tensorflow的mnist改写成pytorch

   最近公司使用算法要用pytorch，所以本人暂时放弃使用tensorflow，为了练手pytorch，本人首先使用pytorch将tensorflow版本的mnist转换成pytorch版本，tensorflow原版本如下所示：

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


import tensorflow as tf

sess = tf.InteractiveSession()


x = tf.placeholder(tf.float32, shape=[None, 784])
y_ = tf.placeholder(tf.float32, shape=[None, 10])
W = tf.Variable(tf.zeros([784,10]))
b = tf.Variable(tf.zeros([10]))


sess.run(tf.global_variables_initializer())

y = tf.matmul(x,W) + b

cross_entropy = tf.reduce_mean(
    tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y))

train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)

for _ in range(1000):
  batch = mnist.train.next_batch(100)
  train_step.run(feed_dict={x: batch[0], y_: batch[1]})
correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))

accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

print(accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels}))

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):
  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                        strides=[1, 2, 2, 1], padding='SAME')

W_conv1 = weight_variable([5, 5, 1, 32])
b_conv1 = bias_variable([32])
x_image = tf.reshape(x, [-1,28,28,1])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)

W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
h_pool2 = max_pool_2x2(h_conv2)

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)
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
W_fc2 = weight_variable([1024, 10])
b_fc2 = bias_variable([10])

y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
cross_entropy = tf.reduce_mean(
    tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
correct_prediction = tf.equal(tf.argmax(y_conv,1), tf.argmax(y_,1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

saver = tf.train.Saver()  # defaults to saving all variables

sess.run(tf.global_variables_initializer())
for i in range(20000):
  batch = mnist.train.next_batch(50)
  if i%100 == 0:
    train_accuracy = accuracy.eval(feed_dict={
        x:batch[0], y_: batch[1], keep_prob: 1.0})
    print("step %d, training accuracy %g"%(i, train_accuracy))

  train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
saver.save(sess, '/home/XXX/learning_tensorflow/form/model.ckpt')  #保存模型参数，注意把这里改为自己的路径

print("test accuracy %g"%accuracy.eval(feed_dict={
    x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0}))

  改写成pytorch版本后如下所示：

import torch.nn as nn
import torch
import torch.nn.functional as F
from torch.autograd import Variable
import argparse
import torchvision.transforms as transforms
import torchvision.datasets as dsets

train_dataset = dsets.MNIST(root = '../../data_sets/mnist',
                           train = True,
                           transform = transforms.ToTensor(),
                           download = True)

class Net(nn.Module):
    def __init__(self):
        super(Net,self).__init__()
        self.conv1 = nn.Conv2d(1, 32, kernel_size=5,stride=1,padding=2)
        self.conv2 = nn.Conv2d(32, 64, kernel_size=5,stride=1,padding=2)
        self.fc1 = nn.Linear(7*7*64, 1024)
        self.fc2 = nn.Linear(1024,10)

    def forward(self, x, target = None):
        x = F.max_pool2d(F.relu(self.conv1(x)),kernel_size=2,stride=2,padding=0)
        x = F.max_pool2d(F.relu(self.conv2(x)),kernel_size=2,stride=2,padding=0)
        x = x.view(-1,7*7*64)
        x = F.relu(self.fc1(x))
        x = F.dropout(x,training=True)
        x = self.fc2(x)
        x = F.log_softmax(x,dim=1)
        return x

model = Net()

def main(args):
    if args.cuda:
        model.cuda()
    criterion = nn.CrossEntropyLoss()
    training_accuracy = 0
    train_loader = torch.utils.data.DataLoader(dataset = train_dataset,
                                           batch_size = args.batch_size,
                                           shuffle = True)
    optimizer = torch.optim.Adam(model.parameters(), lr=args.learning_rate)
    model.train()
    for epochs in range(1,20000):
        for i,(images,labels) in enumerate(train_loader):
            if args.cuda:
                images, labels = images.cuda(), labels.cuda()
            images = Variable(images.view(-1,1,28,28))
            labels = Variable(labels)
            optimizer.zero_grad()
            outputs = model(images)
            loss = criterion(outputs,labels)
            loss.backward()
            optimizer.step()
            if i%100 == 0:
                pred = outputs.data.max(1)[1]
                training_accuracy += pred.eq(labels.data[1]).sum()
                print('epochs:%d,Loss:%5f,Acuuracy:%g'%(epochs,loss,training_accuracy))
                training_accuracy = 0

if __name__=="__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument('--learning_rate', default=1e-3, type=float, help='learning rate for the stochastic gradient update.')
    parser.add_argument('--batch_size', type=int, default=50, help='input batch size for training (default: 64)')
    parser.add_argument('--cuda', action='store_true', default=True,help='Enable CUDA training')
    args = parser.parse_args()
    main(args)

几点感受:
1.pytorch不需要定义静态图，可以直接上手使用，网络定义更加方便快捷。
2.许多功能定义封装非常完善，不需要自己手写。
3.变量的定义和训练使用非常方便。

参考：
1.https://blog.csdn.net/victoriaw/article/details/72354307
2.https://blog.csdn.net/caichao08/article/details/78997033
3.https://blog.csdn.net/sparta_117/article/details/66965760