吴裕雄--天生自然深度学习TensorBoard可视化:projector_MNIST

import os
import tensorflow as tf

from tensorflow.examples.tutorials.mnist import input_data
from tensorflow.contrib.tensorboard.plugins import projector

INPUT_NODE = 784
OUTPUT_NODE = 10
LAYER1_NODE = 500

def get_weight_variable(shape, regularizer):
    weights = tf.get_variable("weights", shape, initializer=tf.truncated_normal_initializer(stddev=0.1))
    if regularizer != None: tf.add_to_collection(‘losses‘, regularizer(weights))
    return weights

def inference(input_tensor, regularizer):
    with tf.variable_scope(‘layer1‘):
        weights = get_weight_variable([INPUT_NODE, LAYER1_NODE], regularizer)
        biases = tf.get_variable("biases", [LAYER1_NODE], initializer=tf.constant_initializer(0.0))
        layer1 = tf.nn.relu(tf.matmul(input_tensor, weights) + biases)

    with tf.variable_scope(‘layer2‘):
        weights = get_weight_variable([LAYER1_NODE, OUTPUT_NODE], regularizer)
        biases = tf.get_variable("biases", [OUTPUT_NODE], initializer=tf.constant_initializer(0.0))
        layer2 = tf.matmul(layer1, weights) + biases
    return layer2

BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 10000
MOVING_AVERAGE_DECAY = 0.99

LOG_DIR = ‘F:\\temp\\log\\‘
SPRITE_FILE = ‘F:\\temp\\log\\mnist_sprite.jpg‘
META_FIEL = "F:\\temp\\log\\mnist_meta.tsv"
TENSOR_NAME = "FINAL_LOGITS"
def train(mnist):
    #  输入数据的命名空间。
    with tf.name_scope(‘input‘):
        x = tf.placeholder(tf.float32, [None, INPUT_NODE], name=‘x-input‘)
        y_ = tf.placeholder(tf.float32, [None, OUTPUT_NODE], name=‘y-input‘)
    regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
    y = inference(x, regularizer)
    global_step = tf.Variable(0, trainable=False)

    # 处理滑动平均的命名空间。
    with tf.name_scope("moving_average"):
        variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
        variables_averages_op = variable_averages.apply(tf.trainable_variables())

    # 计算损失函数的命名空间。
    with tf.name_scope("loss_function"):
        cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=y, labels=tf.argmax(y_, 1))
        cross_entropy_mean = tf.reduce_mean(cross_entropy)
        loss = cross_entropy_mean + tf.add_n(tf.get_collection(‘losses‘))

    # 定义学习率、优化方法及每一轮执行训练的操作的命名空间。
    with tf.name_scope("train_step"):
        learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE,global_step,mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY,staircase=True)

        train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)
        with tf.control_dependencies([train_step, variables_averages_op]):
            train_op = tf.no_op(name=‘train‘)

    # 训练模型。
    with tf.Session() as sess:
        tf.global_variables_initializer().run()
        for i in range(TRAINING_STEPS):
            xs, ys = mnist.train.next_batch(BATCH_SIZE)
            _, loss_value, step = sess.run([train_op, loss, global_step], feed_dict={x: xs, y_: ys})
            if(i % 1000 == 0):
                print("After %d training step(s), loss on training batch is %g." % (i, loss_value))
        final_result = sess.run(y, feed_dict={x: mnist.test.images})
    return final_result
def visualisation(final_result):
    y = tf.Variable(final_result, name = TENSOR_NAME)
    summary_writer = tf.summary.FileWriter(LOG_DIR)

    config = projector.ProjectorConfig()
    embedding = config.embeddings.add()
    embedding.tensor_name = y.name

    # Specify where you find the metadata
    embedding.metadata_path = META_FIEL

    # Specify where you find the sprite (we will create this later)
    embedding.sprite.image_path = SPRITE_FILE
    embedding.sprite.single_image_dim.extend([28,28])

    # Say that you want to visualise the embeddings
    projector.visualize_embeddings(summary_writer, config)

    sess = tf.InteractiveSession()
    sess.run(tf.global_variables_initializer())
    saver = tf.train.Saver()
    saver.save(sess, os.path.join(LOG_DIR, "model"), TRAINING_STEPS)

    summary_writer.close()
def main(argv=None):
    mnist = input_data.read_data_sets("F:\\TensorFlowGoogle\\201806-github\\datasets\\MNIST_data", one_hot=True)
    final_result = train(mnist)
    visualisation(final_result)

if __name__ == ‘__main__‘:
    main()

原文地址:https://www.cnblogs.com/tszr/p/12098472.html

时间: 2024-11-06 07:07:15

吴裕雄--天生自然深度学习TensorBoard可视化:projector_MNIST的相关文章

吴裕雄--天生自然 高等数学学习:区间

区间.领域 自然数集——N 整数集——Z 有理数集——Q 实数集——R 建立数轴后,实数与数轴上的点一一对应. 建立某一实数集A与数轴上某一区间对应. 区间:设有数a,b,a<b,则称实数集{x|a<x<b}为一个开区间.记为:(a,b),即: (a,b)={x|a<x<b} a称为区间(a,b)的左端点. b称为区间(a,b)的右端点.   原文地址:https://www.cnblogs.com/tszr/p/11153079.html

吴裕雄--天生自然 高等数学学习:基本积分表

原文地址:https://www.cnblogs.com/tszr/p/11158956.html

吴裕雄--天生自然 高等数学学习:定积分的应用

原文地址:https://www.cnblogs.com/tszr/p/11159340.html

吴裕雄--天生自然 高等数学学习:柱面

原文地址:https://www.cnblogs.com/tszr/p/11164548.html

吴裕雄--天生自然 高等数学学习:空间曲线在坐标面上的投影

原文地址:https://www.cnblogs.com/tszr/p/11164639.html

吴裕雄--天生自然 高等数学学习:空间曲线及其方程

原文地址:https://www.cnblogs.com/tszr/p/11164609.html

吴裕雄--天生自然 高等数学学习:高阶偏导数

原文地址:https://www.cnblogs.com/tszr/p/11165379.html

吴裕雄--天生自然 高等数学学习:全微分

原文地址:https://www.cnblogs.com/tszr/p/11165473.html

吴裕雄--天生自然 高等数学学习:二重积分的计算方法

原文地址:https://www.cnblogs.com/tszr/p/11169530.html