3月份的时候其实用过一次TF的，但当时记忆一点都不深……而且没有硬件，跑什么东西都跑不起来。
现在TF出了正式版了，改动也比较大，于是就重新学TF。
下面是一个LeNet5的例子，是根据Tutorial改的。
TensorFlow Tutorial里面“MNIST高级教程”里面是有一个LeNet5的例子的。跑完之后看了一下Yan Lecun的文章，发现好像教程和文章并不完全对应。教程中的每层的特征数更多，并且加入了Dropout。那么就自己对着论文试着写一下这个网络吧。（反正肯定还跟作者文章中的网络不对应）
首先，输入改为了28×28。之后，里面的特征维度按照Lecon的文章改了一下。
代码
# -*- coding: utf-8 -*-
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import sys
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
FLAGS = None
def deepnn(x):
x_image = tf.reshape(x, [-1, 28, 28, 1])
conv_1_W = weight_variable([5, 5, 1, 6])
conv_1_b = bias_variable([6])
conv_1 = tf.nn.relu(tf.nn.conv2d(x_image, conv_1_W, strides=[1, 1, 1, 1], padding="SAME") + conv_1_b)
pool_2 = max_pool_2x2(conv_1)
conv_3_W = weight_variable([5, 5, 6, 16])
conv_3_b = bias_variable([16])
conv_3 = tf.nn.relu(tf.nn.conv2d(pool_2, conv_3_W, strides=[1, 1, 1, 1], padding="VALID") + conv_3_b)
pool_4 = max_pool_2x2(conv_3)
conv_5_W = weight_variable([5, 5, 16, 120])
conv_5_b = bias_variable([120])
conv_5 = tf.nn.relu(tf.nn.conv2d(pool_4, conv_5_W, strides=[1, 1, 1, 1], padding="VALID") + conv_5_b)
conv_5_reshape = tf.reshape(conv_5, [-1, 120])
fc_6_W = weight_variable([120, 84])
fc_6_b = bias_variable([84])
fc_6 = tf.matmul(conv_5_reshape, fc_6_W) + fc_6_b
output_W = weight_variable([84, 10])
output_b = bias_variable([10])
output = tf.matmul(fc_6, output_W) + output_b
return output
def conv2d(x, W):
"""conv2d returns a 2d convolution layer with full stride."""
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
"""max_pool_2x2 downsamples a feature map by 2X."""
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
def weight_variable(shape):
"""weight_variable generates a weight variable of a given shape."""
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
"""bias_variable generates a bias variable of a given shape."""
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def main(_):
# 读数据
mnist = input_data.read_data_sets(FLAGS.data_dir, one_hot=True)
# 设置PlaceHolder
x = tf.placeholder(tf.float32, [None, 784])
y_ = tf.placeholder(tf.float32, [None, 10])
# 构建网络
y_conv = deepnn(x)
# 定义Loss
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=y_conv))
# 定义如何优化
train_step = tf.train.AdamOptimizer(1e-4).minimize(loss)
# 输出用的“精度”
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
with tf.Session() as sess:
tf.global_variables_initializer().run()
for i in range(20000):
data_x, data_y = mnist.train.next_batch(50)
if i % 100 == 0:
train_accuracy = accuracy.eval(feed_dict={x: data_x, y_: data_y})
train_loss = loss.eval(feed_dict={x: data_x, y_: data_y})
print('迭代次数 %d, loss %g, 精度 %g' % (i, train_loss, train_accuracy))
train_step.run(feed_dict={x: data_x, y_: data_y})
print('测试精度 %g' % accuracy.eval(feed_dict={x: mnist.test.images, y_: mnist.test.labels}))
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--data_dir', type=str, default='data_mnist', help='数据存放位置')
FLAGS, unparsed = parser.parse_known_args()
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
发表回复