使用minst识别例子,使用tensorboard调参

1、准备mnists数据集，其方法有两种：

第一种使用tensorflow的接口函数--input_data.read_data_sets()，其会警告：提示要自己实现下载函数，但是其是可以实现下载数据的，其需要翻墙。否则会报错退出。

第二种自己手动到LeCun官网上下在数据集，其网站是：mnist数据集。把里面的四个文件都下载下来

 注：把下载好的数据放到相应的文件夹下。

然后代码相应的代码如下：

import os
import tensorflow as tf
import urllib.request  #python3使用的接口方法。python2使用的是另一种方法
import tensorflow.examples.tutorials.mnist.input_data as input_data

#这个文件路径在开头不能有‘/’，否则会路径出错
LOGDIR = 'tmp/mnist_tutorial/'
GITHUB_URL = 'https://raw.githubusercontent.com/mamcgrath/TensorBoard-TF-Dev-Summit-Tutorial/master/'
LOGDIR = 'tmp/mnist_tutorial/'

### MNIST EMBEDDINGS ###
mnist = input_data.read_data_sets(LOGDIR, one_hot=True)
### Get a sprite and labels file for the embedding projector ###
urllib.request.urlretrieve(GITHUB_URL + 'labels_1024.tsv', LOGDIR + 'labels_1024.tsv')
urllib.request.urlretrieve(GITHUB_URL + 'sprite_1024.png', LOGDIR + 'sprite_1024.png')


def conv_layer(input, size_in, size_out, name="conv"):
    # tf.name_scope creates namespace for operators in the default graph , places into group, easier to read
    # A graph maintains a stack of name scopes. A `with name_scope(...):`
    # statement pushes a new name onto the stack for the lifetime of the context.
    # Ops have names, name scopes group ops
    # 为下面创建的变量添加一个命名空间，其类似于C++里的命名空间，还有一个是variable_scope命名空间。其跟name_scope有区别，具体看相应博客
    with tf.name_scope(name):
        # 其中为w、b进行初始化为适合的数值，这样子有助于网络的训练，否则容易出现梯度消失的现象。这里使用tensorflow自带的初始化函数接口
        w = tf.Variable(tf.truncated_normal([5, 5, size_in, size_out], stddev=0.1), name="W")
        b = tf.Variable(tf.constant(0.1, shape=[size_out]), name="B")
        conv = tf.nn.conv2d(input, w, strides=[1, 1, 1, 1], padding="SAME")
        act = tf.nn.relu(conv + b)
        # collect this data by attaching tf.summary.histogram ops to the gradient outputs and to the variable that holds weights, respectively.
        # visualize the the distribution of weights and biases
        tf.summary.histogram("weights", w)
        tf.summary.histogram("biases", b)
        tf.summary.histogram("activations", act)
        return tf.nn.max_pool(act, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME")


def fc_layer(input, size_in, size_out, name="fc"):
    with tf.name_scope(name):
        w = tf.Variable(tf.truncated_normal([size_in, size_out], stddev=0.1), name="W")
        b = tf.Variable(tf.constant(0.1, shape=[size_out]), name="B")
        act = tf.nn.relu(tf.matmul(input, w) + b)
        tf.summary.histogram("weights", w)
        tf.summary.histogram("biases", b)
        tf.summary.histogram("activations", act)
        return act


def mnist_model(learning_rate, use_two_conv, use_two_fc, hparam):
    tf.reset_default_graph()
    # 这里时设置模型训练占用gpu的大小。
    gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.6)
    sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))

    # Setup placeholders, and reshape the data
    # 为变量申请占位符，相当于申请内存
    x = tf.placeholder(tf.float32, shape=[None, 784], name="x")
    x_image = tf.reshape(x, [-1, 28, 28, 1])
    # Outputs a Summary protocol buffer with 3 images.
    tf.summary.image('input', x_image, 3)
    y = tf.placeholder(tf.float32, shape=[None, 10], name="labels")

    if use_two_conv:
        conv1 = conv_layer(x_image, 1, 32, "conv1")
        conv_out = conv_layer(conv1, 32, 64, "conv2")
    else:
        conv1 = conv_layer(x_image, 1, 64, "conv")
        conv_out = tf.nn.max_pool(conv1, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="SAME")
    # 这里是为了是卷积输出的特征图转换为一个两维的数据，从而变成适合后面全连层的输入数据
    flattened = tf.reshape(conv_out, [-1, 7 * 7 * 64])

