search

MedARC-AI / fMRI-reconstruction-NSD

fMRI-to-image reconstruction on the NSD dataset.
MIT License
308 stars 44 forks source link

Error when using --no-hidden flag #35

Closed MSurfer20 closed 12 months ago

MSurfer20 commented 12 months ago

If we run the script with the hidden arg set to False, the following error is encountered

Traceback (most recent call last):
  File "/home2/suyash.mathur/Brain_project/fMRI-reconstruction-NSD/src/Train_MindEy
e.py", line 604, in <module>
    clip_voxels, clip_voxels_proj = diffusion_prior.module.voxel2clip(voxel) if distri
buted else diffusion_prior.voxel2clip(voxel)
ValueError: not enough values to unpack (expected 2, got 1)
Traceback (most recent call last):
  File "/home2/suyash.mathur/Brain_project/fMRI-reconstruction-NSD/src/Train_MindEy
e.py", line 604, in <module>
    clip_voxels, clip_voxels_proj = diffusion_prior.module.voxel2clip(voxel) if distri
buted else diffusion_prior.voxel2clip(voxel)
ValueError: not enough values to unpack (expected 2, got 1)
Traceback (most recent call last):
  File "/home2/suyash.mathur/Brain_project/fMRI-reconstruction-NSD/src/Train_MindEy
e.py", line 604, in <module>
    clip_voxels, clip_voxels_proj = diffusion_prior.module.voxel2clip(voxel) if distri
buted else diffusion_prior.voxel2clip(voxel)
ValueError: not enough values to unpack (expected 2, got 1)
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0
 (pid: 2575) of binary: /home2/suyash.mathur/anaconda3/envs/mindeye/bin/python
Traceback (most recent call last):
  File "/home2/suyash.mathur/anaconda3/envs/mindeye/bin/accelerate", line 8, in <modul
e>
    sys.exit(main())
  File "/home2/suyash.mathur/anaconda3/envs/mindeye/lib/python3.10/site-packages/accel
erate/commands/accelerate_cli.py", line 47, in main
    args.func(args)
  File "/home2/suyash.mathur/anaconda3/envs/mindeye/lib/python3.10/site-packages/accel
erate/commands/launch.py", line 977, in launch_command
    multi_gpu_launcher(args)
  File "/home2/suyash.mathur/anaconda3/envs/mindeye/lib/python3.10/site-packages/accel
erate/commands/launch.py", line 646, in multi_gpu_launcher
    distrib_run.run(args)
  File "/home2/suyash.mathur/anaconda3/envs/mindeye/lib/python3.10/site-packages/torch
/distributed/run.py", line 753, in run
[
MSurfer20 commented 12 months ago

Nvm, figured out wrong usage of use_projector argument.