ethanscuter / simpgan Goto Github PK

Hi, thank you for the nice work. I got the following error when running "pretrain.py". How can I solve this issue?

/home/redhat/cd/lib/python3.6/site-packages/torchvision-0.2.0-py3.6.egg/torchvision/transforms/transforms.py:156: UserWarning: The use of the transforms.Scale transform is deprecated, please use transforms.Resize instead.
Traceback (most recent call last):
File "pretrain.py", line 188, in
softmax_pretrain_on_datasets(source)
File "pretrain.py", line 182, in softmax_pretrain_on_datasets
softmax_model_pretrain(train_list, train_dir, class_count, './' + source + '_softmax_pretrain.pkl')
File "pretrain.py", line 146, in softmax_model_pretrain
out_nouse, outputs = model(images)
File "/home/redhat/cd/lib/python3.6/site-packages/torch/nn/modules/module.py", line 357, in call
result = self.forward(*input, **kwargs)
File "/home/redhat/cd/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 73, in forward
outputs = self.parallel_apply(replicas, inputs, kwargs)
File "/home/redhat/cd/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 83, in parallel_apply
return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
File "/home/redhat/cd/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 67, in parallel_apply
raise output
File "/home/redhat/cd/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 42, in _worker
output = module(*input, **kwargs)
File "/home/redhat/cd/lib/python3.6/site-packages/torch/nn/modules/module.py", line 357, in call
result = self.forward(*input, **kwargs)
File "pretrain.py", line 106, in forward
out = self.fc(x)
File "/home/redhat/cd/lib/python3.6/site-packages/torch/nn/modules/module.py", line 357, in call
result = self.forward(*input, **kwargs)
File "/home/redhat/cd/lib/python3.6/site-packages/torch/nn/modules/linear.py", line 55, in forward
return F.linear(input, self.weight, self.bias)
File "/home/redhat/cd/lib/python3.6/site-packages/torch/nn/functional.py", line 835, in linear
return torch.addmm(bias, input, weight.t())
RuntimeError: size mismatch at /opt/conda/conda-bld/pytorch_1523244252089/work/torch/lib/THC/generic/THCTensorMathBlas.cu:247

Hi is it an end to end method? Or you generate images in one phase then you apply the generated imaged in another phase in the reID system?

Did you run this code using GPU or CPU? Why it took so much time to start running the code? My PC is super slow now to run the code. :D

Hi,I download the grid and market data in grid and market directory.When i run the code, i meet the following problem which is very confuse to me.Have you ever meet this problem before,thanks.

Traceback (most recent call last):
File "main.py", line 65, in
main()
File "main.py", line 31, in main
solver.train()
File "/tmp/ReidDataSet/ReidCode/SimPGAN/solver.py", line 181, in train
market, m_labels = market_iter.next()
ValueError: too many values to unpack

Traceback (most recent call last):
File "main.py", line 8, in
from solver_double_siamese_im1 import Solver
ImportError: No module named 'solver_double_siamese_im1'