学习笔记：动手学深度学习 18 Dropout

最新推荐文章于 2024-01-17 11:01:15 发布

进击的番茄~

最新推荐文章于 2024-01-17 11:01:15 发布

阅读量423

点赞数

文章标签：深度学习 python pytorch

本文链接：https://blog.csdn.net/weixin_43137437/article/details/121222858

版权

从0开始实现

Python 3.8.8 (default, Apr 13 2021, 15:08:03) [MSC v.1916 64 bit (AMD64)]
Type 'copyright', 'credits' or 'license' for more information
IPython 7.22.0 -- An enhanced Interactive Python. Type '?' for help.
PyDev console: using IPython 7.22.0
Python 3.8.8 (default, Apr 13 2021, 15:08:03) [MSC v.1916 64 bit (AMD64)] on win32
import torch
from torch import nn
from d2l import torch as d2l
Backend Qt5Agg is interactive backend. Turning interactive mode on.
def dropout_layer(X, dropout):
    assert 0 <= dropout <= 1
    # 在本情况中，所有元素都被丢弃。
    if dropout == 1:
        return torch.zeros_like(X)
    # 在本情况中，所有元素都被保留。
    if dropout == 0:
        return X
    mask = (torch.randn(X.shape)> dropout).float()
    return mask * X / (1.0 - dropout)
X= torch.arange(16, dtype = torch.float32).reshape((2, 8))
print(X)
print(dropout_layer(X, 0.))
print(dropout_layer(X, 0.5))
prin