pytorch学习笔记，cnn与gpu加速

cnn代码，警告见gpu版修正，版本问题。

import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision      # 数据库模块
import matplotlib.pyplot as plt

import logging

logger = logging.Logger(None)

torch.manual_seed(1)    # reproducible

# Hyper Parameters
EPOCH = 1           # 训练整批数据多少次, 为了节约时间, 我们只训练一次
BATCH_SIZE = 50
LR = 0.001          # 学习率
DOWNLOAD_MNIST = True  # 如果你已经下载好了mnist数据就写上 False


# Mnist 手写数字
train_data = torchvision.datasets.MNIST(
    root=\'./mnist/\',    # 保存或者提取位置
    train=True,  # this is training data
    transform=torchvision.transforms.ToTensor(),    # 转换 PIL.Image or numpy.ndarray 成
                                                    # torch.FloatTensor (C x H x W), 训练的时候 normalize 成 [0.0, 1.0] 区间
    download=DOWNLOAD_MNIST,          # 没下载就下载, 下载了就不用再下了
)
test_data = torchvision.datasets.MNIST(root=\'./mnist/\', train=False)

# 批训练 50samples, 1 channel, 28x28 (50, 1, 28, 28)
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)

# 为了节约时间, 我们测试时只测试前2000个，警告就是这里产生的，新版本换名字了。见gpu版
test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[:2000]/255.   # shape from (2000, 28, 28) to (2000, 1, 28, 28), value in range(0,1)
test_y = test_data.test_labels[:2000]

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Sequential(  # input shape (1, 28, 28)
            nn.Conv2d(
                in_channels=1,      # input height
                out_channels=16,    # n_filters
                kernel_size=5,      # filter size
                stride=1,           # filter movement/step
                padding=2,      # 如果想要 con2d 出来的图片长宽没有变化, padding=(kernel_size-1)/2 当 stride=1
            ),      # output shape (16, 28, 28)
            nn.ReLU(),    # activation
            nn.MaxPool2d(kernel_size=2),    # 在 2x2 空间里向下采样, output shape (16, 14, 14)
        )
        self.conv2 = nn.Sequential(  # input shape (16, 14, 14)
            nn.Conv2d(16, 32, 5, 1, 2),  # output shape (32, 14, 14)
            nn.ReLU(),  # activation
            nn.MaxPool2d(2),  # output shape (32, 7, 7)
        )
        self.out = nn.Linear(32 * 7 * 7, 10)   # fully connected layer, output 10 classes

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0), -1)   # 展平多维的卷积图成 (batch_size, 32 * 7 * 7)
        output = self.out(x)
        return output

cnn = CNN()
print(cnn)  # net architecture
\"\"\"
CNN (
  (conv1): Sequential (
    (0): Conv2d(1, 16, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (1): ReLU ()
    (2): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
  )
  (conv2): Sequential (
    (0): Conv2d(16, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (1): ReLU ()
    (2): MaxPool2d (size=(2, 2), stride=(2, 2), dilation=(1, 1))
  )
  (out): Linear (1568 -> 10)
)
\"\"\"

optimizer = torch.optim.Adam(cnn.parameters(), lr=LR)   # optimize all cnn parameters
loss_func = nn.CrossEntropyLoss()   # the target label is not one-hotted

# training and testing
for epoch in range(EPOCH):
    num_correct = 0
    for step, (b_x, b_y) in enumerate(train_loader):   # 分配 batch data, normalize x when iterate train_loader
        output = cnn(b_x)               # cnn output
        loss = loss_func(output, b_y)   # cross entropy loss
        optimizer.zero_grad()           # clear gradients for this training step
        loss.backward()                 # backpropagation, compute gradients
        optimizer.step()                # apply gradients
        pred = output.argmax(dim=1)
        num_correct += torch.eq(pred, b_y).sum().float().item()
    print(\"Train Epoch: {}\\t Loss: {:.6f}\\t Acc: {:.6f}\".format(epoch,loss,num_correct/len(train_loader.dataset)))

\"\"\"
...
Epoch:  0 | train loss: 0.0306 | test accuracy: 0.97
Epoch:  0 | train loss: 0.0147 | test accuracy: 0.98
Epoch:  0 | train loss: 0.0427 | test accuracy: 0.98
Epoch:  0 | train loss: 0.0078 | test accuracy: 0.98
\"\"\"

test_output = cnn(test_x[:10])
pred_y = torch.max(test_output, 1)[1].data.numpy().squeeze()
print(pred_y, \'prediction number\')
print(test_y[:10].numpy(), \'real number\')

\"\"\"
[7 2 1 0 4 1 4 9 5 9] prediction number
[7 2 1 0 4 1 4 9 5 9] real number
\"\"\"

# 测试集测试
test_output = cnn(test_x)
loss = loss_func(test_output, test_y)
pred_y = test_output.argmax(dim=1)
c = torch.eq(pred_y, test_y).sum().float().item()
print(\"Loss: {:.6f}\\t Acc: {:.6f}\".format(loss,c/len(test_output)))

gpu加速上面代码，警告没了

import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision

# torch.manual_seed(1)

EPOCH = 1
BATCH_SIZE = 50
LR = 0.001
DOWNLOAD_MNIST = False

train_data = torchvision.datasets.MNIST(root=\'./mnist/\', train=True, transform=torchvision.transforms.ToTensor(), download=DOWNLOAD_MNIST,)
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)

test_data = torchvision.datasets.MNIST(root=\'./mnist/\', train=False)

# !!!!!!!! Change in here !!!!!!!!! #
test_x = torch.unsqueeze(test_data.data, dim=1).type(torch.FloatTensor)[:2000].cuda()/255.   # Tensor on GPU
test_y = test_data.targets[:2000].cuda()


class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Sequential(nn.Conv2d(in_channels=1, out_channels=16, kernel_size=5, stride=1, padding=2,),
                                   nn.ReLU(), nn.MaxPool2d(kernel_size=2),)
        self.conv2 = nn.Sequential(nn.Conv2d(16, 32, 5, 1, 2), nn.ReLU(), nn.MaxPool2d(2),)
        self.out = nn.Linear(32 * 7 * 7, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0), -1)
        output = self.out(x)
        return output

cnn = CNN()

# !!!!!!!! Change in here !!!!!!!!! #
cnn.cuda()      # Moves all model parameters and buffers to the GPU.

optimizer = torch.optim.Adam(cnn.parameters(), lr=LR)
loss_func = nn.CrossEntropyLoss()

for epoch in range(EPOCH):
    for step, (x, y) in enumerate(train_loader):

        # !!!!!!!! Change in here !!!!!!!!! #
        b_x = x.cuda()    # Tensor on GPU
        b_y = y.cuda()    # Tensor on GPU

        output = cnn(b_x)
        loss = loss_func(output, b_y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if step % 50 == 0:
            test_output = cnn(test_x)

            # !!!!!!!! Change in here !!!!!!!!! #
            pred_y = torch.max(test_output, 1)[1].cuda().data  # move the computation in GPU

            accuracy = torch.sum(pred_y == test_y).type(torch.FloatTensor) / test_y.size(0)
            print(\'Epoch: \', epoch, \'| train loss: %.4f\' % loss.data.cpu().numpy(), \'| test accuracy: %.2f\' % accuracy)


test_output = cnn(test_x[:10])

# !!!!!!!! Change in here !!!!!!!!! #
pred_y = torch.max(test_output, 1)[1].cuda().data # move the computation in GPU

print(pred_y, \'prediction number\')
print(test_y[:10], \'real number\')

# 测试集
test_output = cnn(test_x)
loss = loss_func(test_output, test_y)
pred_y = torch.max(test_output, 1)[1].cuda().data
accuracy = torch.sum(pred_y == test_y).type(torch.FloatTensor) / test_y.size(0)
print(\"Loss: {:.6f}\\t Acc: {:.6f}\".format(loss,accuracy))