Pytorch学习08——CNN卷积神经网络

完整代码

import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision     # 数据库模块
import os
import matplotlib.pyplot as plt
from matplotlib import cm
import numpy as np

torch.manual_seed(1)    # reproducible

# Hyper Parameters
EPOCH = 1               # train the training data n times, to save time, we just train 1 epoch
BATCH_SIZE = 50
LR = 0.001              # learning rate
DOWNLOAD_MNIST = False

# Mnist digits dataset
if not(os.path.exists('./mnist/')) or not os.listdir('./mnist/'):
    # not mnist dir or mnist is empyt dir
    DOWNLOAD_MNIST = True

train_data = torchvision.datasets.MNIST(
    root='./mnist/',
    train=True,                                     # this is training data
    transform=torchvision.transforms.ToTensor(),    # Converts a PIL.Image or numpy.ndarray to
                                                    # torch.FloatTensor of shape (C x H x W) and normalize in the range [0.0, 1.0]
    download=DOWNLOAD_MNIST,
)

# Data Loader for easy mini-batch return in training, the image batch shape will be (50, 1, 28, 28)
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)

# pick 2000 samples to speed up testing
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)
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]

# CNN模型 卷积-> 激烈函数 ->池化
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, x

cnn = CNN()

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

for epoch in range(EPOCH):
    for step, (b_x, b_y) in enumerate(train_loader):
        output = cnn(b_x)[0]  # 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

        if step % 50 == 0:
            test_output, last_layer = cnn(test_x)
            pred_y = torch.max(test_output, 1)[1].data.numpy()
            accuracy = float((pred_y == test_y.data.numpy()).astype(int).sum()) / float(test_y.size(0))
            print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy(), '| test accuracy: %.2f' % accuracy)

        plt.ioff()

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')

显示结果：

Epoch:  0 | train loss: 2.3125 | test accuracy: 0.18
Epoch:  0 | train loss: 0.4850 | test accuracy: 0.85
Epoch:  0 | train loss: 0.3738 | test accuracy: 0.90
Epoch:  0 | train loss: 0.3810 | test accuracy: 0.90
Epoch:  0 | train loss: 0.2345 | test accuracy: 0.93
Epoch:  0 | train loss: 0.1631 | test accuracy: 0.93
Epoch:  0 | train loss: 0.0555 | test accuracy: 0.95
Epoch:  0 | train loss: 0.1947 | test accuracy: 0.95
Epoch:  0 | train loss: 0.0674 | test accuracy: 0.96
Epoch:  0 | train loss: 0.0985 | test accuracy: 0.97
Epoch:  0 | train loss: 0.0847 | test accuracy: 0.97
Epoch:  0 | train loss: 0.0597 | test accuracy: 0.96
Epoch:  0 | train loss: 0.0408 | test accuracy: 0.96
Epoch:  0 | train loss: 0.0896 | test accuracy: 0.97
Epoch:  0 | train loss: 0.0192 | test accuracy: 0.96
Epoch:  0 | train loss: 0.0906 | test accuracy: 0.97
Epoch:  0 | train loss: 0.2287 | test accuracy: 0.96
Epoch:  0 | train loss: 0.0407 | test accuracy: 0.97
Epoch:  0 | train loss: 0.0432 | test accuracy: 0.97
Epoch:  0 | train loss: 0.0825 | test accuracy: 0.98
Epoch:  0 | train loss: 0.0121 | test accuracy: 0.97
Epoch:  0 | train loss: 0.0838 | test accuracy: 0.98
Epoch:  0 | train loss: 0.0261 | test accuracy: 0.98
Epoch:  0 | train loss: 0.0597 | test accuracy: 0.98