资源简介
深度学习21个项目实例
代码片段和文件信息
# coding: utf-8
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
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‘)
if __name__ == ‘__main__‘:
# 读入数据
mnist = input_data.read_data_sets(“MNIST_data/“ one_hot=True)
# x为训练图像的占位符、y_为训练图像标签的占位符
x = tf.placeholder(tf.float32 [None 784])
y_ = tf.placeholder(tf.float32 [None 10])
# 将单张图片从784维向量重新还原为28x28的矩阵图片
x_image = tf.reshape(x [-1 28 28 1])
# 第一层卷积层
W_conv1 = weight_variable([5 5 1 32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image W_conv1) + b_conv1)
h_pool1 = max_pool_2x2(h_conv1)
# 第二层卷积层
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)
# 全连接层,输出为1024维的向量
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)
# 使用Dropout,keep_prob是一个占位符,训练时为0.5,测试时为1
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1 keep_prob)
# 把1024维的向量转换成10维,对应10个类别
W_fc2 = weight_variable([1024 10])
b_fc2 = bias_variable([10])
y_conv = tf.matmul(h_fc1_drop W_fc2) + b_fc2
# 我们不采用先Softmax再计算交叉熵的方法,而是直接用tf.nn.softmax_cross_entropy_with_logits直接计算
cross_entropy = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(labels=y_ logits=y_conv))
# 同样定义train_step
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
# 定义测试的准确率
correct_prediction = tf.equal(tf.argmax(y_conv 1) tf.argmax(y_ 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction tf.float32))
# 创建Session和变量初始化
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
# 训练20000步
for i in range(20000):
batch = mnist.train.next_batch(50)
# 每100步报告一次在验证集上的准确度
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})
# 训练结束后报告在测试集上的准确度
print(“test accuracy %g“ % accuracy.eval(feed_dict={
x: mnist.test.images y_: mnist.test.labels keep_prob: 1.0}))
属性 大小 日期 时间 名称
----------- --------- ---------- ----- ----
文件 1676 2018-05-04 12:04 Deep-Learning-21-Examples-master\.gitignore
文件 3222 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_1\convolutional.py
文件 871 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_1\download.py
文件 576 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_1\label.py
文件 1648877 2018-07-24 15:11 Deep-Learning-21-Examples-master\chapter_1\MNIST_data\t10k-images-idx3-ubyte.gz
文件 4542 2018-07-24 15:11 Deep-Learning-21-Examples-master\chapter_1\MNIST_data\t10k-labels-idx1-ubyte.gz
文件 9912422 2018-07-24 15:11 Deep-Learning-21-Examples-master\chapter_1\MNIST_data\train-images-idx3-ubyte.gz
文件 28881 2018-07-24 15:11 Deep-Learning-21-Examples-master\chapter_1\MNIST_data\train-labels-idx1-ubyte.gz
文件 2554 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_1\README.md
文件 1120 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_1\save_pic.py
文件 2487 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_1\softmax_regression.py
文件 1447 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\delete_broken_img.py
文件 89 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\.gitignore
文件 4264 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\docker\Dockerfile
文件 25553 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\docs\1-inputs.png
文件 101045 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\docs\1-targets.png
文件 99973 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\docs\1-tensorflow.png
文件 10630 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\docs\1-torch.jpg
文件 117940 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\docs\418.png
文件 18392 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\docs\5-inputs.png
文件 95452 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\docs\5-targets.png
文件 97818 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\docs\5-tensorflow.png
文件 8524 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\docs\5-torch.jpg
文件 51210 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\docs\51-inputs.png
文件 100405 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\docs\51-targets.png
文件 112270 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\docs\51-tensorflow.png
文件 13039 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\docs\51-torch.jpg
文件 35342 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\docs\95-inputs.png
文件 81306 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\docs\95-targets.png
文件 113817 2018-05-04 12:04 Deep-Learning-21-Examples-master\chapter_10\pix2pix-tensorflow\docs\95-tensorflow.png
............此处省略985个文件信息
评论
共有 条评论