CS_ALearn/ailearning
1
0
Fork 0
mirror of https://github.com/apachecn/ailearning.git synced 2026-04-23 18:13:05 +08:00
Code Issues Projects Releases Wiki Activity

2020-10-19 21:48:57

Browse Source
This commit is contained in:
wizardforcel
2020-10-19 21:48:57 +08:00
parent 74f7d35aeb
commit 045dee5888
20 changed files with 73 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/pytorch/11.md
View File

@@ -6,7 +6,7 @@ Torch 中提供了很多方便的途径, 同样是神经网络, 能快则快,
我们先看看之前写神经网络时用到的步骤. 我们用 net1  代表这种方式搭建的神经网络.
```
```py
class Net(torch.nn.Module):
def __init__(self, n_feature, n_hidden, n_output):
super(Net, self).__init__()
@@ -23,7 +23,7 @@ net1 = Net(1, 10, 1) # 这是我们用这种方式搭建的 net1
我们用 class 继承了一个 torch 中的神经网络结构, 然后对其进行了修改, 不过还有更快的一招, 用一句话就概括了上面所有的内容!
```
```py
net2 = torch.nn.Sequential(
torch.nn.Linear(1, 10),
torch.nn.ReLU(),
@@ -33,7 +33,7 @@ net2 = torch.nn.Sequential(
我们再对比一下两者的结构:
```
```py
print(net1)
"""
Net (