Villa974的博客

一个块：Inception 1x1卷积最主要的工作：改变通道数，减小复杂度 Inception的实现 class InceptionA(nn.Module): def __init__(self.in_channels): super(InceptionA, self).__init__() self.branch1x1 = nn.Conv2d(in_channels, 16, kernel_size=1) self.branch5X5_1 = nn.Con...

1 二维卷积神经网络 import torch in_channels, out_channels=5, 10 witdh, height ![在这里插入图片描述](https://img-blog.csdnimg.cn/20210510170655629.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L1ZpbGxhOTc0,size_16,co

具体流程： 0 Import Package import torch from torchvision import transforms #针对图像对数据进行原始处理 from torchvision import datasets from torch.utils.data import DatatLoader import torch.nn.functional as F #激活函数 import torch.optim as optim 1 Prepare Dataset batch

利用pytorch实现反向传播，简单代码 # -*- coding: utf-8 -*- """ Spyder Editor This is a temporary script file. """ import torch x_data = [1.0, 2.0, 3.0] y_data = [2.0, 4.0, 6.0] w = torch.Tensor([1.0]) w.requires_grad = True def forward(x): return x * w def los