andre/PyTorch-Tutorial
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge pull request #32 from Hierom/patch-2

Browse Source 
Fixing error accurate and error tensor to numpy
This commit is contained in:
Morvan
2018-07-15 20:24:35 +08:00
committed by GitHub
parent d053113d3a 99158fd0ca
commit b161aa063f
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tutorial-contents/502_GPU.py
View File

@ -70,8 +70,8 @@ for epoch in range(EPOCH):
# !!!!!!!! Change in here !!!!!!!!! #
pred_y = torch.max(test_output, 1)[1].cuda().data.squeeze() # move the computation in GPU
accuracy = torch.sum(pred_y == test_y) / test_y.size(0)
print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy(), '| test accuracy: %.2f' % accuracy)
accuracy = torch.sum(pred_y == test_y).type(torch.FloatTensor) / test_y.size(0)
print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.cpu().numpy(), '| test accuracy: %.2f' % accuracy)
test_output = cnn(test_x[:10])