I have a bug when I launch train.py

[SylvainArd]

Thanks for your error report and we appreciate it a lot.

Checklist

1. I have searched related issues but cannot get the expected help.
2. The bug has not been fixed in the latest version.

Describe the bug A clear and concise description of what the bug is. An error when I launch train.py

Reproduction

1. What command or script did you run? a batch file containing : call conda activate solov2 cd C:\Users\MASTER\Desktop\SOLO-master\SOLO-master set PYTHONPATH=C:\Users\MASTER\Desktop\SOLO-master;%PYTHONPATH% python tools/train.py configs/solov2/solov2_light_448_r18_fpn_8gpu_3x.py pause

   A placeholder for the command.

2. Did you make any modifications on the code or config? Did you understand what you have modified? yes I added a my_dataset.py in mmdet/datasets with the content : from .coco import CocoDataset from .registry import DATASETS @DATASETS.register_module class MyDataset(CocoDataset): CLASSES = ['null', 'points']

and I have change the configs/solov2/solov2_light_448_r18_fpn_8gpu_3x.py file to :

model settings

model = dict( type='SOLOv2', pretrained='torchvision://resnet18', backbone=dict( type='ResNet', depth=18, num_stages=4, out_indices=(0, 1, 2, 3), # C2, C3, C4, C5 frozen_stages=1, style='pytorch'), neck=dict( type='FPN', in_channels=[64, 128, 256, 512], out_channels=256, start_level=0, num_outs=5), bbox_head=dict( type='SOLOv2Head', num_classes=1, in_channels=256, stacked_convs=2, seg_feat_channels=256, strides=[8, 8, 16, 32, 32], scale_ranges=((1, 56), (28, 112), (56, 224), (112, 448), (224, 896)), sigma=0.2, num_grids=[40, 36, 24, 16, 12], ins_out_channels=128, loss_ins=dict( type='DiceLoss', use_sigmoid=True, loss_weight=3.0), loss_cate=dict( type='FocalLoss', use_sigmoid=True, gamma=2.0, alpha=0.25, loss_weight=1.0)), mask_feat_head=dict( type='MaskFeatHead', in_channels=256, out_channels=128, start_level=0, end_level=3, num_classes=128, norm_cfg=dict(type='GN', num_groups=32, requires_grad=True)), )

training and testing settings

train_cfg = dict() test_cfg = dict( nms_pre=500, score_thr=0.1, mask_thr=0.5, update_thr=0.05, kernel='gaussian', # gaussian/linear sigma=2.0, max_per_img=100)

dataset settings

dataset_type = 'MyDataset' data_root = 'datasets/' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True) train_pipeline = [ dict(type='LoadImageFromFile'), dict(type='LoadAnnotations', with_bbox=True, with_mask=True), dict(type='Resize', img_scale=[(768, 512), (768, 480), (768, 448), (768, 416), (768, 384), (768, 352)], multiscale_mode='value', keep_ratio=True), dict(type='RandomFlip', flip_ratio=0.5), dict(type='Normalize', img_norm_cfg), dict(type='Pad', size_divisor=32), dict(type='DefaultFormatBundle'), dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']), ] test_pipeline = [ dict(type='LoadImageFromFile'), dict( type='MultiScaleFlipAug', img_scale=(768, 448), flip=False, transforms=[ dict(type='Resize', keep_ratio=True), dict(type='RandomFlip'), dict(type='Normalize', img_norm_cfg), dict(type='Pad', size_divisor=32), dict(type='ImageToTensor', keys=['img']), dict(type='Collect', keys=['img']), ]) ] data = dict( imgs_per_gpu=2, workers_per_gpu=2, train=dict( type=dataset_type, ann_file=data_root + 'trainval.json', img_prefix=data_root + 'trainval/', pipeline=train_pipeline), val=dict( type=dataset_type, ann_file=data_root + 'trainval.json', img_prefix=data_root + 'trainval/', pipeline=test_pipeline), test=dict( type=dataset_type, ann_file=data_root + 'trainval.json', img_prefix=data_root + 'trainval/', pipeline=test_pipeline))

optimizer

optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001) optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))

learning policy

lr_config = dict( policy='step', warmup='linear', warmup_iters=500, warmup_ratio=0.01, step=[27, 33]) checkpoint_config = dict(interval=1)

yapf:disable

log_config = dict( interval=50, hooks=[ dict(type='TextLoggerHook'),

dict(type='TensorboardLoggerHook')

])

yapf:enable

runtime settings

total_epochs = 36 device_ids = range(8) dist_params = dict(backend='nccl') log_level = 'INFO' work_dir = './work_dirs/solov2_light_release_r18_fpn_8gpu_3x' load_from = None resume_from = None workflow = [('train', 1)]

I have added at root directory a folder "datasets" with a folder of images in it and a trainval.json file containing the coco annotations my polygons instances are of category "points"

5. What dataset did you use?

Environment

1. Please run python tools/collect_env.py to collect necessary environment infomation and paste it here. I have the error : Traceback (most recent call last): File "tools/collect_env.py", line 12, in from mmdet.ops import get_compiler_version, get_compiling_cuda_version ModuleNotFoundError: No module named 'mmdet.ops' when I run python tools/collect_env.py
2. You may add addition that may be helpful for locating the problem, such as
   • How you installed PyTorch [e.g., pip, conda, source] conda create --name solov2 python=3.7 -y conda activate solov2 conda install pytorch==1.8.0 torchvision==0.9.0 torchaudio==0.8.0 cudatoolkit=11.1 -c pytorch -c conda-forgey pip install mmdet mmcv==2.0.0
   • Other environment variables that may be related (such as $PATH, $LD_LIBRARY_PATH, $PYTHONPATH, etc.)

Error traceback If applicable, paste the error trackback here.

(solov2) C:\Users\MASTER\Desktop\SOLO-master\SOLO-master>python tools/train.py configs/solov2/solov2_light_448_r18_fpn_8gpu_3x.py
Traceback (most recent call last):
  File "tools/train.py", line 9, in <module>
    from mmcv import Config
ImportError: cannot import name 'Config' from 'mmcv' (C:\ProgramData\Anaconda3\envs\solov2\lib\site-packages\mmcv\__init__.py)

Bug fix If you have already identified the reason, you can provide the information here. If you are willing to create a PR to fix it, please also leave a comment here and that would be much appreciated!