使用rtmpose-m_8xb512-700e_body8-halpe26-256x192.py训练模型时候遇到错误，数据集只下载的coco和 halpe,当只训练halpe时不会报错，加上coco就会报错

[zbzzz]

报错信息：09/26 13:49:34 - mmengine - WARNING - The prefix is not set in metric class PCKAccuracy.
09/26 13:49:34 - mmengine - WARNING - The prefix is not set in metric class AUC.
09/26 13:49:38 - mmengine - INFO - load backbone. in model from: https://download.openmmlab.com/mmpose/v1/projects/rtmposev1/rtmpose-m_simcc-body7_pt-body7_420e-256x192-e48f03d0_20230504.pth
Loads checkpoint by http backend from path: https://download.openmmlab.com/mmpose/v1/projects/rtmposev1/rtmpose-m_simcc-body7_pt-body7_420e-256x192-e48f03d0_20230504.pth
09/26 13:49:38 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io
09/26 13:49:38 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future.
09/26 13:49:38 - mmengine - INFO - Checkpoints will be saved to /home/zhangbao/projects/rtmpose/work_dirs/my_rtmpose_body26.
Traceback (most recent call last):
File "/home/zhangbao/projects/rtmpose/tools/train.py", line 162, in
main()
File "/home/zhangbao/projects/rtmpose/tools/train.py", line 158, in main
runner.train()
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/mmengine/runner/runner.py", line 1777, in train
model = self.train_loop.run() # type: ignore
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/mmengine/runner/loops.py", line 98, in run
self.run_epoch()
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/mmengine/runner/loops.py", line 114, in run_epoch
for idx, data_batch in enumerate(self.dataloader):
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 630, in next
data = self._next_data()
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1345, in _next_data
return self._process_data(data)
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/torch/utils/data/dataloader.py", line 1371, in _process_data
data.reraise()
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/torch/_utils.py", line 694, in reraise
raise exception
AttributeError: Caught AttributeError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/torch/utils/data/_utils/worker.py", line 308, in _worker_loop
data = fetcher.fetch(index)
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 51, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/torch/utils/data/_utils/fetch.py", line 51, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/mmengine/dataset/base_dataset.py", line 410, in getitem
data = self.prepare_data(idx)
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/mmpose/datasets/dataset_wrappers.py", line 114, in prepare_data
data_info = self.get_data_info(idx)
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/mmpose/datasets/dataset_wrappers.py", line 133, in get_data_info
data_info = self.datasets[subset_idx][sample_idx]
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/mmengine/dataset/base_dataset.py", line 410, in getitem
data = self.prepare_data(idx)
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/mmengine/dataset/base_dataset.py", line 115, in wrapper
return old_func(obj, *args, **kwargs)
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/mmpose/datasets/datasets/base/base_coco_style_dataset.py", line 170, in prepare_data
return self.pipeline(data_info)
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/mmengine/dataset/base_dataset.py", line 60, in call
data = t(data)
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/mmcv/transforms/base.py", line 12, in call
return self.transform(results)
File "/home/zhangbao/miniconda3/envs/rtmpose/lib/python3.9/site-packages/mmpose/datasets/transforms/converting.py", line 108, in transform
c = results[key].shape[-1]
AttributeError: 'NoneType' object has no attribute 'shape'

修改后的脚本配置：train_dataloader = dict(
batch_size=train_batch_size,
num_workers=10,
pin_memory=True,
persistent_workers=True,
sampler=dict(type='DefaultSampler', shuffle=True),
dataset=dict(
type='CombinedDataset',
metainfo=dict(from_file='configs/base/datasets/halpe26.py'),
datasets=[
dataset_coco,
dataset_halpe,
# dataset_aic,
# dataset_crowdpose,
# dataset_mpii,
# dataset_jhmdb,
#
# dataset_posetrack,
],
pipeline=train_pipeline,
test_mode=False,
))