search

open-mmlab / mmdetection

OpenMMLab Detection Toolbox and Benchmark
https://mmdetection.readthedocs.io
Apache License 2.0
29.16k stars 9.39k forks source link

Channels Error #7561

Closed zehranrgi closed 2 years ago

zehranrgi commented 2 years ago

My image size is 416*416, I changed the config.file like that but still I got this error. How can I solve this problem?

My custom config file: 

# The new config inherits a base config to highlight the necessary modification
_base_ = 'cascade_rcnn/cascade_rcnn_r101_fpn_1x_coco.py'

# /content/drive/MyDrive/KU/mmdetection/configs/

# Modify dataset related settings
model = dict(
    type='CascadeRCNN',
    backbone=dict(
        type='ResNet',
        depth=50,
        num_stages=4,
        out_indices=(0, 1, 2, 3),
        frozen_stages=1,
        norm_cfg=dict(type='BN', requires_grad=True),
        norm_eval=True,
        style='pytorch',
        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
    neck=dict(
        type='FPN',
        in_channels=[416, 512, 1024, 2048], 
        out_channels=416,
        num_outs=3),
    rpn_head=dict(
        type='RPNHead',
        in_channels=416,
        feat_channels=416,
        anchor_generator=dict(
            type='AnchorGenerator',
            scales=[8],
            ratios=[0.5, 1.0, 2.0],
            strides=[4, 8, 16, 32, 64]),
        bbox_coder=dict(
            type='DeltaXYWHBBoxCoder',
            target_means=[.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='SmoothL1Loss', beta=1.0 / 9.0, loss_weight=1.0)),
    roi_head=dict(
        type='CascadeRoIHead',
        num_stages=3,
        stage_loss_weights=[1, 0.5, 0.25],
        bbox_roi_extractor=dict(
            type='SingleRoIExtractor',
            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
            out_channels=416,
            featmap_strides=[4, 8, 16, 32]),
        bbox_head=[
            dict(
                type='Shared2FCBBoxHead',
                in_channels=416,
                fc_out_channels=1024,
                roi_feat_size=7,
                num_classes=3,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0., 0., 0., 0.],
                    target_stds=[0.1, 0.1, 0.2, 0.2]),
                reg_class_agnostic=True,
                loss_cls=dict(
                    type='CrossEntropyLoss',
                    use_sigmoid=False,
                    loss_weight=1.0),
                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
                               loss_weight=1.0)),
            dict(
                type='Shared2FCBBoxHead',
                in_channels=416,
                fc_out_channels=1024,
                roi_feat_size=7,
                num_classes=3,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0., 0., 0., 0.],
                    target_stds=[0.05, 0.05, 0.1, 0.1]),
                reg_class_agnostic=True,
                loss_cls=dict(
                    type='CrossEntropyLoss',
                    use_sigmoid=False,
                    loss_weight=1.0),
                loss_bbox=dict(type='SmoothL1Loss', beta=1.0,
                               loss_weight=1.0)),
            dict(
                type='Shared2FCBBoxHead',
                in_channels=416,
                fc_out_channels=1024,
                roi_feat_size=7,
                num_classes=3,
                bbox_coder=dict(
                    type='DeltaXYWHBBoxCoder',
                    target_means=[0., 0., 0., 0.],
                    target_stds=[0.033, 0.033, 0.067, 0.067]),
                reg_class_agnostic=True,
                loss_cls=dict(
                    type='CrossEntropyLoss',
                    use_sigmoid=False,
                    loss_weight=1.0),
                loss_bbox=dict(type='SmoothL1Loss', beta=1.0, 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=416,  
                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=2000,
            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),
            dict(
                assigner=dict(
                    type='MaxIoUAssigner',
                    pos_iou_thr=0.6,
                    neg_iou_thr=0.6,
                    min_pos_iou=0.6,
                    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),
            dict(
                assigner=dict(
                    type='MaxIoUAssigner',
                    pos_iou_thr=0.7,
                    neg_iou_thr=0.7,
                    min_pos_iou=0.7,
                    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_pre=1000,
            max_per_img=1000,
            nms=dict(type='nms', iou_threshold=0.7),
            min_bbox_size=0),
        rcnn=dict(
            score_thr=0.05,
            nms=dict(type='nms', iou_threshold=0.5),
            max_per_img=100)))

dataset_type = 'CocoDataset'
classes = ('Platelets','RBC','WBC')

data = dict(
    train=dict(
        img_prefix='datasetsx/train/',
        classes=classes,
        ann_file='datasetsx/train/_annotations.coco.json'),
    val=dict(
        img_prefix='datasetsx/val/',
        classes=classes,
        ann_file='datasetsx/val/_annotations.coco.json'),
    test=dict(
        img_prefix='datasetsx/val/',
        classes=classes,
        ann_file='datasetsx/val/_annotations.coco.json'))

My coco dataset: 


@DATASETS.register_module()
class CocoDataset(CustomDataset):

    CLASSES = ('Platelets','RBC','WBC')

