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)