-01-11T03:18:02.609804Z"},"papermill":{"duration":30.134112,"end_time":"2026-01-11T03:18:02.611978","exception":false,"start_time":"2026-01-11T03:17:32.477866","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"9e4f46ba","cell_type":"markdown","source":"## Model5 SigEngine","metadata":{"papermill":{"duration":0.006471,"end_time":"2026-01-11T03:18:02.625114","exception":false,"start_time":"2026-01-11T03:18:02.618643","status":"completed"},"tags":[]}},{"id":"1fe19339","cell_type":"code","source":"import os\nimport glob\nfrom pathlib import Path\nimport sys\nfrom tqdm.auto import tqdm\nimport json\nfrom copy import deepcopy\n\nimport pandas as pd\nimport numpy as np\nimport os\nimport math\nimport random\n\nimport torch\nimport torch.nn as nn\nfrom torchvision import transforms\n\nfrom PIL import Image\nimport cv2\n\nfrom transformers import AutoProcessor, AutoImageProcessor, AutoModel, Siglip2Model, Siglip2ImageProcessor, SiglipModel, SiglipImageProcessor\nfrom sklearn.model_selection import KFold, GroupKFold\nfrom sklearn.linear_model import LinearRegression, Ridge, Lasso, BayesianRidge\nfrom sklearn.svm import SVR\nfrom sklearn.ensemble import GradientBoostingRegressor, HistGradientBoostingRegressor, ExtraTreesRegressor\nfrom xgboost import XGBRegressor\nfrom lightgbm import LGBMRegressor\nfrom catboost import CatBoostRegressor\nfrom sklearn.svm import LinearSVR\nfrom sklearn.dummy import DummyRegressor\n\nfrom sklearn.decomposition import PCA\nfrom sklearn import model_selection\nfrom sklearn import preprocessing\n\nfrom dataclasses import dataclass\nfrom typing import Optional, Dict\n\nimport matplotlib.pyplot as plt\n\ndef seeding(SEED):\n np.random.seed(SEED)\n random.seed(SEED)\n os.environ['PYTHONHASHSEED'] = str(SEED)\n torch.manual_seed(SEED)\n # pl.seed_everything(SEED)\n if torch.cuda.is_available(): \n torch.cuda.manual_seed(SEED)\n torch.cuda.manual_seed_all(SEED)\n torch.backends.cudnn.deterministic = True\n torch.backends.cudnn.benchmark = False\n print('seeding done!!!')\n\ndef flush():\n import gc\n gc.collect()\n if torch.cuda.is_available():\n torch.cuda.empty_cache()\n torch.cuda.reset_peak_memory_stats()\n\nseeding(43)\n\n@dataclass\nclass Config:\n # Data paths\n DATA_PATH: Path = Path(\"/kaggle/input/csiro-biomass/\")\n TRAIN_DATA_PATH: Path = DATA_PATH/'train'\n TEST_DATA_PATH: Path = DATA_PATH/'test'\n\n device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n seed = 42\n\ncfg = Config()\nseeding(cfg.seed)\n\ndef pivot_table(df: pd.DataFrame)->pd.DataFrame:\n\n if 'target' in df.columns.tolist():\n df_pt = pd.pivot_table(\n df, \n values='target', \n index=['image_path', 'Sampling_Date', 'State', 'Species', 'Pre_GSHH_NDVI', 'Height_Ave_cm'], \n columns='target_name', \n aggfunc='mean'\n ).reset_index()\n else:\n df['target'] = 0\n df_pt = pd.pivot_table(\n df, \n values='target', \n index='image_path', \n columns='target_name', \n aggfunc='mean'\n ).reset_index()\n return df_pt\n\n# train_df = pd.read_csv(cfg.DATA_PATH/'train.csv')\ntest_df = pd.read_csv(cfg.DATA_PATH/'test.csv')\n# train_df = pivot_table(df=train_df)\ntest_df = pivot_table(df=test_df)\n\n# train_df['image_path'] = train_df['image_path'].apply(lambda p: str(cfg.DATA_PATH / p))\ntest_df['image_path'] = test_df['image_path'].apply(lambda p: str(cfg.DATA_PATH / p))\n# test_df.head()\n\ntrain_df = pd.read_csv(\"/kaggle/input/k/samu2505/csiro-datasplit/csiro_data_split.csv\")\n\n# 1. 定义要排除的 ID (转换为字符串以确保匹配)\nexclude_ids = [\n '230058600', '1403107574', \n 'ID230058600', 'ID1403107574'\n]\n\n# 2. 