Need help in VGG16 Faster R-CNN implementation (2024)

!pip3 install openmim!mim install mmengine!pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0!pip install mmcv==2.1.0 -f https://download.openmmlab.com/mmcv/dist/cu121/torch2.1/index.html

data|-- plat|--|-- test|--|--|-- _anotations.coco.json|--|--|-- [images_x].jpg|--|--|-- [images_x].jpg|--|--|-- [..................]|--|-- train|--|--|-- _anotations.coco.json|--|--|-- [images_x].jpg|--|--|-- [images_x].jpg|--|--|-- [..................]|--|-- valid|--|--|-- _anotations.coco.json|--|--|-- [images_x].jpg|--|--|-- [images_x].jpg|--|--|-- [..................]|--|-- readme.txt

base = [ "../base/models/faster-rcnn_v16.py", "../base/schedules/schedule_1x.py", "../base/default_runtime.py",]# Dataset settingsdataset_type = "PlatDataset"data_root = "data/plat/"train_ann_file = "train/_annotations.coco.json"train_data_prefix = "train/"val_ann_file = "valid/_annotations.coco.json"val_data_prefix = "valid/"test_ann_file = "test/_annotations.coco.json"test_data_prefix = "test/"class_name = "plat"num_classes = 1img_scale = (640, 640) # width, height# Train settingstrain_batch_size_per_gpu = 16train_num_workers = 10train_persistent_workers = True# Valid settingsval_batch_size_per_gpu = 16val_num_workers = 10val_persistent_workers = True# Train Val settingsbase_lr = 0.01 # Base learning rate for optim_wrappermax_epochs = 20 # Maximum training epochslearning_rate = 0.01momentum = 0.937weight_decay = 0.0005lr_start_factor = 1.0e-5backend_args = Nonemodel_test_cfg = dict( # The config of multi-label for multi-class prediction. multi_label=True, # The number of boxes before NMS nms_pre=30000, score_thr=0.001, # Threshold to filter out boxes. nms=dict(type="nms", iou_threshold=0.95), # NMS type and threshold max_per_img=300, # Max number of detections of each image)train_pipeline = [ dict(type="LoadImageFromFile", backend_args=backend_args), dict(type="LoadAnnotations", with_bbox=True), dict(type="PackDetInputs"),]test_pipeline = [ dict(type="LoadImageFromFile", backend_args=backend_args), dict(type='LoadAnnotations', with_bbox=True), dict( type="PackDetInputs", meta_keys=( "img_id", "img_path", "ori_shape", "img_shape", "scale_factor", ), ),]train_dataloader = dict( batch_size=train_batch_size_per_gpu, num_workers=train_num_workers, persistent_workers=train_persistent_workers, sampler=dict(type="DefaultSampler", shuffle=True), batch_sampler=dict(type="AspectRatioBatchSampler"), dataset=dict( type=dataset_type, data_root=data_root, ann_file=train_ann_file, data_prefix=dict(img=train_data_prefix), filter_cfg=dict(filter_empty_gt=True, min_size=32), pipeline=train_pipeline, backend_args=backend_args, ),)val_dataloader = dict( batch_size=val_batch_size_per_gpu, num_workers=val_num_workers, persistent_workers=val_persistent_workers, drop_last=False, sampler=dict(type="DefaultSampler", shuffle=False), dataset=dict( type=dataset_type, data_root=data_root, ann_file=val_ann_file, data_prefix=dict(img=val_data_prefix), test_mode=True, pipeline=test_pipeline, backend_args=backend_args, ),)test_dataloader = dict( batch_size=1, num_workers=2, persistent_workers=True, drop_last=False, sampler=dict(type="DefaultSampler", shuffle=False), dataset=dict( type=dataset_type, data_root=data_root, ann_file=test_ann_file, data_prefix=dict(img=test_data_prefix), test_mode=True, pipeline=test_pipeline, ),)val_evaluator = dict( type="CocoMetric", ann_file=data_root + val_ann_file, metric="bbox", format_only=False, backend_args=backend_args,)test_evaluator = dict( type="CocoMetric", metric="bbox", format_only=True, ann_file=data_root + test_ann_file, outfile_prefix="./work_dirs/plat_detection/test",)# Config of batch shapes. Only on val.batch_shapes_cfg = dict( type="BatchShapePolicy", batch_size=val_batch_size_per_gpu, img_size=img_scale[0], size_divisor=32, extra_pad_ratio=0.5,)optimizer = dict(type="SGD", lr=base_lr, momentum=momentum, weight_decay=weight_decay)optimizer_config = dict(_delete_=True)# learning rateparam_scheduler = [ dict( type="LinearLR", start_factor=lr_start_factor, by_epoch=True, begin=0, end=max_epochs, convert_to_iter_based=True, )]norm_cfg = dict(type="BN") # Normalization config# -----train val related-----lr_start_factor = 1.0e-5dsl_topk = 13 # Number of bbox selected in each levelloss_cls_weight = 1.0loss_bbox_weight = 2.0qfl_beta = 2.0 # beta of QualityFocalLossweight_decay = 0.05# Save model checkpoint and validation intervalssave_checkpoint_intervals = 10# The maximum checkpoints to keep.max_keep_ckpts = 3# single-scale training is recommended to# be turned on, which can speed up training.env_cfg = dict(cudnn_benchmark=True)# hooksdefault_hooks = dict( checkpoint=dict( type="CheckpointHook", interval=save_checkpoint_intervals, max_keep_ckpts=max_keep_ckpts, # only keep latest 3 checkpoints ))custom_hooks = [ dict( type="EMAHook", ema_type="ExpMomentumEMA", momentum=0.0002, update_buffers=True, strict_load=False, priority=49, )]train_cfg = dict( type="EpochBasedTrainLoop", max_epochs=max_epochs, val_interval=save_checkpoint_intervals,)val_cfg = dict(type="ValLoop")test_cfg = dict(type="TestLoop")

