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：1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91from 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：1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67import 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