mirrors/mmengine
1
0
Fork 0
mirror of https://github.com/open-mmlab/mmengine.git synced 2025-06-03 21:54:44 +08:00
Code Issues Projects Releases Wiki Activity

[Docs] Fix a link error in initialization tutorial (#843)

Browse Source
This commit is contained in:
Mashiro 2022-12-23 12:17:08 +08:00 committed by GitHub
parent bb11f4d392
commit 7af68d1b5e
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
docs/en/advanced_tutorials/initialize.md
View File

@ -278,7 +278,7 @@ Initialized by user-defined `init_weights` in ToyConv
### Ininitailize module with function
As mentioned in prior \[section\](#Customize the initialization method), we could customize our initialization in `init_weights`. To make it more convenient to initialize modules, MMEngine provides a series of **module initialization functions** to initialize the whole module based on `torch.nn.init`. For example, we want to initialize the weights of the convolutional layer with normal distribution and initialize the bias of the convolutional layer with a constant. The implementation of `torch.nn.init` is as follows:
As mentioned in prior [section](#customize-the-initialization-method), we could customize our initialization in `init_weights`. To make it more convenient to initialize modules, MMEngine provides a series of **module initialization functions** to initialize the whole module based on `torch.nn.init`. For example, we want to initialize the weights of the convolutional layer with normal distribution and initialize the bias of the convolutional layer with a constant. The implementation of `torch.nn.init` is as follows:
```python
from torch.nn.init import normal_, constant_