distillation python base code initial commit #1
Loading…
Reference in a new issue
No description provided.
Delete branch "ruby/tensorflow_privacy:akemi/lira_2021_fix"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Nice distillation! I'll give it a run shortly on the other machine. It might be nice to put the code being executed at the end, away from the class/function definitions
@ -0,0 +29,4 @@
test_loader = torch.utils.data.DataLoader(test_dataset, batch_size=128, shuffle=False, num_workers=2)
# Deeper neural network class to be used as teacher:
I'm assuming future commits will change this one to a resnet?
@ -0,0 +130,4 @@
print(f"Test Accuracy: {accuracy:.2f}%")
return accuracy
torch.manual_seed(42)
Why are these lines in the middle?
@ -0,0 +470,4 @@
# Initialize a ModifiedLightNNRegressor
torch.manual_seed(42)
I think we need a main function or something, I'm having a bit of trouble following the flow of this code
View command line instructions
Checkout
From your project repository, check out a new branch and test the changes.Merge
Merge the changes and update on Forgejo.Warning: The "Autodetect manual merge" setting is not enabled for this repository, you will have to mark this pull request as manually merged afterwards.