确保从 image_path 中提取出的 ID 与排除列表格式一致\n# 截图中的路径是：/kaggle/input/csiro-biomass/train/ID1011485656.jpg\ndef extract_id(path):\n # os.path.basename 得到 \"ID1011485656.jpg\"\n # split('.')[0] 得到 \"ID1011485656\"\n return os.path.basename(str(path)).split('.')[0]\n\ntrain_df['temp_check_id'] = train_df['image_path'].apply(extract_id)\n\n# 3. 执行过滤\ninitial_count = len(train_df)\ntrain_df = train_df[~train_df['temp_check_id'].isin(exclude_ids)].reset_index(drop=True)\n\n# 4. 删除临时列\ntrain_df = train_df.drop(columns=['temp_check_id'])\n\nprint(f\"⚠️ 数据清洗结果：\")\nprint(f\" 原始行数: {initial_count}\")\nprint(f\" 过滤后行数: {len(train_df)}\")\n\n\ndef melt_table(df: pd.DataFrame) -> pd.DataFrame:\n TARGET_NAMES = ['Dry_Clover_g', 'Dry_Dead_g', 'Dry_Green_g', 'Dry_Total_g', 'GDM_g']\n melted = df.melt(\n id_vars='image_path',\n value_vars=TARGET_NAMES,\n var_name='target_name',\n value_name='target'\n )\n melted['sample_id'] = (\n melted['image_path']\n .str.replace(r'^.*/', '', regex=True) # remove folder path, keep filename\n .str.replace('.jpg', '', regex=False) # remove extension\n + '__' + melted['target_name']\n )\n \n return melted[['sample_id', 'image_path', 'target_name', 'target']]\n\n\ndef split_image(image, patch_size=520, overlap=16):\n h, w, c = image.shape\n stride = patch_size - overlap\n \n patches = []\n coords = [] # (y1, x1, y2, x2)\n \n for y in range(0, h, stride):\n for x in range(0, w, stride):\n y1 = y\n x1 = x\n y2 = y + patch_size\n x2 = x + patch_size\n \n # Pad last patch if needed (very rare with your fixed 1000×2000)\n patch = image[y1:y2, x1:x2, :]\n if patch.shape[0] < patch_size or patch.shape[1] < patch_size:\n pad_h = patch_size - patch.shape[0]\n pad_w = patch_size - patch.shape[1]\n patch = np.pad(patch, ((0,pad_h), (0,pad_w), (0,0)), mode='reflect')\n \n patches.append(patch)\n coords.append((y1, x1, y2, x2))\n \n return patches, coords\n\ndef get_model(model_path: str, device: str = 'cpu'):\n model = AutoModel.from_pretrained(\n model_path,\n local_files_only=True\n )\n processor = AutoImageProcessor.from_pretrained(model_path)\n return model.eval().to(device), processor\n\ndino_path = \"/kaggle/input/dinov2/pytorch/giant/1\"\nsiglip_path = \"/kaggle/input/google-siglip-so400m-patch14-384/transformers/default/1\"\n\ndef compute_embeddings(model_path, df, patch_size=520):\n device = 'cuda' if torch.cuda.is_available() else 'cpu'\n print(device)\n\n model, processor = get_model(\n model_path=model_path, device=device\n )\n\n IMAGE_PATHS = []\n EMBEDDINGS = []\n\n for i, row in tqdm(df.iterrows(), total=len(df)):\n img_path = row['image_path']\n img = cv2.imread(img_path, cv2.IMREAD_COLOR)\n patches, coords = split_image(img, patch_size=patch_size)\n images = [Image.fromarray(p).convert(\"RGB\") for p in patches]\n\n inputs = processor(images=images, return_tensors=\"pt\").to(model.device)\n with torch.no_grad():\n if 'siglip' in model_path:\n features = model.get_image_features(**inputs)\n elif 'dino' in model_path:\n features = model(**inputs).pooler_output\n # patches = model(**inputs).last_hidden_state\n # features = patches[:, 0, :]\n else:\n raise Exception(\"Model should be dino or siglip\")\n embeds = features.mean(dim=0).detach().cpu().numpy()\n EMBEDDINGS.append(embeds)\n IMAGE_PATHS.append(img_path)\n\n embeddings = np.stack(EMBEDDINGS, axis=0)\n n_features = embeddings.shape[1]\n emb_columns = [f\"emb{i+1}\" for i in range(n_features)]\n emb_df = pd.DataFrame(embeddings, columns=emb_columns)\n emb_df['image_path'] = IMAGE_PATHS\n df_final = df.merge(emb_df, on='image_path', how='left')\n flush()\n return df_final \n\n# train_siglip_df = compute_embeddings(model_path=siglip_path, df=train_df, patch_size=520)\ntrain_siglip_df = train_df.copy()\ntest_siglip_df = compute_embeddings(model_path=siglip_path, df=test_df, patch_size=520)\n\nflush()\n\ndef generate_semantic_features(image_embeddings, model_path=siglip_path):\n \"\"\"\n Generates 'Concept Scores' by averaging synonyms and calculating biological ratios.\n \"\"\"\n print(f\"Loading SigLIP Text Encoder from {model_path}...\")\n device = 'cuda' if torch.cuda.is_available() else 'cpu'\n \n try:\n model = AutoModel.from_pretrained(model_path).to(device)\n tokenizer = AutoTokenizer.from_pretrained(model_path)\n except Exception as e:\n print(f\"Error loading model: {e}\")\n return None\n\n # 1. Define Concept Ensembles (Grouping synonyms reduces noise)\n concept_groups = {\n # Quantity Anchors\n \"bare\": [\"bare soil\", \"dirt ground\", \"sparse vegetation\", \"exposed earth\"],\n \"sparse\": [\"low density pasture\", \"thin grass\", \"short clipped grass\"],\n \"medium\": [\"average pasture cover\", \"medium height grass\", \"grazed pasture\"],\n \"dense\": [\"dense tall pasture\", \"thick grassy volume\", \"high biomass\", \"overgrown vegetation\"],\n \n # State Anchors\n \"green\": [\"lush green vibrant pasture\", \"photosynthesizing leaves\", \"fresh growth\"],\n \"dead\": [\"dry brown dead grass\", \"yellow straw\", \"senesced material\", \"standing hay\"],\n \n # Species Anchors\n \"clover\": [\"white clover\", \"trifolium repens\", \"broadleaf legume\", \"clover flowers\"],\n \"grass\": [\"ryegrass\", \"blade-like leaves\", \"fescue\", \"grassy sward\"],\n \"weeds\": [\"broadleaf weeds\", \"thistles\", \"non-pasture vegetation\"]\n }\n \n # 2. Encode and Average Prompts for each Concept\n concept_vectors = {}\n with torch.no_grad():\n for name, prompts in concept_groups.items():\n inputs = tokenizer(prompts, padding=\"max_length\", return_tensors=\"pt\").to(device)\n emb = model.get_text_features(**inputs)\n emb = emb / emb.norm(p=2, dim=-1, keepdim=True)\n # Average the embeddings of synonyms to get a stable \"Concept Vector\"\n concept_vectors[name] = emb.mean(dim=0, keepdim=True)\n\n # 3. Compute Concept Scores\n if isinstance(image_embeddings, np.ndarray):\n img_tensor = torch.tensor(image_embeddings, dtype=torch.float32).to(device)\n else:\n img_tensor = image_embeddings.to(device)\n img_tensor = img_tensor / img_tensor.norm(p=2, dim=-1, keepdim=True)\n\n scores = {}\n for name, vec in concept_vectors.items():\n # Dot product\n scores[name] = torch.matmul(img_tensor, vec.T).cpu().numpy().flatten()\n \n # 4. Feature Engineering: Explicit Ratios\n # These help models distinguish between \"High Biomass Dead\" vs \"High Biomass Green\"\n \n # Convert dict to DataFrame for easy math\n df_scores = pd.DataFrame(scores)\n \n # A. Greenness Ratio: Green / (Green + Dead)\n df_scores['ratio_greenness'] = df_scores['green'] / (df_scores['green'] + df_scores['dead'] + 1e-6)\n \n # B. Legume Fraction: Clover / (Clover + Grass)\n df_scores['ratio_clover'] = df_scores['clover'] / (df_scores['clover'] + df_scores['grass'] + 1e-6)\n \n # C. Vegetation Cover: (Dense + Medium) / (Bare + Sparse)\n df_scores['ratio_cover'] = (df_scores['dense'] + df_scores['medium']) / (df_scores['bare'] + df_scores['sparse'] + 1e-6)\n \n # D. \"Volume\": Max of density anchors\n df_scores['max_density'] = df_scores[['bare', 'sparse', 'medium', 'dense']].max(axis=1)\n\n print(f\"Generated {df_scores.shape[1]} semantic features (Ensembles + Ratios).