LL3RD / ACFormer

Code for Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection (ICCV 2023)
MIT License
38 stars 6 forks source link

sampler is not in the sampler registry issue #2

Open dong-ma-zi opened 11 months ago

dong-ma-zi commented 11 months ago
fatal: not a git repository (or any parent up to mount point /home)
Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).
Traceback (most recent call last):
  File "tools/train.py", line 200, in <module>
    main()
  File "tools/train.py", line 188, in main
    train_detector(
  File "/home/data1/my/Project/nucleiDetCls/ACFormer/ssod/apis/train.py", line 70, in train_detector
    data_loaders = [
  File "/home/data1/my/Project/nucleiDetCls/ACFormer/ssod/apis/train.py", line 71, in <listcomp>
    build_dataloader(
  File "/home/data1/my/Project/nucleiDetCls/ACFormer/ssod/datasets/builder.py", line 68, in build_dataloader
    build_sampler(sampler_cfg, default_args=default_sampler_cfg)
  File "/home/data1/my/Project/nucleiDetCls/ACFormer/ssod/datasets/builder.py", line 40, in build_sampler
    return build_from_cfg(cfg, SAMPLERS, default_args)
  File "/home/my/.conda/envs/ACFormer/lib/python3.8/site-packages/mmcv/utils/registry.py", line 61, in build_from_cfg
    raise KeyError(
KeyError: 'sampler is not in the sampler registry'

I'm not very familiar with the mechanics of mmdetection, can you help me with this?

dddddddck commented 8 months ago

I also have this problem, have you solved it?

LL3RD commented 8 months ago

Please try using distributed training script _bash tools/dist_train.sh {configfile} 1 instead of using python train.py