Deep Learning——TensorFlow平台下MNIST的实现(改进)(基于convolutional neural network)
2016-10-21 18:24
525 查看
****改进版mnist****采用卷积神经网络
1.下载input_data.py文件 (此文件代码主要是实现下载数据集)
2.切换到python命令模式下
import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) #这里的第一个参数是下载的文件所放的位置
3.下载完成之后,建一个文件test_tensor_flow_mnist_conv.py
然后在Linux命令模式下执行该程序
改进后大有改观,基本在98%以上,不过对机器的要求要是很压力的,本人机子内存32G的跑了2个小时。大家可以把20000改小点!
1.下载input_data.py文件 (此文件代码主要是实现下载数据集)
2.切换到python命令模式下
import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True) #这里的第一个参数是下载的文件所放的位置
3.下载完成之后,建一个文件test_tensor_flow_mnist_conv.py
#!/usr/bin/env python import input_data import tensorflow as tf mnist = input_data.read_data_sets("MNIST_data", one_hot=True) sess = tf.InteractiveSession() x = tf.placeholder("float", shape=[None, 784]) 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("float") h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob) W_fc2 = weight_variable([1024, 10]) b_fc2 = bias_variable([10]) y_conv=tf.nn.softmax(tf.matmul(h_fc1_drop, W_fc2) + b_fc2) cross_entropy = -tf.reduce_sum(y_*tf.log(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, "float")) sess.run(tf.initialize_all_variables()) 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}) print "test accuracy %g"%accuracy.eval(feed_dict={ x: mnist.test.images, y_: mnist.test.labels, keep_prob: 1.0})
然后在Linux命令模式下执行该程序
python test_tensor_flow_mnist_conv.py
改进后大有改观,基本在98%以上,不过对机器的要求要是很压力的,本人机子内存32G的跑了2个小时。大家可以把20000改小点!
相关文章推荐
- Deep Learning——TensorFlow平台下MNIST的实现(基于shallow learning)
- 深度学习FPGA实现基础知识10(Deep Learning(深度学习)卷积神经网络(Convolutional Neural Network,CNN))
- 深度学习FPGA实现基础知识10(Deep Learning(深度学习)卷积神经网络(Convolutional Neural Network,CNN))
- 用tensorflow实现的,基于mnist数据集上的一个简易模型
- 基于TensorFLow实现MNIST和softmax回归
- Convolutional Neural Network-based Place Recognition 基于卷积神经网络的地点识别算法
- fast neural style transfer图像风格迁移基于tensorflow实现
- Tensorflow: Convolutional Neural Network Basic
- kaggle competition 实践学习 文本分类 keras实现 模型基于yoon kim 的 Convolutional Neural Networks for Sentence Class
- tensorflow实战一---基于线性回归简单实现mnist手写体识别
- tensorflow(4)---mnist问题的深度卷积神经网络(基于官网文档的实现)
- Face Expression Recognition with a 2-Channel Convolutional Neural Network(基于双通道卷积神经网络的表情识别部分翻译)
- Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring代码实现注意实现
- tensorflow MNIST Convolutional Neural Network
- 【Deep Learning】Review of Stereo Matching by Training a Convolutional Neural Network to Compare Image
- Deep Learning-TensorFlow (1) CNN卷积神经网络_MNIST手写数字识别代码实现详解
- 基于TensorFlow的mnist数据集的最近邻算法实现代码
- 基于深度学习的风格迁移转换的两种实现——style-transfer和fast-neural-style-tensorflow
- 利用tensorflow一步一步实现基于MNIST 数据集进行手写数字识别的神经网络,逻辑回归
- Deep Learning-TensorFlow (1) CNN卷积神经网络_MNIST手写数字识别代码实现