\")\n return df_scores.values\n\n\nimport numpy as np\nfrom sklearn.base import BaseEstimator, TransformerMixin\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.decomposition import PCA\nfrom sklearn.cross_decomposition import PLSRegression\nfrom sklearn.mixture import GaussianMixture\nfrom sklearn.linear_model import BayesianRidge\nfrom sklearn.metrics.pairwise import cosine_similarity\n\n\nclass SupervisedEmbeddingEngine(BaseEstimator, TransformerMixin):\n def __init__(self, \n n_pca=0.98, # Slightly higher to keep texture details\n n_pls=8, # Keep 8, it worked well\n n_gmm=5, \n random_state=42):\n \n self.n_pca = n_pca\n self.n_pls = n_pls\n self.n_gmm = n_gmm\n self.random_state = random_state\n \n self.scaler = StandardScaler()\n self.pca = PCA(n_components=n_pca, random_state=random_state)\n self.pls = PLSRegression(n_components=n_pls, scale=False)\n self.gmm = GaussianMixture(n_components=n_gmm, covariance_type='diag', random_state=random_state)\n\n self.pls_fitted_ = False\n\n def fit(self, X, y=None, X_semantic=None):\n # 1. Standard Scaling on IMAGE embeddings only\n X_scaled = self.scaler.fit_transform(X)\n \n # 2. Fit Unsupervised on IMAGES\n self.pca.fit(X_scaled)\n self.gmm.fit(X_scaled)\n \n # 3. Fit PLS on IMAGES (Supervised)\n if y is not None:\n y_clean = y.values if hasattr(y, 'values') else y\n self.pls.fit(X_scaled, y_clean)\n self.pls_fitted_ = True\n \n return self\n\n def transform(self, X, X_semantic=None):\n X_scaled = self.scaler.transform(X)\n return self._generate_features(X_scaled, X_semantic)\n\n def _generate_features(self, X_scaled, X_semantic=None):\n features = []\n \n # A. PCA (Texture/Structure from Images)\n f_pca = self.pca.transform(X_scaled)\n features.append(f_pca)\n \n # B. PLS (Biomass-correlated signals from Images)\n if self.pls_fitted_:\n f_pls = self.pls.transform(X_scaled)\n features.append(f_pls)\n \n # C. GMM (Cluster probs)\n f_gmm = self.gmm.predict_proba(X_scaled)\n features.append(f_gmm)\n \n # D. Semantic Features (LATE FUSION)\n # We append them raw. They are already high-level signals.\n if X_semantic is not None:\n # Normalize semantic scores relative to themselves to match scale of PCA/PLS\n sem_norm = (X_semantic - np.mean(X_semantic, axis=0)) / (np.std(X_semantic, axis=0) + 1e-6)\n features.append(sem_norm)\n\n return np.hstack(features)\n\nCOLUMNS = train_df.filter(like=\"emb\").columns\nTARGET_NAMES = ['Dry_Clover_g', 'Dry_Dead_g', 'Dry_Green_g', 'Dry_Total_g', 'GDM_g']\nweights = {\n 'Dry_Green_g': 0.1,\n 'Dry_Dead_g': 0.1,\n 'Dry_Clover_g': 0.1,\n 'GDM_g': 0.2,\n 'Dry_Total_g': 0.5,\n}\n\nTARGET_MAX = {\n \"Dry_Clover_g\": 71.7865,\n \"Dry_Dead_g\": 83.8407,\n \"Dry_Green_g\": 157.9836,\n \"Dry_Total_g\": 185.70,\n \"GDM_g\": 157.9836,\n}\n\ndef competition_metric(y_true, y_pred) -> float:\n y_weighted = 0\n for l, label in enumerate(TARGET_NAMES):\n y_weighted = y_weighted + y_true[:, l].mean() * weights[label]\n\n ss_res = 0\n ss_tot = 0\n for l, label in enumerate(TARGET_NAMES):\n ss_res = ss_res + ((y_true[:, l] - y_pred[:, l])**2).mean() * weights[label]\n ss_tot = ss_tot + ((y_true[:, l] - y_weighted)**2).mean() * weights[label]\n\n return 1 - ss_res / ss_tot\n\n\ndef post_process_biomass(df_preds):\n \"\"\"\n Enforces physical mass balance constraints on biomass predictions.\n \n Constraints enforced:\n 1. Dry_Green_g + Dry_Clover_g = GDM_g\n 2. GDM_g + Dry_Dead_g = Dry_Total_g\n \n Method:\n Uses Orthogonal Projection. It finds the set of values that satisfy\n the constraints while minimizing the Euclidean distance to the \n original model predictions.\n \n Args:\n df_preds (pd.DataFrame): DataFrame containing the 5 prediction columns.\n \n Returns:\n pd.DataFrame: A new DataFrame with consistent, non-negative values.