Skip to content

Navigate link test.py pytorch-syncbn Usage section #159

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Navigate link test.py pytorch-syncbn Usage section #159

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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 inference/interact/fbrs/model/syncbn/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,7 @@ JIT and cpp extensions are supported after PyTorch0.4, however it is highly reco

## Usage

Please refer to [`test.py`](./test.py) for testing the difference between `nn.BatchNorm2d` and `modules.nn.BatchNorm2d`
Please refer to [`test.py`](https://github.com/tamakoji/pytorch-syncbn/blob/master/test.py) for testing the difference between `nn.BatchNorm2d` and `modules.nn.BatchNorm2d`

```
import torch
Expand Down Expand Up @@ -124,4 +124,4 @@ z = model(x)

Note that in the implementation, normalization with N is performed at step (2) and above equation and implementation is not exactly the same, but mathematically is same.

You can go deeper on above explanation at [Kevin Zakka's Blog](https://kevinzakka.github.io/2016/09/14/batch_normalization/)
You can go deeper on above explanation at [Kevin Zakka's Blog](https://kevinzakka.github.io/2016/09/14/batch_normalization/)