pytorch 實現minist手寫識別體

from 莫煩python

import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision      # 數據庫模塊
import matplotlib.pyplot as plt

torch.manual_seed(1)    # reproducible

# Hyper Parameters
EPOCH = 1           # 訓練整批數據多少次, 爲了節約時間, 我們只訓練一次
BATCH_SIZE = 50
LR = 0.001          # 學習率
DOWNLOAD_MNIST = True  # 如果你已經下載好了mnist數據就寫上 False


# Mnist 手寫數字
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(),    # 轉換 PIL.Image or numpy.ndarray 成
                                                    # torch.FloatTensor (C x H x W), 訓練的時候 normalize 成 [0.0, 1.0] 區間
    download=DOWNLOAD_MNIST,          # 沒下載就下載, 下載了就不用再下了
)

print(train_data.train_data.size())
print(train_data.train_labels.size())
plt.imshow(train_data.train_data[0].numpy(), cmap='gray')
plt.title("%i" % train_data.train_labels[0])
plt.show()

test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)#讀取測試數據

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

# 爲了節約時間, 我們測試時只測試前2000個
test_x = torch.unsqueeze(test_data.data, dim=1).type(torch.FloatTensor)/255.   # shape from (2000, 28, 28) to (2000, 1, 28, 28), value in range(0,1)
test_y = test_data.targets

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 出來的圖片長寬沒有變化, padding=(kernel_size-1)/2 當 stride=1
            ),      # output shape (16, 28, 28)
            nn.ReLU(),    # activation
            nn.MaxPool2d(kernel_size=2),    # 在 2x2 空間裏向下採樣, 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)   # 展平多維的卷積圖成 (batch_size, 32 * 7 * 7)
        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, (b_x, b_y) in enumerate(train_loader):   # 分配 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

# 測試集
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')