• 神经网络 (2)- Alexnet Training on MNIST


    Win10 Anaconda下配置tensorflow+jupyter notebook环境

    1.安装anaconda
    到Anaconda官网下载,我是用的是Anaconda3-4.8.0版本(Python3对应的是Anaconda3,Python2对应的是Anaconda2),根据需要下载即可。下载好之后点击exe文件安装没什么好讲的。

    唯一需要特别说明的是,安装的过程中要把添加路径到环境中选项选中!安装完成之后到命令行输入命令验证是否成功安装:

    conda --version
    
    1. 安装tensorflow 官方步骤创建环境,
      If you installed a TensorFlow as it said in official documentation: https://www.tensorflow.org/versions/r0.10/get_started/os_setup.html#overview

    I mean creating an environment called tensorflow and tested your installation in python, but TensorFlow can not be imported in jupyter, you have to install jupyter in your tensorflow environment too:

    conda install jupyter notebook
    
    

    After that I run a jupyter and it can import TensorFlow too:

    jupyter notebook
    
    

    AlexNet 识别MNIST

    在这里插入图片描述

    以上是AlexNet的结构,上下其实是一样的,共同用一套参数。 Similar structure to LeNet, AlexNet has more filters per layer, deeper and stacked. There are 5 convolutional layers, 3 fully connected layers and with Relu applied after each of them, and dropout applied before the first and second fully connected layer.AlexNet是2012年ImageNet比赛的冠军,虽然过去了很长时间,但是作为深度学习中的经典模型,AlexNet不但有助于我们理解其中所使用的很多技巧,而且非常有助于提升我们使用深度学习工具箱的熟练度。

    from tensorflow.examples.tutorials.mnist import input_data
    mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
    import tensorflow as tf
     
    # 
    learning_rate = 0.001
    training_iters = 200000
    batch_size = 64
    display_step = 20
     
    # 
    n_input = 784 # 
    n_classes = 10 # 
    dropout = 0.8 # Dropout 
     
    # 
    x = tf.placeholder(tf.float32, [None, n_input])
    y = tf.placeholder(tf.float32, [None, n_classes])
    keep_prob = tf.placeholder(tf.float32)
     
    # 
    def conv2d(name, l_input, w, b):
        return tf.nn.relu(tf.nn.bias_add(tf.nn.conv2d(l_input, w, strides=[1, 1, 1, 1], padding='SAME'),b), name=name)
     
    # 
    def max_pool(name, l_input, k):
        return tf.nn.max_pool(l_input, ksize=[1, k, k, 1], strides=[1, k, k, 1], padding='SAME', name=name)
     
    # 
    def norm(name, l_input, lsize=4):
        return tf.nn.lrn(l_input, lsize, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name=name)
     
    #  
    def alex_net(_X, _weights, _biases, _dropout):
        # 
        _X = tf.reshape(_X, shape=[-1, 28, 28, 1])
     
        # 
        conv1 = conv2d('conv1', _X, _weights['wc1'], _biases['bc1'])
        # 
        pool1 = max_pool('pool1', conv1, k=2)
        # 
        norm1 = norm('norm1', pool1, lsize=4)
        # Dropout
        norm1 = tf.nn.dropout(norm1, _dropout)
     
        # 
        conv2 = conv2d('conv2', norm1, _weights['wc2'], _biases['bc2'])
        # 
        pool2 = max_pool('pool2', conv2, k=2)
        # 
        norm2 = norm('norm2', pool2, lsize=4)
        # Dropout
        norm2 = tf.nn.dropout(norm2, _dropout)
     
        # 
        conv3 = conv2d('conv3', norm2, _weights['wc3'], _biases['bc3'])
        conv4 = conv2d('conv4', conv3, _weights['wc4'], _biases['bc4'])
        conv5 = conv2d('conv5', conv4, _weights['wc5'], _biases['bc5']) 
        pool5 = max_pool('pool5', conv5, k=2)
        # 
        norm5 = norm('norm5', pool5, lsize=4)
        # Dropout
        norm5 = tf.nn.dropout(norm5, _dropout)
     
        # 
        dense1 = tf.reshape(norm5, [-1, _weights['wd1'].get_shape().as_list()[0]]) 
        dense1 = tf.nn.relu(tf.matmul(dense1, _weights['wd1']) + _biases['bd1'], name='fc1') 
        # 
        dense2 = tf.nn.relu(tf.matmul(dense1, _weights['wd2']) + _biases['bd2'], name='fc2') # Relu activation
     
        # 
        out = tf.matmul(dense2, _weights['out']) + _biases['out']
        return out
     
    # 
    weights = {
        'wc1': tf.Variable(tf.random_normal([11, 11, 1, 64])),
        'wc2': tf.Variable(tf.random_normal([5, 5, 64, 192])),
        'wc3': tf.Variable(tf.random_normal([3, 3, 192, 384])),
        'wc4': tf.Variable(tf.random_normal([3, 3, 384, 256])),
        'wc5': tf.Variable(tf.random_normal([3, 3, 256, 256])),
        'wd1': tf.Variable(tf.random_normal([4*4*256, 1024])),
        'wd2': tf.Variable(tf.random_normal([1024, 1024])),
        'out': tf.Variable(tf.random_normal([1024, 10]))
    }
    biases = {
        'bc1': tf.Variable(tf.random_normal([64])),
        'bc2': tf.Variable(tf.random_normal([192])),
        'bc3': tf.Variable(tf.random_normal([384])),
        'bc4': tf.Variable(tf.random_normal([256])),
        'bc5': tf.Variable(tf.random_normal([256])),
        'bd1': tf.Variable(tf.random_normal([1024])),
        'bd2': tf.Variable(tf.random_normal([1024])),
        'out': tf.Variable(tf.random_normal([n_classes]))
    }
     
    # 
    pred = alex_net(x, weights, biases, keep_prob)
     
    # 
    cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=y))
    optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
     
    # 
    correct_pred = tf.equal(tf.argmax(pred,1), tf.argmax(y,1))
    accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
     
    # 
    init = tf.initialize_all_variables()
     
    # 
    with tf.Session() as sess:
        sess.run(init)
        step = 1
        # Keep training until reach max iterations
        while step * batch_size < training_iters:
            batch_xs, batch_ys = mnist.train.next_batch(batch_size)
            # 
            sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys, keep_prob: dropout})
            if step % display_step == 0:
                # 
                acc = sess.run(accuracy, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
                # 
                loss = sess.run(cost, feed_dict={x: batch_xs, y: batch_ys, keep_prob: 1.})
                print ("Iter " + str(step*batch_size) + ", Minibatch Loss= " + "{:.6f}".format(loss) + ", Training Accuracy= " + "{:.5f}".format(acc))
            step += 1
        print ("Optimization Finished!")
        # 
        print ("Testing Accuracy:", sess.run(accuracy, feed_dict={x: mnist.test.images[:256], y: mnist.test.labels[:256], keep_prob: 1.}))
    
  • 相关阅读:
    精选文章
    Eclipse Git插件切换分支的时候不要Reset
    Spring ContentNegotiatingViewResolver
    Spring3 MVC 类型转换
    FTP DOS 命令行
    Java xml 解析
    Java 实现FTP上传和下载
    Hibernate update 和 merge 、saveOrUpdate的区别
    Spring MVC 文件下载时候 发现IE不支持
    Javasript 正则匹配任意字符
  • 原文地址:https://www.cnblogs.com/mrcharles/p/11879753.html
Copyright © 2020-2023  润新知