learning/annotated_deep_learning_paper_implementations
1
0
Fork 0
mirror of https://github.com/labmlai/annotated_deep_learning_paper_implementations.git synced 2025-10-29 17:57:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

Typo fixes (#125)

Browse Source
This commit is contained in:
Daniel Tse
2022-06-02 20:08:12 -07:00
committed by GitHub
parent 6a41c82b30
commit c5d9235280
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
labml_nn/optimizers/__init__.py
View File

@ -32,7 +32,7 @@ Here are some concepts on PyTorch optimizers:
### Parameter groups ### Parameter groups
PyTorch optimizers group parameters into sets called groups. PyTorch optimizers group parameters into sets called groups.
Each group can have it's own hyper-parameters like learning rates. Each group can have its own hyper-parameters like learning rates.
In most common cases there will be only one group. In most common cases there will be only one group.
This is when you initialize your optimizer with, This is when you initialize your optimizer with,
@ -47,7 +47,7 @@ You can define multiple parameter groups when initializing the optimizer:
Optimizer([{'params': model1.parameters()}, {'params': model2.parameters(), 'lr': 2}]) Optimizer([{'params': model1.parameters()}, {'params': model2.parameters(), 'lr': 2}])
``` ```
Here we pass a list of groups. Each group is a dictionary with it's parameters under the key 'params'. Here we pass a list of groups. Each group is a dictionary with its parameters under the key 'params'.
You specify any hyper-parameters as well. If the hyper parameters are not defined they will default You specify any hyper-parameters as well. If the hyper parameters are not defined they will default
to the optimizer level defaults. to the optimizer level defaults.