model = dict( type="FasterRCNN", backbone=dict( type="VGG", depth=16, num_stages=4, dilations=(1, 1, 1, 1), out_indices=(3,), frozen_stages=-1, bn_eval=True, with_bn=True, pretrained="torchvision://vgg16_bn", ), rpn_head=dict( type="RPNHead", in_channels=512, # channel changed feat_channels=512, # channel changed anchor_generator=dict( type="AnchorGenerator", scales=[2, 4, 8, 16, 32], ratios=[0.5, 1.0, 2.0], strides=[16], ), bbox_coder=dict( type="DeltaXYWHBBoxCoder", target_means=[0.0, 0.0, 0.0, 0.0], target_stds=[1.0, 1.0, 1.0, 1.0], ), loss_cls=dict(type="CrossEntropyLoss", use_sigmoid=True, loss_weight=1.0), loss_bbox=dict(type="L1Loss", loss_weight=1.0), ), roi_head=dict( type="StandardRoIHead", bbox_roi_extractor=dict( type="SingleRoIExtractor", roi_layer=dict(type="RoIAlign", output_size=7, sampling_ratio=0), out_channels=512, # channel changed featmap_strides=[16], ), bbox_head=dict( type="Shared2FCBBoxHead", in_channels=512, # channel changed fc_out_channels=1024, roi_feat_size=7, num_classes=2, bbox_coder=dict( type="DeltaXYWHBBoxCoder", target_means=[0.0, 0.0, 0.0, 0.0], target_stds=[0.1, 0.1, 0.2, 0.2], ), reg_class_agnostic=False, loss_cls=dict(type="CrossEntropyLoss", use_sigmoid=False, loss_weight=1.0), loss_bbox=dict(type="L1Loss", loss_weight=1.0), ), ), # model training and testing settings train_cfg=dict( rpn=dict( assigner=dict( type="MaxIoUAssigner", pos_iou_thr=0.7, neg_iou_thr=0.3, min_pos_iou=0.3, match_low_quality=True, ignore_iof_thr=-1, ), sampler=dict( type="RandomSampler", num=256, pos_fraction=0.5, neg_pos_ub=-1, add_gt_as_proposals=False, ), allowed_border=0, pos_weight=-1, debug=False, ), rpn_proposal=dict( nms_pre=12000, max_per_img=2000, nms=dict(type="nms", iou_threshold=0.7), min_bbox_size=0, ), rcnn=dict( assigner=dict( type="MaxIoUAssigner", pos_iou_thr=0.5, neg_iou_thr=0.5, min_pos_iou=0.5, match_low_quality=False, ignore_iof_thr=-1, ), sampler=dict( type="RandomSampler", num=512, pos_fraction=0.25, neg_pos_ub=-1, add_gt_as_proposals=True, ), pos_weight=-1, debug=False, ), ), test_cfg=dict( rpn=dict( nms=dict(type="nms", iou_threshold=0.7), nms_pre=6000, max_per_img=1000, min_bbox_size=0, ), rcnn=dict( score_thr=0.05, nms=dict(type="nms", iou_threshold=0.5), max_per_img=100 ), ),)

from mmdet.registry import MODELSfrom mmcv.cnn import VGG@MODELS.register_module()class VGG(VGG): def __init__(self, pretrained=None, *args, **kwargs): self.pretrained = pretrained super().__init__(*args, **kwargs) def init_weights(self, pretrained=None): super().init_weights(pretrained) def forward(self, x): outs = [] vgg_layers = getattr(self, self.module_name) for i in range(len(self.stage_blocks)): for j in range(*self.range_sub_modules[i]): vgg_layer = vgg_layers[j] x = vgg_layer(x) if i in self.out_indices: outs.append(x) if self.num_classes > 0: x = x.view(x.size(0), -1) x = self.classifier(x) outs.append(x) return tuple(outs)

!python tools/train.py configs/faster_rcnn/faster_rcnn_v16_platBS16E20.py

Traceback (most recent call last): File "/content/ta-mmdetection/tools/train.py", line 121, in <module> main() File "/content/ta-mmdetection/tools/train.py", line 110, in main runner = Runner.from_cfg(cfg) File "/usr/local/lib/python3.10/dist-packages/mmengine/runner/runner.py", line 463, in from_cfg model=cfg['model'], File "/usr/local/lib/python3.10/dist-packages/mmengine/config/config.py", line 1502, in __getitem__ return self._cfg_dict.__getitem__(name) File "/usr/local/lib/python3.10/dist-packages/mmengine/config/config.py", line 138, in __getitem__ return self.build_lazy(super().__getitem__(key)) File "/usr/local/lib/python3.10/dist-packages/mmengine/config/config.py", line 105, in __missing__ raise KeyError(name)KeyError: 'model'