Skip to content

Replace model.forward() with model() #53

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Nov 20, 2018
Merged

Replace model.forward() with model() #53

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4850dd4
Replace model.forward with model
jaintj95 Nov 19, 2018
40fb603
Replace model.forward with model
jaintj95 Nov 19, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions intro-to-pytorch/Part 3 - Training Neural Networks (Exercises).ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -380,7 +380,7 @@
"optimizer.zero_grad()\n",
"\n",
"# Forward pass, then backward pass, then update weights\n",
"output = model.forward(images)\n",
"output = model(images)\n",
"loss = criterion(output, labels)\n",
"loss.backward()\n",
"print('Gradient -', model[0].weight.grad)"
Expand Down Expand Up @@ -463,7 +463,7 @@
"img = images[0].view(1, 784)\n",
"# Turn off gradients to speed up this part\n",
"with torch.no_grad():\n",
" logits = model.forward(img)\n",
" logits = model(img)\n",
"\n",
"# Output of the network are logits, need to take softmax for probabilities\n",
"ps = F.softmax(logits, dim=1)\n",
Expand Down
6 changes: 3 additions & 3 deletions intro-to-pytorch/Part 3 - Training Neural Networks (Solution).ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -494,7 +494,7 @@
"optimizer.zero_grad()\n",
"\n",
"# Forward pass, then backward pass, then update weights\n",
"output = model.forward(images)\n",
"output = model(images)\n",
"loss = criterion(output, labels)\n",
"loss.backward()\n",
"print('Gradient -', model[0].weight.grad)"
Expand Down Expand Up @@ -581,7 +581,7 @@
" # TODO: Training pass\n",
" optimizer.zero_grad()\n",
" \n",
" output = model.forward(images)\n",
" output = model(images)\n",
" loss = criterion(output, labels)\n",
" loss.backward()\n",
" optimizer.step()\n",
Expand Down Expand Up @@ -625,7 +625,7 @@
"img = images[0].view(1, 784)\n",
"# Turn off gradients to speed up this part\n",
"with torch.no_grad():\n",
" logps = model.forward(img)\n",
" logps = model(img)\n",
"\n",
"# Output of the network are logits, need to take softmax for probabilities\n",
"ps = torch.exp(logps)\n",
Expand Down