Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Time-lapse saved from Fiji are not compatible #6

Open
romainGuiet opened this issue Jul 26, 2023 · 0 comments
Open

Time-lapse saved from Fiji are not compatible #6

romainGuiet opened this issue Jul 26, 2023 · 0 comments

Comments

@romainGuiet
Copy link
Contributor

Dear @bentaculum ,

I tried to save time-lapse as a single tif file from Fiji and got the error below , when starting the training :

train.py: Run name `h2b_backbone_unet`
set_device.py: PyTorch uses GPUs 0.
train.py: Build visualisation datasets.
tarrow_dataset.py: Load images 0-1
Traceback (most recent call last):
  File "train.py", line 453, in <module>
    main(args)
  File "train.py", line 344, in main
    data_visuals = tuple(
  File "train.py", line 345, in <genexpr>
    _build_dataset(
  File "train.py", line 224, in _build_dataset
    return TarrowDataset(
  File "C:\Users\guiet\AppData\Local\mambaforge\envs\tarrow_4\lib\site-packages\tarrow\data\tarrow_dataset.py", line 166, in __init__
    raise NotImplementedError(
NotImplementedError: only 2D timelapses supported (total image shape: torch.Size([1, 1, 240, 540, 540]))

Current workaround is to save the time-lapse from Fiji using: File> Save As > Image Sequence

Best

R

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant