pytorch突击|pytorch-13-激活函数&GPU加速&测试深度学习|pytorch

【pytorch突击|pytorch-13-激活函数&GPU加速&测试】
激活函数与GPU加速&测试

1、激活函数
2、GPU加速

1、激活函数

文章图片

文章图片

很少用的激活函数：Relu改进版

文章图片

文章图片

2、GPU加速

文章图片

代码如下

importtorch importtorch.nn as nn importtorch.nn.functional as F importtorch.optim as optim fromtorchvision import datasets, transformsbatch_size=200 learning_rate=0.01 epochs=10train_loader = torch.utils.data.DataLoader( datasets.MNIST('./data', train=True, download=True, transform=transforms.Compose([ transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,)) ])), batch_size=batch_size, shuffle=True) test_loader = torch.utils.data.DataLoader( datasets.MNIST('./data', train=False, transform=transforms.Compose([ transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,)) ])), batch_size=batch_size, shuffle=True)class MLP(nn.Module):def __init__(self): super(MLP, self).__init__()self.model = nn.Sequential( nn.Linear(784, 200), nn.LeakyReLU(inplace=True), nn.Linear(200, 200), nn.LeakyReLU(inplace=True), nn.Linear(200, 10), nn.LeakyReLU(inplace=True), )def forward(self, x): x = self.model(x)return xdevice = torch.device('cuda:0') net = MLP().to(device) optimizer = optim.SGD(net.parameters(), lr=learning_rate) criteon = nn.CrossEntropyLoss().to(device)for epoch in range(epochs):for batch_idx, (data, target) in enumerate(train_loader): data = https://www.it610.com/article/data.view(-1, 28*28) #data, target = data.to(device), target.cuda() data, target = data.to(device), target.to(device)logits = net(data) loss = criteon(logits, target)optimizer.zero_grad() loss.backward() # print(w1.grad.norm(), w2.grad.norm()) optimizer.step()if batch_idx % 100 == 0: print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format( epoch, batch_idx * len(data), len(train_loader.dataset), 100. * batch_idx / len(train_loader), loss.item()))test_loss = 0 correct = 0 for data, target in test_loader: data = https://www.it610.com/article/data.view(-1, 28 * 28) data, target = data.to(device), target.cuda() logits = net(data) test_loss += criteon(logits, target).item()pred = logits.data.max(1)[1] correct += pred.eq(target.data).sum()test_loss /= len(test_loader.dataset) print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format( test_loss, correct, len(test_loader.dataset), 100. * correct / len(test_loader.dataset)))