ValueError: Key img_path is not in available keys.

[gogoworker]

When I run each coco class config file, I encounter the same issue every time. I only modified the path of the coco dataset. Here are the detailed errors:
05/18 13:10:57 - mmengine - INFO - Checkpoints will be saved to /media/cs303-1/disk1/xdn/mmyolo/work_dirs/yolov8_s_syncbn_fast_8xb16-500e_coco.
Traceback (most recent call last):
File "tools/train.py", line 123, in
main()
File "tools/train.py", line 119, in main
runner.train()
File "/home/cs303-1/miniconda3/envs/mmyolo/lib/python3.8/site-packages/mmengine/runner/runner.py", line 1777, in train
model = self.train_loop.run() # type: ignore
File "/home/cs303-1/miniconda3/envs/mmyolo/lib/python3.8/site-packages/mmengine/runner/loops.py", line 96, in run
self.run_epoch()
File "/home/cs303-1/miniconda3/envs/mmyolo/lib/python3.8/site-packages/mmengine/runner/loops.py", line 112, in run_epoch
for idx, data_batch in enumerate(self.dataloader):
File "/home/cs303-1/miniconda3/envs/mmyolo/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 521, in next
data = self._next_data()
File "/home/cs303-1/miniconda3/envs/mmyolo/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1203, in _next_data
return self._process_data(data)
File "/home/cs303-1/miniconda3/envs/mmyolo/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1229, in _process_data
data.reraise()
File "/home/cs303-1/miniconda3/envs/mmyolo/lib/python3.8/site-packages/torch/_utils.py", line 434, in reraise
raise exception
ValueError: Caught ValueError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/cs303-1/miniconda3/envs/mmyolo/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
data = fetcher.fetch(index)
File "/home/cs303-1/miniconda3/envs/mmyolo/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/cs303-1/miniconda3/envs/mmyolo/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/cs303-1/miniconda3/envs/mmyolo/lib/python3.8/site-packages/mmengine/dataset/base_dataset.py", line 410, in getitem
data = self.prepare_data(idx)
File "/media/cs303-1/disk1/xdn/mmyolo/mmyolo/datasets/yolov5_coco.py", line 53, in prepare_data
return self.pipeline(data_info)
File "/home/cs303-1/miniconda3/envs/mmyolo/lib/python3.8/site-packages/mmengine/dataset/base_dataset.py", line 60, in call
data = t(data)
File "/home/cs303-1/miniconda3/envs/mmyolo/lib/python3.8/site-packages/mmcv/transforms/base.py", line 12, in call
return self.transform(results)
File "/home/cs303-1/miniconda3/envs/mmyolo/lib/python3.8/site-packages/mmdet/structures/bbox/box_type.py", line 267, in wrapper
return func(self, results)
File "/home/cs303-1/miniconda3/envs/mmyolo/lib/python3.8/site-packages/mmdet/datasets/transforms/transforms.py", line 1699, in transform
results = self.aug(**results)
File "/home/cs303-1/miniconda3/envs/mmyolo/lib/python3.8/site-packages/albumentations/core/composition.py", line 247, in call
self._check_args(**data)
File "/home/cs303-1/miniconda3/envs/mmyolo/lib/python3.8/site-packages/albumentations/core/composition.py", line 316, in _check_args
raise ValueError(msg)
ValueError: Key img_path is not in available keys.
why?How can I resolve this issue?

[macwx]

我也遇到了同样的问题，请问你解决了马

[gogoworker]

我直接把错的那里注释掉了了，然后continue一下，跑起来了但是不知道会不会有什么隐患，暂时解决了

[macwx]

哪个地方呢，是composition.py的第316行吗

[gogoworker]

你好，具体哪一行我忘记了，就是一个if语句判断他是不是available key那里，里面是抛出异常的代码

[N176CM]

composition.py文件注释掉322到324行，把那个判断整个注释了，就好了，暂时没看出啥影响

[Syed05]

Facing the same issue. Did anyone solve this?

[debugmax]

thanks for your sharing. I slove it.

[anying111]

我在其他项目中遇到了这个问题。当我可以运行时，albumentations 的版本是 1.4.8。也许你可以试试。pip install albumentations==1.3.1

you're right, thanks

[diego20050818]

thanks，very useful tips

[Seatosoak]

完美解决了我的问题！！！

[bigqinghit]

感谢，我也遇到了这个问题。我查看我的albumentations版本是1.4.18，然后执行了pip install albumentations==1.3.1，也可以正常训练了

[leo038]

solved. thank you!