{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":67836,"databundleVersionId":7527339,"sourceType":"competition"},{"sourceId":6063037,"sourceType":"datasetVersion","datasetId":3469773},{"sourceId":6063590,"sourceType":"datasetVersion","datasetId":3470137},{"sourceId":8521750,"sourceType":"datasetVersion","datasetId":5088299}],"dockerImageVersionId":30699,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"code","source":"from IPython.display import clear_output\n\n!pip install --no-index --no-deps /kaggle/input/mmdetectron-31-wheel/pycocotools-2.0.6-cp310-cp310-linux_x86_64.whl\n!pip install --no-index --no-deps /kaggle/input/mmdetectron-31-wheel/torch-1.12.1+cu116-cp310-cp310-linux_x86_64.whl\n!pip install --no-index --no-deps /kaggle/input/mmdetectron-31-wheel/torchvision-0.13.1+cu116-cp310-cp310-linux_x86_64.whl\n!pip install --no-index --no-deps /kaggle/input/mmdetectron-31-wheel/mmcv-2.0.1-cp310-cp310-manylinux1_x86_64.whl \n!pip install --no-index --no-deps /kaggle/input/mmdetectron-31-wheel/openmim-0.3.9-py2.py3-none-any.whl\n!pip install --no-index --no-deps /kaggle/input/mmdetectron-31-wheel/mmengine-0.7.4-py3-none-any.whl\n!pip install --no-index --no-deps /kaggle/input/mmdetectron-31-wheel/addict-2.4.0-py3-none-any.whl\n!pip install yapf==0.40.1\n!pip install --no-index --no-deps /kaggle/input/mmpretrain/einops-0.6.1-py3-none-any.whl\n!pip install --no-index --no-deps /kaggle/input/mmpretrain/mat4py-0.5.0-py2.py3-none-any.whl\n!pip install --no-index --no-deps /kaggle/input/mmpretrain/ordered_set-4.1.0-py3-none-any.whl\n!pip install --no-index --no-deps /kaggle/input/mmpretrain/model_index-0.1.11-py3-none-any.whl\n!pip install --no-index --no-deps /kaggle/input/mmpretrain/modelindex-0.0.2-py3-none-any.whl\n!pip install --no-index --no-deps /kaggle/input/mmpretrain/mmpretrain-1.0.0rc8-py2.py3-none-any.whl\nclear_output()","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-06-01T10:20:13.056862Z","iopub.execute_input":"2024-06-01T10:20:13.057108Z","iopub.status.idle":"2024-06-01T10:22:11.006648Z","shell.execute_reply.started":"2024-06-01T10:20:13.057085Z","shell.execute_reply":"2024-06-01T10:22:11.005494Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from tqdm.notebook import tqdm\nimport pandas as pd\n\nimport matplotlib.pyplot as plt\nfrom PIL import Image\n\nfrom glob import glob\nimport matplotlib.pyplot as plt","metadata":{"execution":{"iopub.status.busy":"2024-06-01T10:22:11.008936Z","iopub.execute_input":"2024-06-01T10:22:11.009246Z","iopub.status.idle":"2024-06-01T10:22:11.460717Z","shell.execute_reply.started":"2024-06-01T10:22:11.009217Z","shell.execute_reply":"2024-06-01T10:22:11.459894Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!git clone -bv3.1.0 https://github.com/open-mmlab/mmdetection.git\n%cd /kaggle/working/mmdetection\n!pip install -v -e .\n\n\nclear_output()","metadata":{"execution":{"iopub.status.busy":"2024-06-01T10:22:11.461826Z","iopub.execute_input":"2024-06-01T10:22:11.462283Z","iopub.status.idle":"2024-06-01T10:22:37.308396Z","shell.execute_reply.started":"2024-06-01T10:22:11.462248Z","shell.execute_reply":"2024-06-01T10:22:37.307222Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import torch, torchvision,mmdet\nprint(\"PyTorch version= \",torch.__version__,torch.cuda.is_available())\nprint(\"mmdet version= \",mmdet.__version__)\n\nfrom mmcv.ops import get_compiling_cuda_version\nprint(\"THE CUDA version \", get_compiling_cuda_version())","metadata":{"execution":{"iopub.status.busy":"2024-06-01T10:22:37.310402Z","iopub.execute_input":"2024-06-01T10:22:37.310821Z","iopub.status.idle":"2024-06-01T10:22:39.421092Z","shell.execute_reply.started":"2024-06-01T10:22:37.310783Z","shell.execute_reply":"2024-06-01T10:22:39.420146Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install -U openmim\nclear_output()","metadata":{"execution":{"iopub.status.busy":"2024-06-01T10:22:39.423002Z","iopub.execute_input":"2024-06-01T10:22:39.423401Z","iopub.status.idle":"2024-06-01T10:23:10.298186Z","shell.execute_reply.started":"2024-06-01T10:22:39.423376Z","shell.execute_reply":"2024-06-01T10:23:10.297038Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!mkdir -p