Skip to content

train #13

Description

@he0713

When I train on the LUNA16 dataset again, I will have the following error, but why does your original code have this error? I'm going to set it up exactly according to your config. Hope you can answer, thanks.

'/home/hpc/.conda/envs/CBCTrecon/bin/python /media/hpc/397C-DC85/DIF-Net-main/code/train.py
Namespace(batch_size=1, combine='mlp', dst_list='knee_cbct', epoch=400, eval_npoint=100000, lr=0.01, name='baseline', num_points=10000, num_views=10, num_workers=2, out_res=256, random_views=False, split='test', view_offset=0, visualize=False)
mixed_dataset: ['knee_cbct']
CBCT_dataset, name: knee_cbct, split: train, len: 71.
mixed_dataset: ['knee_cbct']
CBCT_dataset, name: knee_cbct, split: eval, len: 5.
DIF_Net, mid_ch: 128, combine: mlp
epoch: 0, loss: 0.03199
Traceback (most recent call last):
File "/media/hpc/397C-DC85/DIF-Net-main/code/train.py", line 112, in
metrics, _ = eval_one_epoch(
File "/media/hpc/397C-DC85/DIF-Net-main/code/evaluate.py", line 41, in eval_one_epoch
ssim = structural_similarity(image, output)
File "/home/hpc/.local/lib/python3.8/site-packages/skimage/metrics/_structural_similarity.py", line 194, in structural_similarity
raise ValueError(
ValueError: Since image dtype is floating point, you must specify the data_range parameter. Please read the documentation carefully (including the note). It is recommended that you always specify the data_range anyway.

Process finished with exit code 1'

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions