{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":19989,"databundleVersionId":1160143,"sourceType":"competition"},{"sourceId":6063037,"sourceType":"datasetVersion","datasetId":3469773},{"sourceId":6063590,"sourceType":"datasetVersion","datasetId":3470137},{"sourceId":7210148,"sourceType":"datasetVersion","datasetId":4116260},{"sourceId":8438567,"sourceType":"datasetVersion","datasetId":5026588}],"dockerImageVersionId":30588,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"## Previous Training method\n\n1. coco_dataset: https://www.kaggle.com/code/ishlove7/how-to-make-coco-dataset \n2. MM Detection FasterRCNN[Training] : https://www.kaggle.com/code/ishlove7/mm-detection-faster-rcnn-train\n3. MM Detection Resnext + CascadeRNN[Training] : https://www.kaggle.com/code/ishlove7/mm-detection-resnext-101-cascadercnn-training\n4. MM Detection Convnext + CascadeRCNN[Training] : https://www.kaggle.com/code/ishlove7/global-wheat-detection-convnext-cascadercnn\n5. MM Detection Submission[Infer] : https://www.kaggle.com/code/ishlove7/wheat-detection-inference-tta-wbf/notebook?scriptVersionId=178769791","metadata":{}},{"cell_type":"markdown","source":"## Install Package","metadata":{}},{"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\nclear_output()\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":{"execution":{"iopub.status.busy":"2024-05-21T13:58:05.165180Z","iopub.execute_input":"2024-05-21T13:58:05.165492Z","iopub.status.idle":"2024-05-21T13:58:20.072647Z","shell.execute_reply.started":"2024-05-21T13:58:05.165465Z","shell.execute_reply":"2024-05-21T13:58:20.071537Z"},"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":"2024-05-21T13:58:20.074096Z","iopub.execute_input":"2024-05-21T13:58:20.074409Z","iopub.status.idle":"2024-05-21T13:58:20.526286Z","shell.execute_reply.started":"2024-05-21T13:58:20.074383Z","shell.execute_reply":"2024-05-21T13:58:20.525492Z"},"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\nclear_output()","metadata":{"execution":{"iopub.status.busy":"2024-05-21T13:58:20.528490Z","iopub.execute_input":"2024-05-21T13:58:20.529038Z","iopub.status.idle":"2024-05-21T13:58:46.316421Z","shell.execute_reply.started":"2024-05-21T13:58:20.529001Z","shell.execute_reply":"2024-05-21T13:58:46.315251Z"},"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":"2024-05-21T13:58:46.317714Z","iopub.execute_input":"2024-05-21T13:58:46.317988Z","iopub.status.idle":"2024-05-21T13:58:48.488791Z","shell.execute_reply.started":"2024-05-21T13:58:46.317965Z","shell.execute_reply":"2024-05-21T13:58:48.487796Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!pip install -U openmim\nclear_output()","metadata":{"execution":{"iopub.status.busy":"2024-05-21T13:58:48.489940Z","iopub.execute_input":"2024-05-21T13:58:48.490413Z","iopub.status.idle":"2024-05-21T13:59:18.936764Z","shell.execute_reply.started":"2024-05-21T13:58:48.490384Z","shell.execute_reply":"2024-05-21T13:59:18.935662Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"!mkdir -p configs/wheat","metadata":{"execution":{"iopub.status.busy":"2024-05-21T13:59:18.938356Z","iopub.execute_input":"2024-05-21T13:59:18.938684Z","iopub.status.idle":"2024-05-21T13:59:19.895878Z","shell.execute_reply.started":"2024-05-21T13:59:18.938657Z","shell.execute_reply":"2024-05-21T13:59:19.894518Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Config","metadata":{}},{"cell_type":"code","source":"%%writefile configs/wheat/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]\n\n# please install mmpretrain\n# import mmpretrain.models to trigger register_module in mmpretrain\ncustom_imports = dict(\n    imports=['mmpretrain.models'], allow_failed_imports=False)\ncheckpoint_file = 'https://download.openmmlab.com/mmclassification/v0/convnext/downstream/convnext-tiny_3rdparty_32xb128-noema_in1k_20220301-795e9634.pth'  # noqa\n\nmodel = dict(\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=1,\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=1,\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=1,\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        _delete_=True,\n        rpn=dict(\n            nms_pre=1000,\n            max_per_img=1000,\n            nms=dict(type='nms', iou_threshold=0.7),\n            min_bbox_size=0),\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\n\n\n# Enable automatic-mixed-precision training with AmpOptimWrapper.\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\nclasses = ('wheat',) # Added\nbackend_args = None\ndata_root = '/kaggle/input/wheat-data/' # Modified\ntrain_cfg = dict(type='EpochBasedTrainLoop', max_epochs=16, val_interval=1)\nval_cfg = dict(type='ValLoop')\ntest_cfg = dict(type='TestLoop')\n\n\nparam_scheduler = [\n    dict(type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=2000),\n    dict(\n        type='MultiStepLR',\n        begin=0,\n        end=16,\n        by_epoch=True,\n        milestones=[8, 11],\n        gamma=0.1)\n]\nalbu_train_transforms = [\n    dict(\n        type='Sharpen',\n        alpha=(0.2, 0.7)\n    )\n]\n\nimg_scale = (1024, 1024)\ntrain_pipeline = [\n    dict(type='Mosaic', img_scale=img_scale, pad_val=114.0),\n    dict(\n        type='RandomAffine',\n        scaling_ratio_range=(0.1, 2),\n        # img_scale is (width, height)\n        border=(-img_scale[0] // 2, -img_scale[1] // 2)),\n     dict(\n        type='MixUp',\n        img_scale=img_scale,\n        ratio_range=(0.8, 1.6),\n        pad_val=114.0),\n    dict(type='RandomFlip', prob=0.5),\n    dict(type='PhotoMetricDistortion',\n         brightness_delta=32, contrast_range=(0.5, 1.5),\n         saturation_range=(0.5, 1.5), hue_delta=18),\n    dict(type='Resize', scale=img_scale, keep_ratio=True),\n    dict(type='FilterAnnotations', min_gt_bbox_wh=(1, 1), keep_empty=False),\n    dict(type='PackDetInputs')\n]\n\n\ntest_pipeline = [\n    dict(type='LoadImageFromFile', backend_args=backend_args),\n    dict(type='LoadAnnotations', with_bbox=True),\n    dict(type='PhotoMetricDistortion',\n          brightness_delta=32, contrast_range=(0.5,1.5),\n          saturation_range=(0.5,1.5),hue_delta=18\n         ),\n    dict(type='Resize', scale=img_scale, keep_ratio=True),\n    # If you don't have a gt annotation, delete the pipeline\n    dict(\n        type='PackDetInputs',\n        meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',\n                   'scale_factor'))\n]\n\ntrain_dataset = dict(\n    # use MultiImageMixDataset wrapper to support mosaic and mixup\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=[\n            dict(type='LoadImageFromFile', backend_args=backend_args),\n            dict(type='LoadAnnotations', with_bbox=True)\n        ],\n        backend_args=backend_args),\n    pipeline=train_pipeline)\n\n\ntrain_dataloader = dict(\n    batch_size=4,\n    num_workers=2,\n    persistent_workers=True,\n    dataset=train_dataset)\nval_dataloader = dict(\n    batch_size=4,\n    num_workers=2,\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\ntest_cfg = dict(type='TestLoop', _delete_=True) \nval_evaluator = dict(\nann_file=data_root + 'annotations_valid.json', metric=['bbox'])\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":{"execution":{"iopub.status.busy":"2024-05-21T14:49:40.159824Z","iopub.execute_input":"2024-05-21T14:49:40.160632Z","iopub.status.idle":"2024-05-21T14:49:40.179482Z","shell.execute_reply.started":"2024-05-21T14:49:40.160543Z","shell.execute_reply":"2024-05-21T14:49:40.177367Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Train","metadata":{}},{"cell_type":"code","source":"!python tools/train.py /kaggle/working/mmdetection/configs/wheat/custom_config.py","metadata":{"execution":{"iopub.status.busy":"2024-05-21T14:49:41.968291Z","iopub.execute_input":"2024-05-21T14:49:41.969014Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{},"execution_count":null,"outputs":[]}]}