On the Environmental Issues of Experimental Operation

[feifancoco]

Hello, how can I run your code after I download it again? Do you need to fully install the installation prompts provided by the "MMClassification" and "PaddleClas" tool boxes? Do you need to install the folder 'mm2'? When I run 'Python - m torch. distributed. launch -- nproc_per_node=2 train. py configs/apvit/RAF. py -- launcher pytorch', there are errors: ModuleNotFoundError: No module named 'mmcv' and 'torch. distributed. final. multiprocessing. errors. ChildFailedError:' I would like to do some research based on your research and cite your paper. I hope to receive your reply.

[feifancoco]

And display: "cannot import name 'Config' from 'mmcv' (unknown location)", how to handle it.

[feifancoco]

May I ask what caused the following error

---

Traceback (most recent call last):

File "/opt/home/hut/miniconda3/envs/pytorch18/lib/python3.9/site-packages/mmcv/utils/registry.py", line 52, in build_ from_ cfg

return obj_ cls(**args)

File "/opt/home/wk/APViT-main/mmcls/datasets/base_dataset.py", line 42, in __ init__

self.data_ infos = self.load_ annotations()

File "/opt/home/wk/APViT-main/mmcls/datasets/raf.py", line 128, in load_ annotations

samples = [[i[0].replace('_aligned', ''), i[1]] for i in samples]

File "/opt/home/wk/APViT-main/mmcls/datasets/raf.py", line 128, in

samples = [[i[0].replace('_aligned', ''), i[1]] for i in samples]

IndexError: list index out of range

During handling of the above exception, another exception occurred:

Traceback (most recent call last):

File "/opt/home/wk/APViT-main/train.py", line 160, in

main()

File "/opt/home/wk/APViT-main/train.py", line 135, in main

datasets = [build_dataset(cfg.data.train)]

File "/opt/home/wk/APViT-main/mmcls/datasets/builder.py", line 35, in build_ dataset

ds = build_ dataset(cfg['dataset'], default_args)

File "/opt/home/wk/APViT-main/mmcls/datasets/builder.py", line 39, in build_ dataset

dataset = build_ from_ cfg(cfg, DATASETS, default_args)

File "/opt/home/hut/miniconda3/envs/pytorch18/lib/python3.9/site-packages/mmcv/utils/registry.py", line 55, in build_ from_ cfg

raise type(e)(f'{obj_cls.name}: {e}')

IndexError: RAF: list index out of range

Traceback (most recent call last):

File "/opt/home/hut/miniconda3/envs/pytorch18/lib/python3.9/site-packages/mmcv/utils/registry.py", line 52, in build_ from_ cfg

return obj_ cls(**args)

File "/opt/home/wk/APViT-main/mmcls/datasets/base_dataset.py", line 42, in __ init__

self.data_ infos = self.load_ annotations()

File "/opt/home/wk/APViT-main/mmcls/datasets/raf.py", line 128, in load_ annotations

samples = [[i[0].replace('_aligned', ''), i[1]] for i in samples]

File "/opt/home/wk/APViT-main/mmcls/datasets/raf.py", line 128, in

samples = [[i[0].replace('_aligned', ''), i[1]] for i in samples]

IndexError: list index out of range

During handling of the above exception, another exception occurred:

Traceback (most recent call last):

File "/opt/home/wk/APViT-main/train.py", line 160, in

main()

File "/opt/home/wk/APViT-main/train.py", line 135, in main

datasets = [build_dataset(cfg.data.train)]

File "/opt/home/wk/APViT-main/mmcls/datasets/builder.py", line 35, in build_ dataset

ds = build_ dataset(cfg['dataset'], default_args)

File "/opt/home/wk/APViT-main/mmcls/datasets/builder.py", line 39, in build_ dataset

dataset = build_ from_ cfg(cfg, DATASETS, default_args)

File "/opt/home/hut/miniconda3/envs/pytorch18/lib/python3.9/site-packages/mmcv/utils/registry.py", line 55, in build_ from_ cfg

raise type(e)(f'{obj_cls.name}: {e}')

IndexError: RAF: list index out of range

ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1)

---

Is it because of a dataset preparation error?
I hope to receive your reply，and I would greatly appreciate it！

[feifancoco]

May I ask if the RAF-DB dataset you tested has been processed? In the dataset I obtained, the images of trian and test are in the same folder.

[youqingxiaozhua]

Yes, the images are aligned with MTCNN first. And the file structure should be organized to satisfy the dataloader. I will update the Readme file for better understand.