\n \"\"\"\n # 1. Define the specific order required for the math\n # We treat the vector x as: [Green, Clover, Dead, GDM, Total]\n ordered_cols = [\n \"Dry_Green_g\", \n \"Dry_Clover_g\", \n \"Dry_Dead_g\", \n \"GDM_g\", \n \"Dry_Total_g\"\n ]\n \n # Check if columns exist\n if not all(col in df_preds.columns for col in ordered_cols):\n missing = [c for c in ordered_cols if c not in df_preds.columns]\n raise ValueError(f\"Input DataFrame is missing columns: {missing}\")\n\n # 2. Extract values in the specific order -> Shape (N_samples, 5)\n Y = df_preds[ordered_cols].values.T # Transpose to (5, N) for matrix math\n\n # 3. Define the Constraint Matrix C\n # We want Cx = 0\n # Eq 1: 1*Green + 1*Clover + 0*Dead - 1*GDM + 0*Total = 0\n # Eq 2: 0*Green + 0*Clover + 1*Dead + 1*GDM - 1*Total = 0\n C = np.array([\n [1, 1, 0, -1, 0],\n [0, 0, 1, 1, -1]\n ])\n\n # 4. Calculate Projection Matrix P\n # P = I - C^T * (C * C^T)^-1 * C\n # This projects any vector onto the null space of C (the valid subspace)\n C_T = C.T\n inv_CCt = np.linalg.inv(C @ C_T)\n P = np.eye(5) - C_T @ inv_CCt @ C\n\n # 5. Apply Projection\n # Y_new = P * Y\n Y_reconciled = P @ Y\n\n # 6. Transpose back to (N, 5)\n Y_reconciled = Y_reconciled.T\n\n # 7. Post-correction for negatives\n # Projection can mathematically create negative values (e.g. if Total was predicted 0)\n # We clip to 0. Note: This might slightly break the sum equality again, \n # but exact equality with negatives is physically impossible anyway.\n Y_reconciled = Y_reconciled.clip(min=0)\n\n # 8. Create Output DataFrame\n df_out = df_preds.copy()\n df_out[ordered_cols] = Y_reconciled\n\n return df_out\n\ndef compare_results(oof, train_data):\n y_oof_df = pd.DataFrame(oof, columns=TARGET_NAMES) # ensure columns match\n # 2. Check Score BEFORE Processing\n raw_score = competition_metric(train_data[TARGET_NAMES].values, y_oof_df.values)\n print(f\"Raw CV Score: {raw_score:.6f}\")\n \n # 3. Apply Post-Processing\n y_oof_proc = post_process_biomass(y_oof_df)\n \n # 4. Check Score AFTER Processing\n proc_score = competition_metric(train_data[TARGET_NAMES].values, y_oof_proc.values)\n print(f\"Processed CV Score: {proc_score:.6f}\")\n \n print(f\"Improvement: {raw_score - proc_score:.6f}\")\n\n\n# Concatenate embeddings\nX_all_emb = np.vstack([\n train_siglip_df[COLUMNS].values, \n test_siglip_df[COLUMNS].values\n])\n\n# Generate Semantic Probes (Using the function defined in Part 1)\n# Make sure SIGLIP_PATH is correct for your environment\nprint(\"Generating Semantic Features via SigLIP Text Encoder...\")\ntry:\n all_semantic_scores = generate_semantic_features(X_all_emb, model_path=siglip_path)\n \n # Split back into Train and Test\n n_train = len(train_siglip_df)\n sem_train_full = all_semantic_scores[:n_train]\n sem_test_full = all_semantic_scores[n_train:]\n print(f\"Semantic Features Generated. Train: {sem_train_full.shape}, Test: {sem_test_full.shape}\")\n \nexcept Exception as e:\n print(f\"Skipping Semantic Features due to error: {e}\")\n # Fallback to None if model path is wrong or memory fails\n sem_train_full = None\n sem_test_full = None\n\n\n# --- STEP 2: Updated Cross-Validation Function ---\ndef cross_validate(model, train_data, test_data, feature_engine, \n semantic_train=None, semantic_test=None, # <--- NEW ARGS\n target_transform='max', seed=42):\n\n n_splits = train_data['fold'].nunique()\n # Setup Targets\n target_max_arr = np.array([TARGET_MAX[t] for t in TARGET_NAMES], dtype=float)\n y_true = train_data[TARGET_NAMES]\n \n # Setup Storage\n y_pred = pd.DataFrame(0.0, index=train_data.index, columns=TARGET_NAMES)\n y_pred_test = np.zeros([len(test_data), len(TARGET_NAMES)], dtype=float)\n\n for fold in range(n_splits):\n seeding(seed*(seed//2 + fold))\n # Create masks\n train_mask = train_data['fold'] != fold\n valid_mask = train_data['fold'] == fold\n val_idx = train_data[valid_mask].index\n\n # Raw Inputs (Embeddings)\n X_train_raw = train_data[train_mask][COLUMNS].values\n X_valid_raw = train_data[valid_mask][COLUMNS].values\n X_test_raw = test_data[COLUMNS].values\n \n # Semantic Inputs (Slicing)\n # We handle the case where semantic features might be None\n sem_train_fold = semantic_train[train_mask] if semantic_train is not None else None\n sem_valid_fold = semantic_train[valid_mask] if semantic_train is not None else None\n \n # Raw Targets\n y_train = train_data[train_mask][TARGET_NAMES].values\n y_valid = train_data[valid_mask][TARGET_NAMES].values\n\n # ===========================\n # 1) TRANSFORM TARGETS\n # ===========================\n if target_transform == 'log':\n y_train_proc = np.log1p(y_train)\n elif target_transform == 'max':\n y_train_proc = y_train / target_max_arr\n else:\n y_train_proc = y_train\n\n # ==========================================\n # 2) FEATURE ENGINEERING\n # ==========================================\n engine = deepcopy(feature_engine)\n \n # FIT: Now passes y (for PLS/RFE) and Semantic Features\n engine.fit(X_train_raw, y=y_train_proc, X_semantic=sem_train_fold)\n \n # TRANSFORM: Pass Semantic Features\n x_train_eng = engine.transform(X_train_raw, X_semantic=sem_train_fold)\n x_valid_eng = engine.transform(X_valid_raw, X_semantic=sem_valid_fold)\n # For test, we use the full test semantic set\n x_test_eng = engine.transform(X_test_raw, X_semantic=semantic_test)\n \n # ==========================================\n # 3) TRAIN & PREDICT\n # ==========================================\n fold_valid_pred = np.zeros_like(y_valid)\n fold_test_pred = np.zeros([len(test_data), len(TARGET_NAMES)])\n\n for k in range(len(TARGET_NAMES)):\n regr = deepcopy(model)\n \n # Fit model\n regr.fit(x_train_eng, y_train_proc[:, k])\n \n # Predict\n pred_valid_raw = regr.predict(x_valid_eng)\n pred_test_raw = regr.predict(x_test_eng)\n \n # ===========================\n # 4) INVERSE TRANSFORM\n # ===========================\n if target_transform == 'log':\n pred_valid_inv = np.expm1(pred_valid_raw)\n pred_test_inv = np.expm1(pred_test_raw)\n elif target_transform == 'max':\n pred_valid_inv = (pred_valid_raw * target_max_arr[k])\n pred_test_inv = (pred_test_raw * target_max_arr[k])\n else:\n pred_valid_inv = pred_valid_raw\n pred_test_inv = pred_test_raw\n\n fold_valid_pred[:, k] = pred_valid_inv\n fold_test_pred[:, k] = pred_test_inv\n\n # Store results\n y_pred.loc[val_idx] = fold_valid_pred\n y_pred_test += fold_test_pred / n_splits\n \n if fold == 0:\n print(f\" [Fold 0 Info] Target: {target_transform}, Feats: {x_train_eng.shape}\")\n\n full_cv = competition_metric(y_true.values, y_pred.values)\n print(f\"Full CV Score: {full_cv:.6f}\")\n \n return y_pred.values, y_pred_test\n\n# --- STEP 3: Run Models ---\n\n# Initialize the NEW Supervised Engine\nfeat_engine = SupervisedEmbeddingEngine(\n n_pca=0.80,\n n_pls=8, # Supervised signals\n n_gmm=6, # Soft clusters\n)\n\nprint(\"\\n###### GradientBoosting Regressor #######\")\noof_gb, pred_test_gb = cross_validate(\n GradientBoostingRegressor(), \n train_siglip_df, test_siglip_df, \n feature_engine=feat_engine,\n semantic_train=sem_train_full,\n semantic_test=sem_test_full\n)\ncompare_results(oof_gb, train_siglip_df)\n\nprint(\"\\n###### Hist