TensorFlow基础笔记(13) Mobilenet训练测试mnist数据
主要是四个文件
mnist_train.py
#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) 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()
mnist_eval.py
#coding: utf-8 import time import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data import mnist_inference import mnist_train #every 10 sec load the newest model EVAL_INTERVAL_SECS = 10 def evaluate_MLP(mnist): with tf.Graph().as_default() as g: 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') validate_feed = {x: mnist.validation.images, y_: mnist.validation.labels} y = mnist_inference.inference(x, None) correcgt_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1)) accuracy = tf.reduce_mean(tf.cast(correcgt_prediction, tf.float32)) variable_averages = tf.train.ExponentialMovingAverage(mnist_train.MOVING_AVERAGE_DECAY) variable_to_restore = variable_averages.variables_to_restore() saver = tf.train.Saver(variable_to_restore) #while True: if 1: with tf.Session() as sess: ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH) if ckpt and ckpt.model_checkpoint_path: #load the model saver.restore(sess, ckpt.model_checkpoint_path) global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1] accuracy_score = sess.run(accuracy, feed_dict=validate_feed) print("After %s training steps, validation accuracy = %g" % (global_step, accuracy_score)) else: print('No checkpoint file found') return #time.sleep(EVAL_INTERVAL_SECS) def evaluate_mobilenet(mnist): with tf.Graph().as_default() as g: 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') #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, None) correcgt_prediction = tf.equal(tf.argmax(y, 1), tf.argmax(y_, 1)) accuracy = tf.reduce_mean(tf.cast(correcgt_prediction, tf.float32)) variable_averages = tf.train.ExponentialMovingAverage(mnist_train.MOVING_AVERAGE_DECAY) variable_to_restore = variable_averages.variables_to_restore() saver = tf.train.Saver(variable_to_restore) input = mnist.validation.images label = mnist.validation.labels batch_size = 100 TEST_STEPS = input.shape[0] / batch_size sum_accury = 0.0 #while True: if 1: with tf.Session() as sess: ckpt = tf.train.get_checkpoint_state(mnist_train.MODEL_SAVE_PATH) if ckpt and ckpt.model_checkpoint_path: #load the model saver.restore(sess, ckpt.model_checkpoint_path) global_step = ckpt.model_checkpoint_path.split('/')[-1].split('-')[-1] for i in range(int(TEST_STEPS)): input_batch = input[i*batch_size : (i + 1)*batch_size, :] label_batch = label[i*batch_size : (i + 1)*batch_size, :] validate_feed = {x: input_batch, y_: label_batch} # 取出部分数据测试 accuracy_score = sess.run(accuracy, feed_dict=validate_feed) sum_accury += accuracy_score print("test %s batch steps, validation accuracy = %g" % (i, accuracy_score)) else: print('No checkpoint file found') return #time.sleep(EVAL_INTERVAL_SECS) print("After %s training steps, all validation accuracy = %g" % (global_step, sum_accury / TEST_STEPS)) def main(argv=None): mnist = input_data.read_data_sets("../MNIST_data", one_hot=True) evaluate_mobilenet(mnist) if __name__ == '__main__': tf.app.run()
mnist_inference.py
#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
mobilenet_v1.py
从此处下载
https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet_v1.py
