nadeemlab / cep Goto Github PK

Hi, Following your instructions I am trying to train CLTS-GAN on the public dataset oldIt_public_data.

My input arguments are as follows:

--dataroot ./Data/cep/FoldIt_public --model cltsgan --name "cltsgan_model_name"

I get the following error

Traceback (most recent call last):
  File "/snap/pycharm-professional/306/plugins/python/helpers/pydev/pydevd.py", line 1496, in _exec
    pydev_imports.execfile(file, globals, locals)  # execute the script
  File "/snap/pycharm-professional/306/plugins/python/helpers/pydev/_pydev_imps/_pydev_execfile.py", line 18, in execfile
    exec(compile(contents+"\n", file, 'exec'), glob, loc)
  File "/home/eposner/Repositories/CEP/train.py", line 51, in <module>
    model.optimize_parameters()   # calculate loss functions, get gradients, update network weights
  File "/home/eposner/Repositories/CEP/models/cltsgan_model.py", line 262, in optimize_parameters
    self.forward()      # compute fake images and reconstruction images.
  File "/home/eposner/Repositories/CEP/models/cltsgan_model.py", line 136, in forward
    self.rec_A   = self.netG_B(self.fake_B, self.nfake_B, self.tfake_B)   # G_B(G_A(A))
  File "/home/eposner/anaconda3/envs/CEP/lib/python3.6/site-packages/torch/nn/modules/module.py", line 532, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/eposner/Repositories/CEP/models/networks.py", line 619, in forward
    out = out + self.n_parm[i] * n
RuntimeError: The size of tensor a (128) must match the size of tensor b (160) at non-singleton dimension 1

I found out the setting --ngf 80 solves this (just like in the googlecolab notebook).
Consider setting it a default value for the dataset?

I noticed in your paper that high intensity specular reflections can be extracted and stored in separate parameters by a loss, and I would like to know exactly how this is done? Is it convenient for you to provide this part of the code?

Hi,
I would like to get the IoU and Dice metrics as done in the FoldIt paper (Table 1), however I cannot find the two sequences that you used to get these metrics. Could you please tell me where I could find them or are they not available?
Thank you

Training data and test data cannot be downloaded

Hello there,

I cannot find any for MissedSurface ISBI'21. Is it released yet? Kindly let me know about it. I need to check that code, for the project I am working on. Thanks

When I read your paper of CLTS-GAN, I found that there was an experiment in which one OC diagram was used to enhance the other one, but I could not find the corresponding part in your code. Could you please tell me how to test this part?
Besides, how does the triple augment work in the paper?
Looking forward to your reply!

When I use the pre-trained model to test the CLTS-GAN，I meet the problem, which is also happened when I use my model to test.
Can you tell me the reason, please?
thanks!

RuntimeError: Error(s) in loading state_dict for invResnetGenerator:
Missing key(s) in state_dict: "model.10.conv_block.6.weight", "model.10.conv_block.6.bias", "model.11.conv_block.6.weight", "model.11.conv_block.6.bias", "model.12.conv_block.6.weight", "model.12.conv_block.6.bias", "model.13.conv_block.6.weight", "model.13.conv_block.6.bias", "model.14.conv_block.6.weight", "model.14.conv_block.6.bias", "model.15.conv_block.6.weight", "model.15.conv_block.6.bias", "model.16.conv_block.6.weight", "model.16.conv_block.6.bias", "model.17.conv_block.6.weight", "model.17.conv_block.6.bias", "model.18.conv_block.6.weight", "model.18.conv_block.6.bias".
Unexpected key(s) in state_dict: "model.10.conv_block.5.weight", "model.10.conv_block.5.bias", "model.11.conv_block.5.weight", "model.11.conv_block.5.bias", "model.12.conv_block.5.weight", "model.12.conv_block.5.bias", "model.13.conv_block.5.weight", "model.13.conv_block.5.bias", "model.14.conv_block.5.weight", "model.14.conv_block.5.bias", "model.15.conv_block.5.weight", "model.15.conv_block.5.bias", "model.16.conv_block.5.weight", "model.16.conv_block.5.bias", "model.17.conv_block.5.weight", "model.17.conv_block.5.bias", "model.18.conv_block.5.weight", "model.18.conv_block.5.bias".

hiiiii,Thank you for your contribution.
Do you have OC map for depth? (original image)
Looking forward to your reply.

Hello, I have some question about the training command. Does "foldit_model_name" in training command represent the concrete model name? Like 'foldit_model_public/latest_net_G_A.pth'.

hi，
i can't download ZIP.File is corrupted.
What's going on here?