    if use_two_fc:
        fc1 = fc_layer(flattened, 7 * 7 * 64, 1024, "fc1")
        # we want these embeeddings to visualize them later
        #把倒数第二层全连层的输出特征添加到tensorboard的embedding里。到时候可以对这些特征进行一些可视化操作，
        #一般这一层已经有样本分类功能
        embedding_input = fc1
        embedding_size = 1024
        logits = fc_layer(fc1, 1024, 10, "fc2")
    else:
        embedding_input = flattened
        embedding_size = 7 * 7 * 64
        logits = fc_layer(flattened, 7 * 7 * 64, 10, "fc")
    with tf.name_scope("xent"):
        xent = tf.reduce_mean(
            tf.nn.softmax_cross_entropy_with_logits(
                logits=logits, labels=y), name="xent")
        # save that single number
        tf.summary.scalar("xent", xent)

    with tf.name_scope("train"):
        #这个是使用比较多的网络权重优化器
        train_step = tf.train.AdamOptimizer(learning_rate).minimize(xent)

    with tf.name_scope("accuracy"):
        correct_prediction = tf.equal(tf.argmax(logits, 1), tf.argmax(y, 1))
        accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
        tf.summary.scalar("accuracy", accuracy)
    # Merges all summaries collected in the default graph
    summ = tf.summary.merge_all()

    # intiialize embedding matrix as 0s
    embedding = tf.Variable(tf.zeros([1024, embedding_size]), name="test_embedding")
    # give it calculated embedding
    assignment = embedding.assign(embedding_input)
    # initialize the saver
    # Add ops to save and restore all the variables.
    saver = tf.train.Saver()

    sess.run(tf.global_variables_initializer())
    # filewriter is how we write the summary protocol buffers to disk
    # writer = tf.summary.FileWriter(<some-directory>, sess.graph)
    writer = tf.summary.FileWriter(LOGDIR + hparam)
    writer.add_graph(sess.graph)

    ## Format: tensorflow/contrib/tensorboard/plugins/projector/projector_config.proto
    config = tf.contrib.tensorboard.plugins.projector.ProjectorConfig()
    ## You can add multiple embeddings. Here we add only one.
    embedding_config = config.embeddings.add()
    embedding_config.tensor_name = embedding.name
    embedding_config.sprite.image_path = LOGDIR + 'sprite_1024.png'
    embedding_config.metadata_path = LOGDIR + 'labels_1024.tsv'
    # Specify the width and height of a single thumbnail.
    embedding_config.sprite.single_image_dim.extend([28, 28])
    tf.contrib.tensorboard.plugins.projector.visualize_embeddings(writer, config)

    for i in range(2001):
        batch = mnist.train.next_batch(100)
        if i % 5 == 0:
            [train_accuracy, s] = sess.run([accuracy, summ], feed_dict={x: batch[0], y: batch[1]})
            # This method wraps the provided summary in an Event protocol buffer and adds it to the event file.
            writer.add_summary(s, i)
        if i % 500 == 0:
            sess.run(assignment, feed_dict={x: mnist.test.images[:1024], y: mnist.test.labels[:1024]})
            saver.save(sess, os.path.join(LOGDIR, "model.ckpt"), i)
        sess.run(train_step, feed_dict={x: batch[0], y: batch[1]})


def make_hparam_string(learning_rate, use_two_fc, use_two_conv):
    conv_param = "conv=2" if use_two_conv else "conv=1"
    fc_param = "fc=2" if use_two_fc else "fc=1"
    return "lr_{}_{}_{}".format(learning_rate, conv_param, fc_param)


def main():
    # You can try adding some more learning rates
    for learning_rate in [1E-3, 1E-4]:

        # Include "False" as a value to try different model architectures
        for use_two_fc in [True, False]:
            for use_two_conv in [True, False]:
                # Construct a hyperparameter string for each one (example: "lr_1E-3,fc=2,conv=2)
                hparam = make_hparam_string(learning_rate, use_two_fc, use_two_conv)
                print('Starting run for %s' % hparam)

                # Actually run with the new settings
                mnist_model(learning_rate, use_two_fc, use_two_conv, hparam)


if __name__ == '__main__':
    main()