莫烦pytorch学习笔记（八）——卷积神经网络（手写数字识别实现）

莫烦视频网址

这个代码实现了预测和可视化

 import os

 # third-party library
 import torch
 import torch.nn as nn
 import torch.utils.data as Data
 import torchvision
 import matplotlib.pyplot as plt

 # torch.manual_seed()    # reproducible

 # Hyper Parameters
 EPOCH =                # train the training data n times, to save time, we just train  epoch
 BATCH_SIZE =
 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(),    # 把数据压缩到0到1之间的numpy数据
                                                     # torch.FloatTensor of shape (C x H x W) and normalize in the range [0.0, 1.0]
     download=DOWNLOAD_MNIST,
 )

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

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

 # pick  samples to speed up testing
 test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)
 test_x = torch.unsqueeze(test_data.test_data, dim=).type(torch.FloatTensor)[:]/.   # shape from (, , ) to (, , , ), value in range(,)
 test_y = test_data.test_labels[:]

 class CNN(nn.Module):
     def __init__(self):
         super(CNN, self).__init__()
         self.conv1 = nn.Sequential(         # input shape (, , )
             nn.Conv2d(
                 in_channels=,              # input height
                 out_channels=,            # n_filters
                 kernel_size=,              # filter size
                 stride=,                   # filter movement/step
                 padding=,                  # if want same width and length of this image after Conv2d, padding=(kernel_size-)/ if stride=
             ),                              # output shape (, , )
             nn.ReLU(),                      # activation
             nn.MaxPool2d(kernel_size=),    # choose max value in 2x2 area, output shape (, , )
         )
         self.conv2 = nn.Sequential(         # input shape (, , )
             nn.Conv2d(, , , , ),     # output shape (, , )
             nn.ReLU(),                      # activation
             nn.MaxPool2d(),                # output shape (, , )
         )
         self.out = nn.Linear( *  * , )   # fully connected layer, output  classes

     def forward(self, x):
         x = self.conv1(x)
         x = self.conv2(x)
         x = x.view(x.size(), -)           # flatten the output of conv2 to (batch_size,  *  * )
         output = self.out(x)
         return output, x    # return x for visualization

 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

 # 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[:, ], lowDWeights[:, ]
     for x, y, s in zip(X, Y, labels):
         c = cm.rainbow(int( * s / )); plt.text(x, y, s, backgroundcolor=c, fontsize=)
     plt.xlim(X.min(), X.max()); plt.ylim(Y.min(), Y.max()); plt.title('Visualize last layer'); plt.show(); plt.pause(0.01)

 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)[]               # 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 %  == :
             test_output, last_layer = cnn(test_x)
             pred_y = torch.max(test_output, )[].data.numpy()
             accuracy = float((pred_y == test_y.data.numpy()).astype(int).sum()) / float(test_y.size())
             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=, n_components=, init='pca', n_iter=)
                 plot_only =
                 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()

 # print  predictions from test data
 test_output, _ = cnn(test_x[:])
 pred_y = torch.max(test_output, )[].data.numpy()
 print(pred_y, 'prediction number')
 print(test_y[:].numpy(), 'real number')

去掉可视化进行代码简化

 import os
 # third-party library
 import torch
 import torch.nn as nn
 import torch.utils.data as Data
 import torchvision
 import matplotlib.pyplot as plt

 EPOCH =                # train the training data n times, to save time, we just train  epoch
 BATCH_SIZE =
 LR = 0.001              # learning rate

 train_data = torchvision.datasets.MNIST(
     root='./mnist/',                                #下载后的存放目录
     train=True,                                     # this is training data
     transform=torchvision.transforms.ToTensor(),    # 把数据压缩到0到1之间的numpy数据，如果原始数据是rgb数据（-）则变为黑白数据，并使numpy数据变为tensor数据                                                 # torch.FloatTensor of shape (C x H x W) and normalize in the range [0.0, 1.0]
     download=True#不存在该数据就设置为True进行下载，存在则改为False
 )

 # plot one example
 print(train_data.train_data.size())                 # (, , )，六万图片
 print(train_data.train_labels.size())               # ()，六万标签
 plt.imshow(train_data.train_data[].numpy(), cmap='gray')#展现第一个训练数据图片
 plt.title('%i' % train_data.train_labels[])
 plt.show()

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

 # pick  samples to speed up testing
 test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)
 test_x = torch.unsqueeze(test_data.test_data, dim=).type(torch.FloatTensor)[:]/.   # shape from (, , ) to (, , , ), value in range(,)
 test_y = test_data.test_labels[:]

 class CNN(nn.Module):
     def __init__(self):
         super(CNN, self).__init__()
         self.conv1 = nn.Sequential(         # input shape (, , )，考虑batch是（batch，,,）
             nn.Conv2d(
                 in_channels=,              # input height
                 out_channels=,            # n_filters
                 kernel_size=,              # filter size
                 stride=,                   # filter movement/step
                 padding=,                  # if want same width and length of this image after Conv2d, padding=(kernel_size-)/ if stride=
             ),                              # output shape (, , )
             nn.ReLU(),                      # activation
             nn.MaxPool2d(kernel_size=),    # choose max value in 2x2 area, output shape (, , )
         )
         self.conv2 = nn.Sequential(         # input shape (, , )
             nn.Conv2d(, , , , ),     # output shape (, , )
             nn.ReLU(),                      # activation
             nn.MaxPool2d(),                # output shape (, , )
         )
         self.out = nn.Linear( *  * , )   # fully connected layer, output  classes

     def forward(self, x):
         x = self.conv1(x)
         x = self.conv2(x)
         x = x.view(x.size(), -)           # flatten the output of conv2 to (batch_size,  *  * )，只有tensor对象才可以使用x.size()
         output = self.out(x)
         return output, x    # return x for visualization

 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, (b_x, b_y) in enumerate(train_loader):   # gives 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

         if step %  == :
             test_output = cnn(test_x)[]
             print("----------------")
             #print(test_output.shape)   #*
             #print(torch.max(test_output, ))     #返回的每一行中最大值和其下标
             pred_y = torch.max(test_output, )[].data.numpy() #返回的是每个样本对应0-9数字可能性最大的概率对应的下标
             accuracy = float((pred_y == test_y.data.numpy()).astype(int).sum()) / float(test_y.size())
             print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy(), '| test accuracy: %.2f' % accuracy)

 # print  predictions from test data
 test_output, _ = cnn(test_x[:])
 pred_y = torch.max(test_output, )[].data.numpy()
 print(pred_y, 'prediction number')
 print(test_y[:].numpy(), 'real number')