Training YOLOv7 on MOT Challenge Dataset

[hoang1007]

Hello, I'm trying to train YOLOv7 model with mmtracking on MOT17 dataset. Here is my yolov7 config: https://pastebin.com/mzkbcPWM
I have face this error:

Traceback (most recent call last):
  File "/data/mtmc/hoang_cam/mot-mmtrack/tools/train.py", line 119, in <module>
    main()
  File "/data/mtmc/hoang_cam/mot-mmtrack/tools/train.py", line 115, in main
    runner.train()
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/mmengine/runner/runner.py", line 1686, in train
    model = self.train_loop.run()  # type: ignore
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/mmengine/runner/loops.py", line 90, in run
    self.run_epoch()
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/mmengine/runner/loops.py", line 105, in run_epoch
    for idx, data_batch in enumerate(self.dataloader):
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 628, in __next__
    data = self._next_data()
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1333, in _next_data
    return self._process_data(data)
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/torch/utils/data/dataloader.py", line 1359, in _process_data
    data.reraise()
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/torch/_utils.py", line 543, in reraise
    raise exception
AssertionError: Caught AssertionError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop
    data = fetcher.fetch(index)
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 58, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/torch/utils/data/_utils/fetch.py", line 58, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/mmengine/dataset/base_dataset.py", line 408, in __getitem__
    data = self.prepare_data(idx)
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/mmengine/dataset/base_dataset.py", line 789, in prepare_data
    return self.pipeline(data_info)
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/mmengine/dataset/base_dataset.py", line 58, in __call__
    data = t(data)
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/mmcv/transforms/base.py", line 12, in __call__
    return self.transform(results)
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/mmcv/transforms/wrappers.py", line 593, in transform
    return self.transforms[idx](results)
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/mmcv/transforms/base.py", line 12, in __call__
    return self.transform(results)
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/mmcv/transforms/wrappers.py", line 87, in transform
    results = t(results)  # type: ignore
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/mmcv/transforms/base.py", line 12, in __call__
    return self.transform(results)
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/mmdet/structures/bbox/box_type.py", line 277, in wrapper
    _results = func(self, results, *args, **kwargs)
  File "/data/mtmc/miniconda3/envs/mot-mmtrack-1x/lib/python3.10/site-packages/mmyolo/datasets/transforms/mix_img_transforms.py", line 129, in transform
    assert 'dataset' in results
AssertionError

How to fix it? Can anyone help me out? 😋 😋

[hhaAndroid]

@hoang1007 mmtrack does not support mmyolo currently. This is under development. Support is expected in the next month.