Gradient Boosting Regressor ######\")\noof_hb, pred_test_hb = cross_validate(\n HistGradientBoostingRegressor(), \n train_siglip_df, test_siglip_df, \n feature_engine=feat_engine,\n semantic_train=sem_train_full,\n semantic_test=sem_test_full\n)\ncompare_results(oof_hb, train_siglip_df)\n\nprint(\"\\n##### CAT Regressor ######\")\noof_cat, pred_test_cat = cross_validate(\n CatBoostRegressor(verbose=0), \n train_siglip_df, test_siglip_df, \n feature_engine=feat_engine,\n semantic_train=sem_train_full,\n semantic_test=sem_test_full\n)\ncompare_results(oof_cat, train_siglip_df)\n\nprint(\"\\n######## LGBM #######\")\noof_lgbm, pred_test_lgbm = cross_validate(\n LGBMRegressor(verbose=-1), \n train_siglip_df, test_siglip_df, \n feature_engine=feat_engine, \n semantic_train=sem_train_full,\n semantic_test=sem_test_full,\n target_transform='max')\ncompare_results(oof_lgbm, train_siglip_df)\n\npred_test = (\n pred_test_hb\n #+ pred_test_gb\n + pred_test_cat\n + pred_test_lgbm\n) / 3\n\n# 2. 写入数据框并进行后处理（物理约束）\ntest_df[TARGET_NAMES] = pred_test\ntest_df = post_process_biomass(test_df)\n\n# 3. 【关键】提取 base_id（横版对齐的基准）\n# 确保 ID 格式为 \"1403107574\" 这种不带后缀的形式\ntest_df['base_id'] = test_df['image_path'].apply(lambda x: os.path.splitext(os.path.basename(x))[0])\n\n# 4. 定义集成脚本需要的列顺序 (宽表格式)\noutput_cols = ['base_id', 'Dry_Total_g', 'GDM_g', 'Dry_Green_g', 'Dry_Dead_g', 'Dry_Clover_g']\n\n# 5. 保存为横版 CSV\ntest_df[output_cols].to_csv(\"preds_siglip_engine_wide.csv\", index=False)\n\nprint(\"✅ SigEngine 已保存为横版格式，准备进入 Part 5 集成。\")\nprint(test_df[output_cols].head())\n","metadata":{"execution":{"iopub.execute_input":"2026-01-11T03:18:02.639296Z","iopub.status.busy":"2026-01-11T03:18:02.639086Z","iopub.status.idle":"2026-01-11T03:20:58.32073Z","shell.execute_reply":"2026-01-11T03:20:58.319569Z"},"papermill":{"duration":175.690809,"end_time":"2026-01-11T03:20:58.322157","exception":false,"start_time":"2026-01-11T03:18:02.631348","status":"completed"},"tags":[]},"outputs":[],"execution_count":null},{"id":"2be087e4","cell_type":"markdown","source":"## Weighted Average Ensemble","metadata":{"papermill":{"duration":0.008196,"end_time":"2026-01-11T03:20:58.338694","exception":false,"start_time":"2026-01-11T03:20:58.330498","status":"completed"},"tags":[]}},{"id":"98687be4","cell_type":"code","source":"# ====================================================================================\n# [Part 5 Final] Robust Arithmetic Ensemble & Orthogonal Projection\n# ====================================================================================\nimport pandas as pd\nimport numpy as np\nimport os\nimport glob\nimport warnings\n\n# 忽略 pandas 的 FutureWarning\nwarnings.filterwarnings('ignore')\n\ndef robust_arithmetic_ensemble_inference():\n print(\"🏁 Starting Robust Arithmetic Ensemble (No Scaling, With Projection)...\")\n \n targets = ['Dry_Total_g', 'GDM_g', 'Dry_Green_g', 'Dry_Dead_g', 'Dry_Clover_g']\n \n # 1. 定义文件和权重\n model_configs = {\n 'DINOMamba': {'file': 'preds_dino_wide.csv', 'weight': 0.35}, \n 'D3': {'file': 'preds_dino3_wide.csv', 'weight': 0.20}, \n 'SigEngine': {'file': 'preds_siglip_engine_wide.csv', 'weight': 0.30}, \n 'CONV': {'file': 'preds_convnext_wide.csv', 'weight': 0.15} \n }\n \n # ❌ 移除全局缩放因子\n # SCALE_FACTOR = 1.02 \n\n loaded_dfs = {}\n valid_weights = {}\n \n print(\" Loading and Expanding predictions...