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

[Doc] delete the error comment in docs (#514)

Browse Source
This commit is contained in:
vansin 2022-10-08 11:34:35 +08:00 committed by GitHub
parent 4e5c40b51b
commit 1f63d2436c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 0 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
docs/zh_cn/tutorials/registry.md
View File

@ -92,7 +92,6 @@ activation = ACTIVATION.build(act_cfg)
output = activation(input)
# call Sigmoid.forward
print(output)
# tensor([0.0159, 0.0815])
```
如果我们想使用 `ReLU`，仅需修改配置。
@ -103,7 +102,6 @@ activation = ACTIVATION.build(act_cfg)
output = activation(input)
# call Sigmoid.forward
print(output)
# tensor([0.0159, 0.0815])
```
如果我们希望在创建实例前检查输入参数的类型（或者任何其他操作），我们可以实现一个构建方法并将其传递给注册器从而实现自定义构建流程。
@ -141,7 +139,6 @@ output = activation(input)
# build activation: Tanh
# call Tanh.forward
print(output)
# tensor([0.0159, 0.0815])
```
```{note}
@ -262,7 +259,6 @@ input = torch.randn(2)
output = model(input)
# call RReLU.forward
print(output)
# tensor([-1.5774, -0.5850])
```
### 调用兄弟节点的模块
@ -289,7 +285,6 @@ model = MODELS.build(cfg=dict(type='mmalpha.LogSoftmax'))
output = model(input)
# call LogSoftmax.forward
print(output)
# tensor([-1.5774, -0.5850])
```
调用兄弟节点的模块需要在 `type` 中指定 `scope` 前缀，所以上面的配置需要加前缀 `mmalpha`。
@ -303,5 +298,4 @@ model = MODELS.build(cfg=dict(type='LogSoftmax', _scope_='mmalpha'))
output = model(input)
# call LogSoftmax.forward
print(output)
# tensor([-1.5774, -0.5850])
```