PyTorch 深度学习实践 GPU版本B站刘二大人第11讲卷积神经网络(高级篇)GPU版本

第11讲卷积神经网络(高级篇) GPU版本源代码

原理是基于B站刘二大人：传送门PyTorch深度学习实践——卷积神经网络(高级篇)

这篇基于博主错错莫：传送门深度学习实践第11讲博文
仅在他的基础上加入了GPU模块，详细原理解释请看他的博文

1、Inception Moudel

import torch
import torch.nn as nn
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim# prepare datasetbatch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])  # 归一化,均值和方差train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)# design model using class
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.Conv2d(in_channels, 16, kernel_size=1)self.branch5x5_2 = nn.Conv2d(16, 24, kernel_size=5, padding=2)self.branch3x3_1 = nn.Conv2d(in_channels, 16, kernel_size=1)self.branch3x3_2 = nn.Conv2d(16, 24, kernel_size=3, padding=1)self.branch3x3_3 = nn.Conv2d(24, 24, kernel_size=3, padding=1)self.branch_pool = nn.Conv2d(in_channels, 24, kernel_size=1)def forward(self, x):branch1x1 = self.branch1x1(x)branch5x5 = self.branch5x5_1(x)branch5x5 = self.branch5x5_2(branch5x5)branch3x3 = self.branch3x3_1(x)branch3x3 = self.branch3x3_2(branch3x3)branch3x3 = self.branch3x3_3(branch3x3)branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)branch_pool = self.branch_pool(branch_pool)outputs = [branch1x1, branch5x5, branch3x3, branch_pool]return torch.cat(outputs, dim=1)  # b,c,w,h  c对应的是dim=1class Net(nn.Module):def __init__(self):super(Net, self).__init__()self.conv1 = nn.Conv2d(1, 10, kernel_size=5)self.conv2 = nn.Conv2d(88, 20, kernel_size=5)  # 88 = 24x3 + 16self.incep1 = InceptionA(in_channels=10)  # 与conv1 中的10对应self.incep2 = InceptionA(in_channels=20)  # 与conv2 中的20对应self.mp = nn.MaxPool2d(2)self.fc = nn.Linear(1408, 10)def forward(self, x):in_size = x.size(0)x = F.relu(self.mp(self.conv1(x)))  # 卷积和池化的先后关系不影响x = self.incep1(x)x = F.relu(self.mp(self.conv2(x)))x = self.incep2(x)x = x.view(in_size, -1)x = self.fc(x)return xmodel = Net()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)
# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)# training cycle forward, backward, updatedef train(epoch):running_loss = 0.0for batch_idx, data in enumerate(train_loader, 0):inputs, target = datainputs, target = inputs.to(device), target.to(device)optimizer.zero_grad()outputs = model(inputs)loss = criterion(outputs, target)loss.backward()optimizer.step()running_loss += loss.item()if batch_idx % 300 == 299:print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))running_loss = 0.0def test():correct = 0total = 0with torch.no_grad():for data in test_loader:images, labels = datalabels, images = labels.to(device), images.to(device)outputs = model(images)_, predicted = torch.max(outputs.data, dim=1)total += labels.size(0)correct += (predicted == labels).sum().item()print('accuracy on test set: %d %% ' % (100 * correct / total))if __name__ == '__main__':for epoch in range(10):train(epoch)test()

2、ResidualBlock


import torch
import torch.nn as nn
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim# prepare datasetbatch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])  # 归一化,均值和方差train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)# design model using class
class ResidualBlock(nn.Module):def __init__(self, channels):super(ResidualBlock, self).__init__()self.channels = channelsself.conv1 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)self.conv2 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)def forward(self, x):y = F.relu(self.conv1(x))y = self.conv2(y)return F.relu(x + y)  # 先做y+x再做reluclass Net(nn.Module):def __init__(self):super(Net, self).__init__()self.conv1 = nn.Conv2d(1, 16, kernel_size=5)self.conv2 = nn.Conv2d(16, 32, kernel_size=5)self.rblock1 = ResidualBlock(16)self.rblock2 = ResidualBlock(32)self.mp = nn.MaxPool2d(2)self.fc = nn.Linear(512, 10)def forward(self, x):in_size = x.size(0)x = self.mp(F.relu(self.conv1(x)))x = self.rblock1(x)x = self.mp(F.relu(self.conv2(x)))x = self.rblock2(x)x = x.view(in_size, -1)x = self.fc(x)return xmodel = Net()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)
# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)# training cycle forward, backward, updatedef train(epoch):running_loss = 0.0for batch_idx, data in enumerate(train_loader, 0):inputs, target = datainputs, target = inputs.to(device), target.to(device)optimizer.zero_grad()outputs = model(inputs)loss = criterion(outputs, target)loss.backward()optimizer.step()running_loss += loss.item()if batch_idx % 300 == 299:print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))running_loss = 0.0def test():correct = 0total = 0with torch.no_grad():for data in test_loader:images, labels = dataimages, labels = images.to(device), labels.to(device)outputs = model(images)_, predicted = torch.max(outputs.data, dim=1)total += labels.size(0)correct += (predicted == labels).sum().item()print('accuracy on test set: %d %% ' % (100 * correct / total))if __name__ == '__main__':for epoch in range(10):train(epoch)test()

