nn.Conv2d(
    in_channels=32,
    out_channels=64,
    kernel_size=3,
    stride=1,
    padding=1,
)

MaxPool2d(kernel_size, 
		stride=None, 
		padding=0, 
		dilation=1, 
		return_indices=False, 
		ceil_mode=False)

import os
import numpy as np
import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt
# 循環世代
EPOCH = 20
BATCH_SIZE = 50
# 下載mnist數據集
train_data = torchvision.datasets.MNIST(root='./mnist/',train=True,transform=torchvision.transforms.ToTensor(),download=True,)
# (60000, 28, 28)
print(train_data.train_data.size())                 
# (60000)
print(train_data.train_labels.size())               
train_loader = Data.DataLoader(dataset=train_data, batch_size=BATCH_SIZE, shuffle=True)
# 測試集
test_data = torchvision.datasets.MNIST(root='./mnist/', train=False)
# (2000, 1, 28, 28)
# 標準化
test_x = torch.unsqueeze(test_data.test_data, dim=1).type(torch.FloatTensor)[:2000]/255.
test_y = test_data.test_labels[:2000]
# 建立pytorch神經網絡
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        #----------------------------#
        #   第一部分卷積
        #----------------------------#
        self.conv1 = nn.Sequential(
            nn.Conv2d(
                in_channels=1,
                out_channels=32,
                kernel_size=5,
                stride=1,
                padding=2,
                dilation=1
            ),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2),
        )
        #----------------------------#
        #   第二部分卷積
        #----------------------------#
        self.conv2 = nn.Sequential( 
            nn.Conv2d(
                in_channels=32,
                out_channels=64,
                kernel_size=3,
                stride=1,
                padding=1,
                dilation=1
            ),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2),
        )
        #----------------------------#
        #   全連接+池化+全連接
        #----------------------------#
        self.ful1 = nn.Linear(64 * 7 * 7, 512)
        self.drop = nn.Dropout(0.5)
        self.ful2 = nn.Sequential(nn.Linear(512, 10),nn.Softmax())
    #----------------------------#
    #   前向傳播
    #----------------------------#   
    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(x.size(0), -1)
        x = self.ful1(x)
        x = self.drop(x)
        output = self.ful2(x)
        return output
cnn = CNN()
# 指定優化器
optimizer = torch.optim.Adam(cnn.parameters(), lr=1e-3) 
# 指定loss函數
loss_func = nn.CrossEntropyLoss()
for epoch in range(EPOCH):
    for step, (b_x, b_y) in enumerate(train_loader): 
        #----------------------------#
        #   計算loss并修正權值
        #----------------------------#   
        output = cnn(b_x)
        loss = loss_func(output, b_y) 
        optimizer.zero_grad() 
        loss.backward() 
        optimizer.step() 
        #----------------------------#
        #   打印
        #----------------------------#   
        if step % 50 == 0:
            test_output = 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: %2d'% epoch, ', loss: %.4f' % loss.data.numpy(), ', accuracy: %.4f' % accuracy)