ReLU之参数 inplace=True

13 篇文章 0 订阅
10 篇文章 0 订阅

在下采样的过程中,我们常常用ReLU(inplace=True),具体的含义:

import torch
from torch import nn as nn
m = nn.ReLU(inplace=True)
input = torch.randn(10)
print(input)
output = m(input)
print(output)
print(input)
tensor([-0.0652,  0.0622,  0.0466, -0.0300, -0.6344, -0.9284, -1.2392,  1.7463,
         0.7938, -0.8787])
tensor([0.0000, 0.0622, 0.0466, 0.0000, 0.0000, 0.0000, 0.0000, 1.7463, 0.7938,
        0.0000])
tensor([0.0000, 0.0622, 0.0466, 0.0000, 0.0000, 0.0000, 0.0000, 1.7463, 0.7938,
        0.0000])

当inplace=True的时候,会改变输入数据;当inplace=False的时候,不会改变输入数据


我们都知道激活函数:ReLU()将小于0的值置为0,大于0 的保存下来了。

描述这段代码 class VGGTest(nn.Module): def __init__(self, pretrained=True, numClasses=10): super(VGGTest, self).__init__() # conv1 1/2 self.conv1_1 = nn.Conv2d(3, 64, kernel_size=3, padding=1) self.relu1_1 = nn.ReLU(inplace=True) self.conv1_2 = nn.Conv2d(64, 64, kernel_size=3, padding=1) self.relu1_2 = nn.ReLU(inplace=True) self.pool1 = nn.MaxPool2d(kernel_size=2, stride=2) # conv2 1/4 self.conv2_1 = nn.Conv2d(64, 128, kernel_size=3, padding=1) self.relu2_1 = nn.ReLU(inplace=True) self.conv2_2 = nn.Conv2d(128, 128, kernel_size=3, padding=1) self.relu2_2 = nn.ReLU(inplace=True) self.pool2 = nn.MaxPool2d(kernel_size=2, stride=2) # conv3 1/8 self.conv3_1 = nn.Conv2d(128, 256, kernel_size=3, padding=1) self.relu3_1 = nn.ReLU(inplace=True) self.conv3_2 = nn.Conv2d(256, 256, kernel_size=3, padding=1) self.relu3_2 = nn.ReLU(inplace=True) self.conv3_3 = nn.Conv2d(256, 256, kernel_size=3, padding=1) self.relu3_3 = nn.ReLU(inplace=True) self.pool3 = nn.MaxPool2d(kernel_size=2, stride=2) # conv4 1/16 self.conv4_1 = nn.Conv2d(256, 512, kernel_size=3, padding=1) self.relu4_1 = nn.ReLU(inplace=True) self.conv4_2 = nn.Conv2d(512, 512, kernel_size=3, padding=1) self.relu4_2 = nn.ReLU(inplace=True) self.conv4_3 = nn.Conv2d(512, 512, kernel_size=3, padding=1) self.relu4_3 = nn.ReLU(inplace=True) self.pool4 = nn.MaxPool2d(kernel_size=2, stride=2) # conv5 1/32 self.conv5_1 = nn.Conv2d(512, 512, kernel_size=3, padding=1) self.relu5_1 = nn.ReLU(inplace=True) self.conv5_2 = nn.Conv2d(512, 512, kernel_size=3, padding=1) self.relu5_2 = nn.ReLU(inplace=True) self.conv5_3 = nn.Conv2d(512, 512, kernel_size=3, padding=1) self.relu5_3 = nn.ReLU(inplace=True) self.pool5 = nn.MaxPool2d(kernel_size=2, stride=2)
05-24
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值