ethanscuter / simpgan Goto Github PK
View Code? Open in Web Editor NEWCode for KSEM 2018 paper SimPGAN
Code for KSEM 2018 paper SimPGAN
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'
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.