"mask_valid" parameter

[kalyani7195]

Hi! Thanks for the great work! 💯
I am a bit confused about this parameter the in yaml file --
use_mask_valid: True # Requires "task" mask_valid to be saved to disk

When I set that to False --I get the following error while
fine-tuning a ViT based model on the NYU dataset--

Original Traceback (most recent call last):
  File "/gscratch/sciencehub/kmarathe/miniconda3/envs/py38/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop
    data = fetcher.fetch(index)
  File "/gscratch/sciencehub/kmarathe/miniconda3/envs/py38/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 "/gscratch/sciencehub/kmarathe/miniconda3/envs/py38/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/mmfs1/gscratch/sciencehub/kmarathe/models/SSL/MAE/mae/evals/MultiMAE/utils/dataset_folder.py", line 307, in __getitem__
    sample_dict = self.transform(sample_dict)
  File "/mmfs1/gscratch/sciencehub/kmarathe/models/SSL/MAE/mae/evals/MultiMAE/utils/dataset_regression.py", line 120, in __call__
    task_dict['mask_valid'] = (task_dict['mask_valid'] == 255)[None]

KeyError: 'mask_valid'

When I set that to True -- I get the following. I used the provided script to create the NYU dataset. -- It did save train test data and depth maps, but there was no folder called mask_valid.

RuntimeError: Found 0 logs in subfolders of: /gscratch/sciencehub/vision_datasets/NYU/train/mask_valid
Supported extensions are: .jpg,.jpeg,.png,.ppm,.bmp,.pgm,.tif,.tiff,.webp,.jpx

I am definitely missing something and any help here is greatly appreciated.

Thanks and regards,
Kalyani

[tyleryzhu]

Does #25 help with your query? I found a similar problem and tracked it down to that.

[ko973]

Pls I beg you can you help

[ko973]

Does #25 help with your query? I found a similar problem and tracked it down to that.

Pls pls I need more to uncoding pls help me I doing it 3rh day .Can I send you all to uncoding

[ko973]

Hi! Thanks for the great work! 💯
I am a bit confused about this parameter the in yaml file --
use_mask_valid: True # Requires "task" mask_valid to be saved to disk

When I set that to False --I get the following error while
fine-tuning a ViT based model on the NYU dataset--

Original Traceback (most recent call last):
  File "/gscratch/sciencehub/kmarathe/miniconda3/envs/py38/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 302, in _worker_loop
    data = fetcher.fetch(index)
  File "/gscratch/sciencehub/kmarathe/miniconda3/envs/py38/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 "/gscratch/sciencehub/kmarathe/miniconda3/envs/py38/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/mmfs1/gscratch/sciencehub/kmarathe/models/SSL/MAE/mae/evals/MultiMAE/utils/dataset_folder.py", line 307, in __getitem__
    sample_dict = self.transform(sample_dict)
  File "/mmfs1/gscratch/sciencehub/kmarathe/models/SSL/MAE/mae/evals/MultiMAE/utils/dataset_regression.py", line 120, in __call__
    task_dict['mask_valid'] = (task_dict['mask_valid'] == 255)[None]

KeyError: 'mask_valid'

When I set that to True -- I get the following. I used the provided script to create the NYU dataset. -- It did save train test data and depth maps, but there was no folder called mask_valid.

RuntimeError: Found 0 logs in subfolders of: /gscratch/sciencehub/vision_datasets/NYU/train/mask_valid
Supported extensions are: .jpg,.jpeg,.png,.ppm,.bmp,.pgm,.tif,.tiff,.webp,.jpx

I am definitely missing something and any help here is greatly appreciated.

Thanks and regards,
Kalyani

I have more ia what I found under my ID NUMBER .I need so much help with it pls pls can I send you all data I found

[ShreyGanatra]

Facing similar problem as @kalyani7195.

I am getting this as dataset after running prepare_nyuv2.py

Any help here is greatly appreciated.