\")\n for name, cfg in model_configs.items():\n fpath = cfg['file']\n if not os.path.exists(fpath):\n alt = os.path.join(\"/kaggle/working\", fpath)\n if os.path.exists(alt): fpath = alt\n\n if os.path.exists(fpath):\n df = pd.read_csv(fpath)\n df['base_id'] = df['base_id'].astype(str)\n df = df.drop_duplicates(subset=['base_id']).set_index('base_id')\n \n # 基础清洗\n for c in ['Dry_Total_g', 'GDM_g', 'Dry_Green_g']:\n if c in df.columns: df[c] = df[c].clip(lower=0)\n\n # 补全逻辑\n if 'Dry_Dead_g' not in df.columns:\n safe_gdm = np.minimum(df['GDM_g'], df['Dry_Total_g'])\n df['Dry_Dead_g'] = df['Dry_Total_g'] - safe_gdm\n \n if 'Dry_Clover_g' not in df.columns:\n safe_green = np.minimum(df['Dry_Green_g'], df['GDM_g'])\n df['Dry_Clover_g'] = df['GDM_g'] - safe_green\n\n # 对齐列\n for t in targets:\n if t not in df.columns: df[t] = 0.0\n df = df[targets]\n \n loaded_dfs[name] = df\n valid_weights[name] = cfg['weight']\n print(f\" ✅ Loaded {name:<10} | Shape: {df.shape}\")\n else:\n print(f\" ⚠️ File not found: {fpath}\")\n\n # 权重归一化\n total_w = sum(valid_weights.values())\n if total_w == 0: return\n final_weights = {k: v / total_w for k, v in valid_weights.items()}\n print(f\"\\n Normalized Weights: {final_weights}\")\n \n # 对齐索引\n base_model = max(loaded_dfs, key=lambda k: len(loaded_dfs[k]))\n all_ids = loaded_dfs[base_model].index\n \n # ====================================================\n # 5. 回归到算术平均 (Arithmetic Mean)\n # ====================================================\n print(\" ⚖️ Weighted Arithmetic Averaging (Standard)...\")\n ensemble_df = pd.DataFrame(index=all_ids, columns=targets)\n ensemble_df[:] = 0\n \n for col in targets:\n weighted_sum = 0\n for name, weight in final_weights.items():\n # 获取数据，填充0，非负截断\n series = loaded_dfs[name][col].reindex(all_ids).fillna(0).clip(lower=0)\n # 普通加权\n weighted_sum += series * weight\n \n ensemble_df[col] = weighted_sum\n\n # ❌ 移除缩放\n # ensemble_df[targets] = ensemble_df[targets] * SCALE_FACTOR\n\n # ====================================================\n # 6. 正交投影修正 (Orthogonal Projection) - 这个保留！\n # ====================================================\n print(\" 🔧 Applying Orthogonal Projection (Physical Constraints)...\")\n \n def apply_projection(df):\n ordered_cols = [\"Dry_Green_g\", \"Dry_Clover_g\", \"Dry_Dead_g\", \"GDM_g\", \"Dry_Total_g\"]\n Y = df[ordered_cols].values.T\n \n # 物理约束矩阵 C (Green+Clover=GDM, Dead+GDM=Total)\n C = np.array([\n [1, 1, 0, -1, 0], \n [0, 0, 1, 1, -1] \n ])\n \n # 投影矩阵\n P = np.eye(5) - C.T @ np.linalg.inv(C @ C.T) @ C\n Y_new = P @ Y\n \n return pd.DataFrame(Y_new.T, columns=ordered_cols, index=df.index)\n\n # 执行投影\n corrected_df = apply_projection(ensemble_df)\n corrected_df[targets] = corrected_df[targets].clip(lower=0)\n ensemble_df = corrected_df[targets]\n\n # 生成提交\n print(\" 📝 Generating submission file...\")\n submission_rows = []\n targets_order = ['Dry_Clover_g', 'Dry_Dead_g', 'Dry_Green_g', 'Dry_Total_g', 'GDM_g']\n \n for base_id, row in ensemble_df.iterrows():\n for t in targets_order:\n submission_rows.append({\n 'sample_id': f\"{base_id}__{t}\",\n 'target': float(row[t])\n })\n \n sub_df = pd.DataFrame(submission_rows)\n sub_df.to_csv(\"submission.csv\", index=False)\n print(f\"🎉 FINAL SUBMISSION GENERATED: submission.csv\")\n print(f\" Shape: {sub_df.shape}\")\n print(sub_df.head(10))\n\nif __name__ == \"__main__\":\n robust_arithmetic_ensemble_inference()","metadata":{"execution":{"iopub.execute_input":"2026-01-11T03:20:58.356394Z","iopub.status.busy":"2026-01-11T03:20:58.35614Z","iopub.status.idle":"2026-01-11T03:20:58.411519Z","shell.execute_reply":"2026-01-11T03:20:58.41034Z"},"papermill":{"duration":0.06647,"end_time":"2026-01-11T03:20:58.413105","exception":false,"start_time":"2026-01-11T03:20:58.346635","status":"completed"},"tags":[]},"outputs":[],"execution_count":null}]}