Skip to content
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

Jump to bottom

[Fix] delete the error comment #514

Merged
merged 1 commit into from
Oct 8, 2022
Merged

[Fix] delete the error comment #514

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.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
6 changes: 0 additions & 6 deletions docs/zh_cn/tutorials/registry.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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。
Expand All @@ -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。
Expand Down Expand Up @@ -141,7 +139,6 @@ output = activation(input)
# build activation: Tanh
# call Tanh.forward
print(output)
# tensor([0.0159, 0.0815])
```

```{note}
Expand Down Expand Up @@ -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
Expand All @@ -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`。
Expand All @@ -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])
```