configs/Enigma","metadata":{"execution":{"iopub.status.busy":"2024-06-01T10:23:10.299484Z","iopub.execute_input":"2024-06-01T10:23:10.299818Z","iopub.status.idle":"2024-06-01T10:23:11.247758Z","shell.execute_reply.started":"2024-06-01T10:23:10.299790Z","shell.execute_reply":"2024-06-01T10:23:11.246662Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"%%writefile configs/Enigma/custom_config.py\n\n_base_ = [\n    '../_base_/models/cascade-rcnn_r50_fpn.py',\n    '../_base_/datasets/coco_instance.py',\n    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'\n]\ncustom_imports = dict(\n    imports=['mmpretrain.models'], allow_failed_imports=False)\ncheckpoint_file = 'https://download.openmmlab.com/mmclassification/v0/convnext/downstream/convnext-small_3rdparty_32xb128-noema_in1k_20220301-303e75e3.pth' # noqa\n\nmodel = dict(\n    data_preprocessor=dict(\n        mean=[123.594, 122.142, 113.73],\n        std=[56.943, 54.945,  54.192]\n    ),  # train data distribution \n    backbone=dict(\n        _delete_=True,\n        type='mmpretrain.ConvNeXt',\n        arch='small',\n        out_indices=[0, 1, 2, 3],\n        drop_path_rate=0.6,\n        layer_scale_init_value=1.0,\n        gap_before_final_norm=False,\n        init_cfg=dict(\n            type='Pretrained', checkpoint=checkpoint_file,\n            prefix='backbone.')),\n    neck=dict(in_channels=[96, 192, 384, 768]),\n    roi_head=dict(bbox_head=[\n        dict(\n            type='ConvFCBBoxHead',\n            num_shared_convs=4,\n            num_shared_fcs=1,\n            in_channels=256,\n            conv_out_channels=256,\n            fc_out_channels=1024,\n            roi_feat_size=7,\n            num_classes=13,\n            bbox_coder=dict(\n                type='DeltaXYWHBBoxCoder',\n                target_means=[0., 0., 0., 0.],\n                target_stds=[0.1, 0.1, 0.2, 0.2]),\n            reg_class_agnostic=False,\n            reg_decoded_bbox=True,\n            norm_cfg=dict(type='SyncBN', requires_grad=True),\n            loss_cls=dict(\n                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),\n            loss_bbox=dict(type='GIoULoss', loss_weight=10.0)),\n        dict(\n            type='ConvFCBBoxHead',\n            num_shared_convs=4,\n            num_shared_fcs=1,\n            in_channels=256,\n            conv_out_channels=256,\n            fc_out_channels=1024,\n            roi_feat_size=7,\n            num_classes=13,\n            bbox_coder=dict(\n                type='DeltaXYWHBBoxCoder',\n                target_means=[0., 0., 0., 0.],\n                target_stds=[0.05, 0.05, 0.1, 0.1]),\n            reg_class_agnostic=False,\n            reg_decoded_bbox=True,\n            norm_cfg=dict(type='SyncBN', requires_grad=True),\n            loss_cls=dict(\n                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),\n            loss_bbox=dict(type='GIoULoss', loss_weight=10.0)),\n        dict(\n            type='ConvFCBBoxHead',\n            num_shared_convs=4,\n            num_shared_fcs=1,\n            in_channels=256,\n            conv_out_channels=256,\n            fc_out_channels=1024,\n            roi_feat_size=7,\n            num_classes=13,\n            bbox_coder=dict(\n                type='DeltaXYWHBBoxCoder',\n                target_means=[0., 0., 0., 0.],\n                target_stds=[0.033, 0.033, 0.067, 0.067]),\n            reg_class_agnostic=False,\n            reg_decoded_bbox=True,\n            norm_cfg=dict(type='SyncBN', requires_grad=True),\n            loss_cls=dict(\n                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),\n            loss_bbox=dict(type='GIoULoss', loss_weight=10.0))\n    ]),\n    test_cfg=dict(\n        rcnn=dict(\n            score_thr=0.05,\n            nms=dict(type='soft_nms', iou_threshold=0.5, min_score=0.05),\n            max_per_img=100))\n)\n\nclasses = ('auto_rickshaw',\n'bicycle',\n'bus',\n'car',\n'cart_vehicle',\n'construction_vehicle',\n'motorbike',\n'person',\n'priority_vehicle',\n'three_wheeler',\n'train',\n'truck',\n'wheelchair') # Added\nbackend_args = None\nepoch =12 \nbth_size = 2\ndata_root = '/kaggle/input/dl-enigma-cocodataset/' # Modified\ntrain_cfg = dict(type='EpochBasedTrainLoop', max_epochs=epoch, val_interval=1)\nval_cfg = dict(type='ValLoop')\ntest_cfg = dict(type='TestLoop')\n\noptim_wrapper = dict(\n    type='AmpOptimWrapper',\n    constructor='LearningRateDecayOptimizerConstructor',\n    paramwise_cfg={\n        'decay_rate': 0.7,\n        'decay_type': 'layer_wise',\n        'num_layers': 12\n    },\n    optimizer=dict(\n        _delete_=True,\n        type='AdamW',\n        lr=0.0002,\n        betas=(0.9, 0.999),\n        weight_decay=0.05))\n\nparam_scheduler = [\n    dict(type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=5000),\n    dict(\n        type='MultiStepLR',\n        begin=0,\n        end=epoch,\n        by_epoch=True,\n        milestones=[8, 10],\n        gamma=0.1)\n]\n\nimage_size = (1300, 1300)\nload_pipeline = [\n    dict(type='LoadImageFromFile', backend_args=backend_args),\n    dict(type='LoadAnnotations', with_bbox=True),\n    dict(\n        type='RandomResize',\n        scale=image_size,\n        scale_factor=1.0, \n        ratio_range=(0.8, 1.25),\n        keep_ratio=True),\n    dict(\n        type='RandomCrop',\n        crop_type='absolute_range',\n        crop_size=image_size,\n        recompute_bbox=True,\n        allow_negative_crop=True),\n    dict(type='FilterAnnotations', min_gt_bbox_wh=(1e-2, 1e-2)),\n    dict(type='RandomFlip', prob=0.5),\n    dict(type='Pad', size=image_size),\n]\n\n\ntrain_pipeline = [\n    dict(type='CopyPaste', max_num_pasted=100, paste_by_box=True),\n    dict(type='PackDetInputs')\n]\n\ntest_pipeline = [\n    dict(type='LoadImageFromFile', backend_args=backend_args),\n    dict(type='LoadAnnotations', with_bbox=True),\n    dict(\n        type='Resize',  # Orignial Size\n        scale=image_size,\n        keep_ratio=True  \n        ),\n    dict(\n        type='PackDetInputs',\n        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',\n                   'scale_factor'))\n]\n\ntrain_dataloader = dict(\n    batch_size=bth_size,\n    num_workers=4,\n    persistent_workers=True,\n    dataset=dict(\n        _delete_=True,\n        type='MultiImageMixDataset',\n        dataset=dict(\n            type='CocoDataset',\n            data_root=data_root,\n            metainfo=dict(classes=classes),\n            ann_file=data_root + 'annotations_train.json',\n            data_prefix=dict(img='train2017/'),\n            pipeline=load_pipeline,\n            backend_args=backend_args),\n        pipeline=train_pipeline))\n\n\nval_dataloader = dict(\n    batch_size=bth_size,\n    num_workers=4,\n    persistent_workers=True,\n    drop_last=False,\n    dataset=dict(\n        type='CocoDataset',\n        data_root=data_root,\n        metainfo=dict(classes=classes),\n        ann_file=data_root + 'annotations_valid.json',\n        data_prefix=dict(img='valid2017/'),\n        test_mode=True,\n        pipeline=test_pipeline,\n        backend_args=backend_args))\ntest_dataloader = val_dataloader\n\nval_evaluator = dict(\nann_file=data_root + 'annotations_valid.json', metric=['bbox'], classwise=True)\nload_from='https://download.openmmlab.com/mmdetection/v2.0/convnext/cascade_mask_rcnn_convnext-s_p4_w7_fpn_giou_4conv1f_fp16_ms-crop_3x_coco/cascade_mask_rcnn_convnext-s_p4_w7_fpn_giou_4conv1f_fp16_ms-crop_3x_coco_20220510_201004-3d24f5a4.pth'\ntest_evaluator = val_evaluator\nfp16=dict(loss_scale=512.)\nresume_from = None","metadata":{"_kg_hide-input":true,"execution":{"iopub.status.busy":"2024-06-01T11:24:50.043551Z","iopub.execute_input":"2024-06-01T11:24:50.043980Z","iopub.status.idle":"2024-06-01T11:24:50.055647Z","shell.execute_reply.started":"2024-06-01T11:24:50.043940Z","shell.execute_reply":"2024-06-01T11:24:50.054394Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!python tools/train.py /kaggle/working/mmdetection/configs/Enigma/custom_config.py","metadata":{"execution":{"iopub.status.busy":"2024-06-01T11:24:50.792018Z","iopub.execute_input":"2024-06-01T11:24:50.792381Z","iopub.status.idle":"2024-06-01T11:32:11.153202Z","shell.execute_reply.started":"2024-06-01T11:24:50.792354Z","shell.execute_reply":"2024-06-01T11:32:11.151882Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}