AssertionError: The `num_classes` (54) in ConvFCBBoxHead of MMDistributedDataParallel does not matches the length of `CLASSES` 80) in CocoDataset about uniformer

[Andy1621]

It seems that you forget to change the num_classes in mask_head, and it loads from configs/_base_/models/cascade_mask_rcnn_uniformer_fpn.

UniFormer/object_detection/configs/_base_/models/cascade_mask_rcnn_uniformer_fpn.py

Lines 102 to 109 in 53215bf

	mask_head=dict(
	type='FCNMaskHead',
	num_convs=4,
	in_channels=256,
	conv_out_channels=256,
	num_classes=80,
	loss_mask=dict(
	type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),

[Andy1621]

Would you like to check all the num_classes in xxx.log? I guess one value for num_classes isn't set to 54.

[Williamlizl]

I check the log file, and all the num_classes in log file has been changed, but it still shows the error,,,,,

[Andy1621]

@Williamlizl Have you changed the num_classes in mask_head ?

[Williamlizl]

@Williamlizl Have you changed the num_classes in mask_head ?

I have changed the num_classes, and the log file shows Ok, but it still could not work

[Andy1621]

I think you should write dataset.py for your dataset, because you load the default file for COCO configs/base/datasets/coco_instance.py.
It will load the annotations of COCO, which consists of 80 classes.

[Andy1621]

You can find it from

UniFormer/object_detection/mmdet/datasets/coco.py

Lines 20 to 36 in 53215bf

	@DATASETS.register_module()
	class CocoDataset(CustomDataset):
	CLASSES = ('person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
	'train', 'truck', 'boat', 'traffic light', 'fire hydrant',
	'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog',
	'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe',
	'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
	'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat',
	'baseball glove', 'skateboard', 'surfboard', 'tennis racket',
	'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl',
	'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot',
	'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
	'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop',
	'mouse', 'remote', 'keyboard', 'cell phone', 'microwave',
	'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock',
	'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush')

[Andy1621]

As there is no more activity, I am closing the issue, don't hesitate to reopen it if necessary.

[Williamlizl]

You can find it from

UniFormer/object_detection/mmdet/datasets/coco.py

Lines 20 to 36 in 53215bf

	@DATASETS.register_module()
	class CocoDataset(CustomDataset):
	CLASSES = ('person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
	'train', 'truck', 'boat', 'traffic light', 'fire hydrant',
	'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog',
	'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe',
	'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
	'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat',
	'baseball glove', 'skateboard', 'surfboard', 'tennis racket',
	'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl',
	'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot',
	'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
	'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop',
	'mouse', 'remote', 'keyboard', 'cell phone', 'microwave',
	'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock',
	'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush')

Thank you, I will try it