mobilenet_v1训练mnist

一般用lenet训练mnist，但是现在也可以使用mobilenet_v1来训练，创建mobilenet_v1_mnist_train.py，写下如下代码并放到/host/models/research/slim/nets中，写下如下代码。

#coding: utf-8
import os

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

import mnist_inference

BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.8
LEARNING_RATE_DECAY = 0.99
REGULARAZTION_RATE = 0.0001
TRAINING_STEPS =10000
MOVING_AVERAGE_DECAY = 0.99
MODEL_SAVE_PATH = "./mobilenet_v1_model/"
MODEL_NAME = "model.ckpt"
channels = 1

def train_MLP(mnist):
    x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input')
    y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')
    regularizer = tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE)

    y = mnist_inference.inference_MLP(x, regularizer)

    global_step = tf.Variable(0, trainable=False)

    tf.contrib.quantize.create_training_graph(quant_delay=100)

    variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
    variable_averages_op = variable_averages.apply(tf.trainable_variables())
    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'))
    learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE, global_step, mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY)
    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)

    with tf.control_dependencies([train_step, variable_averages_op]):
        train_op = tf.no_op(name='train')

    saver = tf.train.Saver()
    with tf.Session() as sess:
        tf.initialize_all_variables().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." % (step, loss_value))
                # print os.path.join(MODEL_SAVE_PATH, MODEL_NAME)
                saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)


def train_mobilenet(mnist):
    x = tf.placeholder(tf.float32, [None, mnist_inference.INPUT_NODE], name='x-input')
    y_ = tf.placeholder(tf.float32, [None, mnist_inference.OUTPUT_NODE], name='y-input')
    regularizer = tf.contrib.layers.l2_regularizer(REGULARAZTION_RATE)

    #mobilenet 把输入数据变成与w矩阵同纬度的
    x_image = tf.reshape(x, [-1,28,28,1])
    x_image = tf.image.resize_image_with_crop_or_pad(x_image, 28*4,28*4)
    y = mnist_inference.inference_mobilenet(x_image, regularizer)

    global_step = tf.Variable(0, trainable=False)

    variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
    variable_averages_op = variable_averages.apply(tf.trainable_variables())
    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'))
    learning_rate = tf.train.exponential_decay(LEARNING_RATE_BASE, global_step, mnist.train.num_examples / BATCH_SIZE, LEARNING_RATE_DECAY)
    train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss, global_step=global_step)

    with tf.control_dependencies([train_step, variable_averages_op]):
        train_op = tf.no_op(name='train')

    saver = tf.train.Saver()
    with tf.Session() as sess:
        tf.initialize_all_variables().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." % (step, loss_value))
                # print os.path.join(MODEL_SAVE_PATH, MODEL_NAME)
                saver.save(sess, os.path.join(MODEL_SAVE_PATH, MODEL_NAME), global_step=global_step)
            else:
                print("After %d training step(s), loss on training batch is %g." % (step, loss_value))

def main(argv=None):
    mnist = input_data.read_data_sets("../MNIST_data", one_hot=True)
    train_mobilenet(mnist)

if __name__ == '__main__':
    tf.app.run()

直接Python一定会报错，因为缺少一个文件mnist_inference.py，写下如下代码

#coding: utf-8
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import numpy as np
import tensorflow as tf

import mobilenet_v1

slim = tf.contrib.slim


#define the variables of nerual network
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

#define the forward network with MLPnet
def inference_MLP(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

#define the forward network with mobilenet_v1
def inference_mobilenet(input_tensor, regularizer):
    #inputs = tf.random_uniform((batch_size, height, width, 3))
    with slim.arg_scope([slim.conv2d, slim.separable_conv2d],
                      normalizer_fn=slim.batch_norm):
        logits, end_points = mobilenet_v1.mobilenet_v1(
            input_tensor,
            num_classes=OUTPUT_NODE,
            dropout_keep_prob=0.8,
            is_training=True,
            min_depth=8,
            depth_multiplier=1.0,
            conv_defs=None,
            prediction_fn=tf.contrib.layers.softmax,
            spatial_squeeze=True,
            reuse=None,
            scope='MobilenetV1',
            global_pool=False
        )

    return logits

[1] TensorFlow基础笔记(13) Mobilenet训练测试mnist数据