深圳网站建设网站制作昆明排名优化

        ResNet (Residual Network) 是由微软研究院的何凯明等人在2015年提出的一种深度卷积神经网络结构。ResNet的设计目标是解决深层网络训练中的梯度消失和梯度爆炸问题，进一步提高网络的表现。下面是一个ResNet模型实现，使用PyTorch框架来展示如何实现基本的ResNet结构。这个例子包括了一个基本的残差块（Residual Block）以及ResNet-18的实现，代码结构分为model.py（模型文件）和train.py（训练文件）。

model.py 

      首先，我们导入所需要的包 

import torch
from torch import nn
from torch.nn import functional as F

        然后，定义Resnet Block（ResBlk）类。

class ResBlk(nn.Module):def __init__(self):super(ResBlk, self).__init__()self.conv1 = nn.Conv2d(ch_in, ch_out, kernel_size=3, stride=1, padding=1)self.bn1 = nn.BatchNorm2d(ch_out)self.conv2 = nn.Conv2d(ch_out, ch_out, kernel_size=3, stride=1, padding=1)self.bn2 = nn.BatchNorm2d(ch_out)self.extra = nn.Sequential()if ch_out != ch_inself.extra = nn.Sequential(nn.Conv2d(ch_in, ch_out, kernel_size=3, stride=1)nn.BatchNorm2d(ch_out))def forward(self, x):out = F.relu(self.bn1(self.conv1(x)))out = F.relu(self.bn2(self.conv2(x)))out = self.extra(x) + outreturn out

        最后，根据ResNet18的结构对ResNet Block进行堆叠。

class Resnet18(nn.Module):def __init__(self):super(Resnet18, self).__init__()self.conv1 = nn.Sequential(nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1)nn.BatchNorm2d(64))self.blk1 = ResBlk(64, 128)self.blk2 = ResBlk(128, 256)self.blk3 = ResBlk(256, 512)self.blk4 = ResBlk(512, 1024)self.outlayer = nn.Linear(512, 10)def forward(self, x):x = F.relu(self.conv1(x))x = self.blk1(x)x = self.blk2(x)x = self.blk3(x)x = self.blk4(x)# print('after conv1:', x.shape)x = F.adaptive_avg_pool2d(x, [1,1])x = x.view(x.size(0), -1)x = self.outlayer(x)return x

        其中，在网络结构搭建过程中，需要用到中间阶段的图片参数，用下述测试过程求得。

def main():tmp = torch.randn(2, 3, 32, 32)out = blk(tmp)print('block', out.shape)x = torch.randn(2, 3, 32, 32)model = ResNet18()out = model(x)print('resnet:', out.shape)

train.py

        首先，导入所需要的包

import torch
from torchvision import datasets
from torchvision import transforms
from torch import nn, optimizer

        然后，定义main()函数

def main():batchsz = 32cifar_train = datasets.CIFAR10('cifar', True, transform=transforms.Compose([transforms.Resize((32, 32)),transforms.ToTensor()]), download=True)cifar_train = DataLoader(cifar_train, batch_size=batchsz, shuffle=True)cifar_test = datasets.CIFAR10('cifar', False, transform=transforms.Compose([transforms.Resize((32, 32)),transforms.ToTensor()]), download=True)cifar_test = DataLoader(cifar_test, batch_size=batchsz, shuffle=True)x, label = iter(cifar_train).next()print('x:', x.shape, 'label:', label.shape)device = torch.device('cuda')model = ResNet18().to(device)criteon = nn.CrossEntropyLoss()optimizer = optim.Adam(model.parameters(), lr=1e-3)print(model)for epoch in range(100):for batchidx, (x, label) in enumerate(cifar_train):x, label = x.to(device), label.to(device)logits = model(x)loss = criteon(logitsm label)optimizer.zero_grad()loss.backward()optimizer.step()print(loss.item())with torch.no_grad():total_correct = 0total_num = 0for x, label in cifar_test:x, label = x.to(device), label.to(device)logits = model(x)pred = logits.argmax(dim=1)total_correct += torch.eq(pred, label).floot().sum().item()total_num += x.size(0)acc = total_correct / total_numprint(epoch, acc)