davrot/pytutorial
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update README.md

Browse source 
Signed-off-by: David Rotermund <54365609+davrot@users.noreply.github.com>
This commit is contained in:
David Rotermund 2024-01-05 15:40:00 +01:00 committed by GitHub
parent 832128acc9
commit d6acd3b230
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
pytorch/own_layer/README.md
View file

@ -17,7 +17,7 @@ I am rewriting the code for [Linear](https://pytorch.org/docs/stable/_modules/to
\_\_init\_\_() : It contains a tensor for the weights and optionally a second tensor for the bias. Both tensors are wrapped within the torch.nn.Parameter class. This is necessary, otherwise the optimizer will not find them. Afterwards the tensors will be initialized via reset_parameters(self).
reset_parameters(): I copied it from the original code.
reset_parameters(): I copied it from the original code. Doesn't need to be there could also be handled directly in the init.
forward(): We get an input tensor and need to produce an output tensor. Please remember that dimension 0 contains the batch. Here we just multiply the input with the weights and add the bias to it (if available).