search

dearleiii / PIRM-2018-SISR-Challenge

Super Resolution
https://www.pirm2018.org/PIRM-SR.html
2 stars 0 forks source link

Add testing data to model directly #16

Open dearleiii opened 6 years ago

dearleiii commented 6 years ago

===== HYPERPARAMETERS ===== batch_size= 50 epochs= 100 learning_rate= 0.001

0 score:: torch.Size([50, 1]) outputs: torch.Size([50, 1]) THCudaCheck FAIL file=/pytorch/aten/src/THC/generic/THCStorage.cu line=58 error=2 : out of memory Traceback (most recent call last): File "model1.py", line 219, in trainNet(approximator, batch_size = 50, n_epochs = 100, learning_rate = 0.001) File "model1.py", line 153, in trainNet optimizer.step() File "/home/home2/leichen/.local/lib/python3.5/site-packages/torch/optim/adam.py", line 76, in step state['exp_avg_sq'] = torch.zeros_like(p.data) RuntimeError: cuda runtime error (2) : out of memory at /pytorch/aten/src/THC/generic/THCStorage.cu:58

dearleiii commented 6 years ago

Using Encoding.nn.DataParallel source code for GPU average usage