    PALETTE = [(220, 20, 60), (119, 11, 32), (0, 0, 142), (0, 0, 230),
               (106, 0, 228), (0, 60, 100), (0, 80, 100), (0, 0, 70),
               (0, 0, 192), (250, 170, 30), (100, 170, 30), (220, 220, 0),
               (175, 116, 175), (250, 0, 30), (165, 42, 42), (255, 77, 255),
               (0, 226, 252), (182, 182, 255), (0, 82, 0), (120, 166, 157),
               (110, 76, 0), (174, 57, 255), (199, 100, 0), (72, 0, 118),
               (255, 179, 240), (0, 125, 92), (209, 0, 151), (188, 208, 182),
               (0, 220, 176), (255, 99, 164), (92, 0, 73), (133, 129, 255),
               (78, 180, 255), (0, 228, 0), (174, 255, 243), (45, 89, 255),
               (134, 134, 103), (145, 148, 174), (255, 208, 186),
               (197, 226, 255), (171, 134, 1), (109, 63, 54), (207, 138, 255),
               (151, 0, 95), (9, 80, 61), (84, 105, 51), (74, 65, 105),
               (166, 196, 102), (208, 195, 210), (255, 109, 65), (0, 143, 149),
               (179, 0, 194), (209, 99, 106), (5, 121, 0), (227, 255, 205),
               (147, 186, 208), (153, 69, 1), (3, 95, 161), (163, 255, 0),
               (119, 0, 170), (0, 182, 199), (0, 165, 120), (183, 130, 88),
               (95, 32, 0), (130, 114, 135), (110, 129, 133), (166, 74, 118),
               (219, 142, 185), (79, 210, 114), (178, 90, 62), (65, 70, 15),
               (127, 167, 115), (59, 105, 106), (142, 108, 45), (196, 172, 0),
               (95, 54, 80), (128, 76, 255), (201, 57, 1), (246, 0, 122),
               (191, 162, 208)]

Traceback (most recent call last): File "tools/train.py", line 209, in main() File "tools/train.py", line 205, in main meta=meta) File "/content/drive/MyDrive/KU/mmdetection/mmdet/apis/train.py", line 208, in train_detector runner.run(data_loaders, cfg.workflow) File "/usr/local/lib/python3.7/dist-packages/mmcv/runner/epoch_based_runner.py", line 127, in run epoch_runner(data_loaders[i], kwargs) File "/usr/local/lib/python3.7/dist-packages/mmcv/runner/epoch_based_runner.py", line 50, in train self.run_iter(data_batch, train_mode=True, kwargs) File "/usr/local/lib/python3.7/dist-packages/mmcv/runner/epoch_based_runner.py", line 30, in run_iter kwargs) File "/usr/local/lib/python3.7/dist-packages/mmcv/parallel/data_parallel.py", line 75, in train_step return self.module.train_step(inputs[0], kwargs[0]) File "/content/drive/MyDrive/KU/mmdetection/mmdet/models/detectors/base.py", line 248, in train_step losses = self(data) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(input, kwargs) File "/usr/local/lib/python3.7/dist-packages/mmcv/runner/fp16_utils.py", line 109, in new_func return old_func(args, kwargs) File "/content/drive/MyDrive/KU/mmdetection/mmdet/models/detectors/base.py", line 172, in forward return self.forward_train(img, img_metas, kwargs) File "/content/drive/MyDrive/KU/mmdetection/mmdet/models/detectors/two_stage.py", line 127, in forward_train x = self.extract_feat(img) File "/content/drive/MyDrive/KU/mmdetection/mmdet/models/detectors/two_stage.py", line 69, in extract_feat x = self.neck(x) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(input, kwargs) File "/usr/local/lib/python3.7/dist-packages/mmcv/runner/fp16_utils.py", line 109, in new_func return old_func(*args, *kwargs) File "/content/drive/MyDrive/KU/mmdetection/mmdet/models/necks/fpn.py", line 159, in forward for i, lateral_conv in enumerate(self.lateral_convs) File "/content/drive/MyDrive/KU/mmdetection/mmdet/models/necks/fpn.py", line 159, in for i, lateral_conv in enumerate(self.lateral_convs) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(input, kwargs) File "/usr/local/lib/python3.7/dist-packages/mmcv/cnn/bricks/conv_module.py", line 201, in forward x = self.conv(x) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(*input, **kwargs) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/conv.py", line 443, in forward return self._conv_forward(input, self.weight, self.bias) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/conv.py", line 440, in _conv_forward self.padding, self.dilation, self.groups) RuntimeError: Given groups=1, weight of size [416, 416, 1, 1], expected input[2, 256, 200, 200] to have 416 channels, but got 256 channels instead

zehranrgi commented 2 years ago

I resized the images to 256 but now, I got this error..What is the problem with using a custom dataset...

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "tools/train.py", line 209, in <module>
    main()
  File "tools/train.py", line 182, in main
    test_cfg=cfg.get('test_cfg'))
  File "/content/drive/MyDrive/KU/mmdetection/mmdet/models/builder.py", line 59, in build_detector
    cfg, default_args=dict(train_cfg=train_cfg, test_cfg=test_cfg))
  File "/usr/local/lib/python3.7/dist-packages/mmcv/utils/registry.py", line 212, in build
    return self.build_func(*args, **kwargs, registry=self)
  File "/usr/local/lib/python3.7/dist-packages/mmcv/cnn/builder.py", line 27, in build_model_from_cfg
    return build_from_cfg(cfg, registry, default_args)
  File "/usr/local/lib/python3.7/dist-packages/mmcv/utils/registry.py", line 55, in build_from_cfg
    raise type(e)(f'{obj_cls.__name__}: {e}')
AssertionError: CascadeRCNN: FPN:
zehranrgi commented 2 years ago

Solved. And, I think examples are not enough...