prasanna1991 / latentmixing Goto Github PK

File "/[...]/LatentMixing/utils/__init__.py", line 10, in <module> from progress.bar import Bar as Bar ModuleNotFoundError: No module named 'progress'

Could you please add it to the github repo?

Hi, thank you for the work, I am a bit confused when I read your code about interleave. can you explain this part a bit more/
`
def interleave_offsets(batch, nu):
groups = [batch // (nu + 1)] * (nu + 1)
for x in range(batch - sum(groups)):
groups[-x - 1] += 1
offsets = [0]
for g in groups:
offsets.append(offsets[-1] + g)
assert offsets[-1] == batch
return offsets

def interleave(xy, batch):
nu = len(xy) - 1
offsets = interleave_offsets(batch, nu)
xy = [[v[offsets[p]:offsets[p + 1]] for p in range(nu + 1)] for v in xy]
for i in range(1, nu + 1):
xy[0][i], xy[i][i] = xy[i][i], xy[0][i]
return [torch.cat(v, dim=0) for v in xy]
`

set val_iteration=250 batchsize=64 , but the len(datasetTrainLabeled)=7311, len(datasetTrainUnLabelled)=96512, this can cover full labeled dataset and unlabeled dataset when training? Thanks for your time.

Hi, great work, thanks for the code~
I have a few questions about the ISIC dataset split.
It seems that the official website does not provide the training data split, and in your paper, you use 350,600 and 1200 for train, val and test.
Do you mind providing the txt file of the split? It will be very helpful!!
Thanks for your time !!

Hello, I have been reading this paper of yours recently, and I am very interested in the semi-supervised classification method you proposed. However, I have encountered some problems when I reproduce this code, so I would like to ask you for some advice. when I run latent-mixing.py, I encountered the following problems:
Traceback (most recent call last):
File "E:/图像分类/2/LatentMixing-master/latent-mixing.py", line 634, in
main()
File "E:/图像分类/2/LatentMixing-master/latent-mixing.py", line 335, in main
train_criterion, epoch, use_cuda, args.mixup, args.noSharp)
File "E:/图像分类/2/LatentMixing-master/latent-mixing.py", line 394, in train
(inputs_x, targets_x) = labeled_train_iter.next()
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 326 and 371 in dimension 3 at C:\w\1\s\windows\pytorch\aten\src\TH/generic/THTensor.cpp:689
Looking forward to your reply!
Thank you very much!