Denoise3d error

[zehrea]

Hello,
I trained topaz model on my dataset (even odd/ frames from tomography data collection), but when I wish to use this model to denoise a tomogram reconstructed in Etomo. I am getting the error below. Why is that?

Many thanks!
Elena

topaz denoise3d -m ../model/train_model_epoch08.sav -o denoised/ --patch-size 1024 tomo038_full.rec
INFO: Could not find any nv files on this host!

denoising with patch size=1024 and padding=48

Traceback (most recent call last):
File "/usr/local/conda/bin/topaz", line 11, in
load_entry_point('topaz-em==0.2.4', 'console_scripts', 'topaz')()
File "/usr/local/conda/lib/python3.7/site-packages/topaz/main.py", line 148, in main
args.func(args)
File "/usr/local/conda/lib/python3.7/site-packages/topaz/commands/denoise3d.py", line 773, in main
, total_volumes=total
File "/usr/local/conda/lib/python3.7/site-packages/topaz/commands/denoise3d.py", line 691, in denoise
x = model(x).squeeze(1).cpu().numpy()
File "/usr/local/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "/usr/local/conda/lib/python3.7/site-packages/topaz/denoise.py", line 476, in forward
p1 = self.enc1(x)
File "/usr/local/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "/usr/local/conda/lib/python3.7/site-packages/torch/nn/modules/container.py", line 92, in forward
input = module(input)
File "/usr/local/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 489, in call
result = self.forward(*input, **kwargs)
File "/usr/local/conda/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 320, in forward
self.padding, self.dilation, self.groups)
RuntimeError: Expected 4-dimensional input for 4-dimensional weight [48, 1, 11, 11], but got 5-dimensional input of size [1, 1, 1120, 1120, 1120] instead

[tbepler]

What happens if you use the default patch size?

[zehrea]

Hello,
Thanks for getting back to me.
I am getting the same error when I do not specify patch size

[tbepler]

How large is your tomogram? Can you make a small version that reproduces this issue for debugging purposes?

[zehrea]

Hello,

I tried on whole reconstruction (4092 544 5760) and on the small section as well (708 917 130), same issue.

Thanks for your help

[tbepler]

Did you manage to figure this out or create of mini tomogram that reproduces the issue I can look at?