代码免积分下载：
https://download.csdn.net/download/air__Heaven/76859016
https://download.csdn.net/download/air__Heaven/76859016
再次感谢b站up刘二大人，和博主错错莫

PyTorch 深度学习实践 GPU版本B站刘二大人第11讲卷积神经网络(高级篇)GPU版本相关推荐

PyTorch深度学习实践（b站刘二大人）P6讲逻辑斯蒂回归 Logistic Regression
1.分类任务的数据集 ① The MNIST Dataset:handwritten digits Training set: 60,000 examples, Test set: 10,000 ex ...
Pytorch深度学习实践（b站刘二大人）P10讲 (CNN卷积神经网络基础篇)
1.全连接网络指的是网络里面用的都是线性层,如果一个网络全都由线性层串行连接起来,就叫做全连接网络在线性层里面输入和每一个输出值之间都存在权重,即每一个输入节点都要参与到下一层输出节点的计算上,这 ...
【Pytorch深度学习实践】B站up刘二大人课程笔记——目录与索引（已完结）
从有代码的课程开始讨论 [Pytorch深度学习实践]B站up刘二大人之LinearModel -代码理解与实现(1/9) [Pytorch深度学习实践]B站up刘二大人之 Gradient Desc ...
【Pytorch深度学习实践】B站up刘二大人之SoftmaxClassifier-代码理解与实现(8/9)
这是刘二大人系列课程笔记的倒数第二个博客了,介绍的是多分类器的原理和代码实现,下一个笔记就是basicCNN和advancedCNN了: 写在前面: 这节课的内容,主要是两个部分的修改: 一是数据集: ...
【Pytorch深度学习实践】B站up刘二大人之BasicCNN Advanced CNN -代码理解与实现(9/9)
这是刘二大人系列课程笔记的最后一个笔记了,介绍的是 BasicCNN 和 AdvancedCNN ,我做图像,所以后面的RNN我可能暂时不会花时间去了解了: 写在前面: 本节把基础个高级CNN放在一 ...
【Pytorch深度学习实践】B站up刘二大人之 Gradient Descend-代码理解与实现(2/9)
开篇几句题外话: 以往的代码,都是随便看看就过去了,没有这样较真过,以至于看了很久的深度学习和Python,都没有能够形成编程能力: 这次算是废寝忘食的深入进去了,踏实地把每一个代码都理解透,包括其中 ...
笔记|（b站）刘二大人：pytorch深度学习实践（代码详细笔记，适合零基础）
pytorch深度学习实践笔记中的代码是根据b站刘二大人的课程所做的笔记,代码每一行都有注释方便理解,可以配套刘二大人视频一同使用. 用PyTorch实现线性回归 # 1.算预测值 # 2.算los ...
【PyTorch深度学习实践 | 刘二大人】B站视频教程笔记
资料 [参考:<PyTorch深度学习实践>完结合集_哔哩哔哩_bilibili] [参考分类专栏:PyTorch 深度学习实践_错错莫的博客-CSDN博客] 全[参考分类专栏:PyT ...
PyTorch 深度学习实践第13讲
PyTorch 深度学习实践第13讲引言代码结果引言近期学习了B站刘二大人的PyTorch深度学习实践,传送门PyTorch 深度学习实践--循环神经网络(高级篇),感觉受益匪浅,发现网 ...

PyTorch 深度学习实践 GPU版本B站刘二大人第11讲卷积神经网络(高级篇)GPU版本

PyTorch 深度学习实践 GPU版本B站刘二大人第11讲卷积神经网络(高级篇)GPU版本相关推荐

最新文章

热门文章

PyTorch 深度学习实践 GPU版本B站 刘二大人第11讲卷积神经网络(高级篇)GPU版本

PyTorch 深度学习实践 GPU版本B站 刘二大人第11讲卷积神经网络(高级篇)GPU版本相关推荐

最新文章

热门文章

PyTorch 深度学习实践 GPU版本B站刘二大人第11讲卷积神经网络(高级篇)GPU版本

PyTorch 深度学习实践 GPU版本B站刘二大人第11讲卷积神经网络(高级篇)GPU版本相关推荐