pytorch 学习（六） CNN搭建

以mnist为数据集：若原来没有数据集，把DOWNLOAD_MNIST=True。

#coding=utf-8
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
from torch.autograd import Variable

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 = False  # 如果你已经下载好了mnist数据就写上 Fasle

# 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
test_x = Variable(torch.unsqueeze(test_data.test_data, dim=1),volatile = True).type(torch.FloatTensor)[:2000]/255.   # shape from (2000, 28, 28) to (2000, 1, 28, 28), value in range(0,1)
#print test_x
test_y = test_data.test_labels[:2000]
#print 'test_y:',test_y

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)   x.size(0) 是x的行数 。  -1就是自适应大小
        output = self.out(x)
        return output

cnn = CNN()
print cnn  # net architecture

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):
    for step, (x,y) in enumerate(train_loader):   # 分配 batch data, normalize x when iterate train_loader
        b_x = Variable(x)   #版本老，所以tensor和Variable还没合并
        b_y = Variable(y)
        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

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


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')

结果：

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)
)
('Epoch: ', 0, '| train loss: 2.3145', '| test accuracy: 0.10')
('Epoch: ', 0, '| train loss: 0.5546', '| test accuracy: 0.83')
('Epoch: ', 0, '| train loss: 0.5857', '| test accuracy: 0.89')
('Epoch: ', 0, '| train loss: 0.1874', '| test accuracy: 0.92')
('Epoch: ', 0, '| train loss: 0.0600', '| test accuracy: 0.94')
('Epoch: ', 0, '| train loss: 0.1769', '| test accuracy: 0.95')
('Epoch: ', 0, '| train loss: 0.0996', '| test accuracy: 0.93')
('Epoch: ', 0, '| train loss: 0.2194', '| test accuracy: 0.95')
('Epoch: ', 0, '| train loss: 0.0381', '| test accuracy: 0.96')
('Epoch: ', 0, '| train loss: 0.0545', '| test accuracy: 0.96')
('Epoch: ', 0, '| train loss: 0.0266', '| test accuracy: 0.96')
('Epoch: ', 0, '| train loss: 0.0898', '| test accuracy: 0.96')
('Epoch: ', 0, '| train loss: 0.0973', '| test accuracy: 0.97')
('Epoch: ', 0, '| train loss: 0.3162', '| test accuracy: 0.97')
('Epoch: ', 0, '| train loss: 0.0421', '| test accuracy: 0.97')
('Epoch: ', 0, '| train loss: 0.1074', '| test accuracy: 0.96')
('Epoch: ', 0, '| train loss: 0.0654', '| test accuracy: 0.97')
('Epoch: ', 0, '| train loss: 0.1057', '| test accuracy: 0.97')
('Epoch: ', 0, '| train loss: 0.1333', '| test accuracy: 0.97')
('Epoch: ', 0, '| train loss: 0.0418', '| test accuracy: 0.98')
('Epoch: ', 0, '| train loss: 0.0289', '| test accuracy: 0.97')
('Epoch: ', 0, '| train loss: 0.0140', '| test accuracy: 0.98')
('Epoch: ', 0, '| train loss: 0.0429', '| test accuracy: 0.98')
('Epoch: ', 0, '| train loss: 0.0085', '| test accuracy: 0.98')
(array([7, 2, 1, 0, 4, 1, 4, 9, 5, 9]), 'prediction number')
(array([7, 2, 1, 0, 4, 1, 4, 9, 5, 9]), 'real number')