mofanpy-Pytorch神经网络学习笔记（三）：高级神经网络——CNN

高级神经网络—— CNN

这篇文章主要关注代码实现CNN，具体的原理介绍见文章《mofanpy-机器学习原理学习笔记》

mofanpy本节完整代码：https://github.com/MorvanZhou/PyTorch-Tutorial/blob/master/tutorial-contents/401_CNN.py

代码实现功能：让计算机识别手写的数字数据并正确进行分类1.2.3…

（1）MNIST手写数据

# library
# standard library
import os

# third-party library
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

# 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 epoch
BATCH_SIZE = 50
LR = 0.001              # learning rate
DOWNLOAD_MNIST = False   # 如果你已经下载好了mnist数据就写上 False


# 训练数据：Mnist 手写数字
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/',   # 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), 原先值是（0，255），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
)

# plot one example
print(train_data.train_data.size())                 # (60000, 28, 28)
print(train_data.train_labels.size())               # (60000)
plt.imshow(train_data.train_data[0].numpy(), cmap='gray')
plt.title('%i' % train_data.train_labels[0])
plt.show()

torch.Size([60000, 28, 28])
torch.Size([60000])

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

# 测试数据
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)

# 为了节约时间, 我们测试时只测试前2000个
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]

（2）CNN模型

CNN 整体流程是：
卷积(Conv2d) -> 激励函数(ReLU) -> 池化, 向下采样 (MaxPooling) -> 再来一遍 -> 展平多维的卷积成的特征图 -> 接入全连接层 (Linear) -> 输出

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Sequential(         # input shape (1, 28, 28)
            nn.Conv2d(                      # Conv2d卷积过滤器
                in_channels=1,              # input height  因为图片是黑白的
                out_channels=16,            # n_filters 有多少个filter就提取出了多少种特征信息
                                            # 可以把他想象为高度为16的一张图片
                kernel_size=5,              # filter size
                stride=1,                   # filter movement/step  移动步长
                padding=2,                  # 在原图上加上2个像素的边框，
                                            # 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(0-9一共10类)

    def forward(self, x):
        x = self.conv1(x)                    #原先是(batch_size, 32， 7， 7)
        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    # return x for visualization


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(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (conv2): Sequential(
    (0): Conv2d(16, 32, kernel_size=(5, 5), stride=(1, 1), padding=(2, 2))
    (1): ReLU()
    (2): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (out): Linear(in_features=1568, out_features=10, bias=True)
)

（3）训练

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

plt.ion()
# training and testing
for epoch in range(EPOCH):
    for step, (b_x, b_y) in enumerate(train_loader):   # gives batch data, normalize x when iterate 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

        #打印一下训练效果
        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)
            if HAS_SK:
                # Visualization of trained flatten layer (T-SNE)
                tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000)
                plot_only = 500
                low_dim_embs = tsne.fit_transform(last_layer.data.numpy()[:plot_only, :])
                labels = test_y.numpy()[:plot_only]
                plot_with_labels(low_dim_embs, labels)
plt.ioff()

Epoch:  0 | train loss: 2.2979 | test accuracy: 0.13   

… …

Epoch:  0 | train loss: 0.0396 | test accuracy: 0.98

最后我们再来取10个数据, 看看预测的值到底对不对:

# print 10 predictions from test data
test_output, _ = cnn(test_x[:10])
pred_y = torch.max(test_output, 1)[1].data.numpy()
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

（4）可视化

# following function (plot_with_labels) is for visualization, can be ignored if not interested
from matplotlib import cm
try: from sklearn.manifold import TSNE; HAS_SK = True
except: HAS_SK = False; print('Please install sklearn for layer visualization')
def plot_with_labels(lowDWeights, labels):
    plt.cla()
    X, Y = lowDWeights[:, 0], lowDWeights[:, 1]
    for x, y, s in zip(X, Y, labels):
        c = cm.rainbow(int(255 * s / 9)); plt.text(x, y, s, backgroundcolor=c, fontsize=9)
    plt.xlim(X.min(), X.max()); plt.ylim(Y.min(), Y.max()); plt.title('Visualize last layer'); plt.show(); plt.pause(0.01)