Skip to content
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

Update tensors and autograd #1185

Merged
merged 17 commits into from
Dec 30, 2020
Merged

Update tensors and autograd #1185

Changes from 1 commit
Commits
Show all changes
17 commits
Select commit Hold shift + click to select a range
e62ee7c
Update tensor_tutorial.py
subramen Sep 29, 2020
0e867c7
Update autograd_tutorial.py
subramen Oct 9, 2020
e874967
Merge branch 'master' into 60mb_setup
brianjo Oct 13, 2020
edf2495
Fix import
subramen Oct 14, 2020
6d094b7
Fix import
subramen Oct 14, 2020
cd6f97a
Fix import
subramen Oct 14, 2020
e0b21e3
Fixes issues in tensor, updates autograd
subramen Oct 20, 2020
bc50302
Adds "what is pytorch" to homepage
subramen Oct 20, 2020
0d16b7b
Fixes formatting
subramen Oct 20, 2020
6d91b98
Fix typo
subramen Oct 20, 2020
75efe8b
Fixes typo
subramen Oct 20, 2020
adee684
fix failing test
subramen Oct 21, 2020
d7b0648
Merge branch 'master' into 60mb_setup
subramen Oct 26, 2020
422296e
Merge branch 'master' into 60mb_setup
subramen Oct 30, 2020
9dc3c79
Make suggested changes
subramen Nov 11, 2020
f56befe
Merge branch 'master' into 60mb_setup
subramen Dec 28, 2020
9568cd2
Merge branch 'master' into 60mb_setup
subramen Dec 30, 2020
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
Prev Previous commit
Next Next commit
Fix typo
  • Loading branch information
@subramen
subramen committed Oct 20, 2020
commit 6d91b988d5d8c1d076f0cd500f9aff50f1e275e9
2 changes: 1 addition & 1 deletion beginner_source/blitz/autograd_tutorial.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@
model = torchvision.models.resnet18(pretrained=True)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think you need a bit more text explanation here - either in text or in code comments.

very roughly something like:
"Let's start by looking at the a single training step. Here we load an existing pretrained resnet18 model, create random input data tensor of shape 3x64x64, and some random output labels."

...

Then we might want to pause again and say "here we push the data forward through the model, calculate the loss, and then call .backward() to collect the gradients for each parameter in the model. <more detail here on what backward does (i.e. where are the gradients stored?>

....

Then we say: "Finally we load in an optimizer, in this case SGD, with a learning rate and momentum of ..., and call .step() to use our gradients and step backwards"

That's a basic model, below we dive a bit deeper into what is going on when we call .backward()

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I agree with Randall here

data = torch.rand(1, 3, 64, 64)
labels = torch.rand(1, 1000)
prediction = model(x) # forward pass
prediction = model(data) # forward pass
loss = prediction - labels
loss.backward() # backward pass

Expand Down