撒花！《神经网络与深度学习》中文教程正式开源！全书 pdf、ppt 和代码一同放出...

import os
import torch
import torch.nn as nn
from torch.autograd import Variable
import torch.utils.data as Data
import torchvision
import torch.nn.functional as F
import numpy as np
learning_rate = 1e-4
keep_prob_rate = 0.7 #
max_epoch = 3
BATCH_SIZE = 50

DOWNLOAD_MNIST = False
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, transform=torchvision.transforms.ToTensor(), download=DOWNLOAD_MNIST,)
train_loader = Data.DataLoader(dataset = train_data ,batch_size= BATCH_SIZE ,shuffle= True)

test_data = torchvision.datasets.MNIST(root = './mnist/',train = False)
test_x = Variable(torch.unsqueeze(test_data.test_data,dim  = 1),volatile = True).type(torch.FloatTensor)[:500]/255.
test_y = test_data.test_labels[:500].numpy()

class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Sequential(
            nn.Conv2d( # ???
                # patch 7 * 7 ; 1  in channels ; 32 out channels ; ; stride is 1
                # padding style is same(that means the convolution opration's input and output have the same size)
                in_channels=      ,  
                out_channels=     ,
                kernel_size=      ,
                stride=           ,
                padding=          ,
            ),
            nn.ReLU(),        # activation function
            nn.MaxPool2d(2),  # pooling operation
        )
        self.conv2 = nn.Sequential( # ???
            # line 1 : convolution function, patch 5*5 , 32 in channels ;64 out channels; padding style is same; stride is 1
            # line 2 : choosing your activation funciont
            # line 3 : pooling operation function.
            
         

        )
        self.out1 = nn.Linear( 7*7*64 , 1024 , bias= True)   # full connection layer one

        self.dropout = nn.Dropout(keep_prob_rate)
        self.out2 = nn.Linear(1024,10,bias=True)



    def forward(self, x):
        x = self.conv1(x)
        x = self.conv2(x)
        x = x.view(      )  # flatten the output of coonv2 to (batch_size ,32 * 7 * 7)    # ???
        out1 = self.out1(x)
        out1 = F.relu(out1)
        out1 = self.dropout(out1)
        out2 = self.out2(out1)
        output = F.softmax(out2)
        return output


def test(cnn):
    global prediction
    y_pre = cnn(test_x)
    _,pre_index= torch.max(y_pre,1)
    pre_index= pre_index.view(-1)
    prediction = pre_index.data.numpy()
    correct  = np.sum(prediction == test_y)
    return correct / 500.0


def train(cnn):
    optimizer = torch.optim.Adam(cnn.parameters(), lr=learning_rate )
    loss_func = nn.CrossEntropyLoss()
    for epoch in range(max_epoch):
        for step, (x_, y_) in enumerate(train_loader):
            x ,y= Variable(x_),Variable(y_)
            output = cnn(x)  
            loss = loss_func(output,y)
            optimizer.zero_grad()
            loss.backward()
            optimizer.step()
            
            if step != 0 and step % 20 ==0:
                print("=" * 10,step,"="*5,"="*5, "test accuracy is ",test(cnn) ,"=" * 10 )

if __name__ == '__main__':
    cnn = CNN()
    train(cnn)

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)

learning_rate = 1e-4
keep_prob_rate = 0.7 # 
max_epoch = 2000
def compute_accuracy(v_xs, v_ys):
    global prediction
    y_pre = sess.run(prediction, feed_dict={xs: v_xs, keep_prob: 1})
    correct_prediction = tf.equal(tf.argmax(y_pre,1), tf.argmax(v_ys,1))
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
    result = sess.run(accuracy, feed_dict={xs: v_xs, ys: v_ys, keep_prob: 1})
    return result

def weight_variable(shape):
    initial = tf.truncated_normal(shape, stddev=0.1)
    return tf.Variable(initial)

def bias_variable(shape):
    initial = tf.constant(0.1, shape=shape)
    return tf.Variable(initial)

def conv2d(x, W):
    # 每一维度  滑动步长全部是 1， padding 方式 选择 same
    # 提示 使用函数  tf.nn.conv2d
    
    return 

def max_pool_2x2(x):
    # 滑动步长 是 2步; 池化窗口的尺度 高和宽度都是2; padding 方式 请选择 same
    # 提示 使用函数  tf.nn.max_pool
    
    return 

# define placeholder for inputs to network
xs = tf.placeholder(tf.float32, [None, 784])/255.
ys = tf.placeholder(tf.float32, [None, 10])
keep_prob = tf.placeholder(tf.float32)
x_image = tf.reshape(xs, [-1, 28, 28, 1])

#  卷积层 1
## conv1 layer ##

W_conv1 =                       # patch 7x7, in size 1, out size 32
b_conv1 =                      
h_conv1 =                       # 卷积  自己选择 选择激活函数
h_pool1 =                       # 池化               

# 卷积层 2
W_conv2 =                        # patch 5x5, in size 32, out size 64
b_conv2 = 
h_conv2 =                        # 卷积  自己选择 选择激活函数
h_pool2 =                        # 池化

#  全连接层 1
## fc1 layer ##
W_fc1 = weight_variable([7*7*64, 1024])
b_fc1 = bias_variable([1024])

h_pool2_flat = tf.reshape(h_pool2, [-1, 7*7*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)

# 全连接层 2
## fc2 layer ##
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])
prediction = tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2)


# 交叉熵函数
cross_entropy = tf.reduce_mean(-tf.reduce_sum(ys * tf.log(prediction),
                                              reduction_indices=[1]))
train_step = tf.train.AdamOptimizer(learning_rate).minimize(cross_entropy)

with tf.Session() as sess:
    init = tf.global_variables_initializer()
    sess.run(init)
    
    for i in range(max_epoch):
        batch_xs, batch_ys = mnist.train.next_batch(100)
        sess.run(train_step, feed_dict={xs: batch_xs, ys: batch_ys, keep_prob:keep_prob_rate})
        if i % 100 == 0:
            print(compute_accuracy(
                mnist.test.images[:1000], mnist.test.labels[:1000]))