adam9500370/facial-expression-generation

facial-expression-generation's Issues

Iteration over 0-dim tensor

Hello!
Thank you for your work

I'm trying to run your code for training, but I stucked with the error : TypeError: iteration over a 0-d tensor

....
(conv1): Conv2d(2048, 1, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(conv2): Conv2d(2048, 7, kernel_size=(1, 1), stride=(1, 1), bias=False)
)
The number of parameters: 44735424
/home/jupyter/Facial-Expression-Generation/solver.py:137: UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead.
return Variable(x, volatile=volatile)
Traceback (most recent call last):
File "main.py", line 119, in
main(config)
File "main.py", line 49, in main
solver.train()
File "/home/jupyter/Facial-Expression-Generation/solver.py", line 294, in train
log = ["{:.2f}".format(acc) for acc in accuracies.data.cpu()]
File "/opt/anaconda3/lib/python3.7/site-packages/torch/tensor.py", line 422, in iter
raise TypeError('iteration over a 0-d tensor')
TypeError: iteration over a 0-d tensor

May be you can help me?

RuntimeError: CUDA out of memory

Hi!
I remembered about Facial Expression GAN I trained 2 monthes ago with your code, and wanted to test it. But I always get

RuntimeError: CUDA out of memory. Tried to allocate 32.00 MiB (GPU 0; 7.43 GiB total capacity; 6.37 GiB already allocated; 20.94 MiB free; 446.36 MiB cached)
what should i do to prevent it?