Learning Tensorflow(4)---使用Lenet測試Mnist

模型定義文件
 

import tensorflow as tf

INPUT_NODE = 784
OUTPUT_NODE = 10
IMAGE_SIZE = 28
NUM_CHANNELS = 1
NUM_LABELS = 10
CONV1_DEEP = 32
CONV1_SIZE = 5
CONV2_DEEP = 64
CONV2_SIZE = 5
FC_SIZE = 512


tf.reset_default_graph()
def inference(input_tensor, train, regularizer):
    with tf.variable_scope('layer1-conv1'):
        conv1_weights = tf.get_variable("weight", [CONV1_SIZE, CONV1_SIZE, NUM_CHANNELS, CONV1_DEEP],initializer=tf.truncated_normal_initializer(stddev=0.1))
        conv1_biases = tf.get_variable("bias", [CONV1_DEEP], initializer=tf.constant_initializer(0.0))
        x = tf.reshape(input_tensor, [-1, 28, 28, 1])
        conv1 = tf.nn.conv2d(x, conv1_weights, strides=[1, 1, 1, 1], padding='SAME')
        relu1 = tf.nn.relu(tf.nn.bias_add(conv1, conv1_biases))
    with tf.name_scope("layer2-pool1"):
        pool1 = tf.nn.max_pool(relu1, ksize = [1,2,2,1],strides=[1,2,2,1],padding="SAME")
    with tf.variable_scope("layer3-conv2"):
        conv2_weights = tf.get_variable(
            "weight", [CONV2_SIZE, CONV2_SIZE, CONV1_DEEP, CONV2_DEEP],
            initializer=tf.truncated_normal_initializer(stddev=0.1))
        conv2_biases = tf.get_variable("bias", [CONV2_DEEP], initializer=tf.constant_initializer(0.0))
        conv2 = tf.nn.conv2d(pool1, conv2_weights, strides=[1, 1, 1, 1], padding='SAME')
        relu2 = tf.nn.relu(tf.nn.bias_add(conv2, conv2_biases))
    with tf.name_scope("layer4-pool2"):
        pool2 = tf.nn.max_pool(relu2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
    with tf.variable_scope('layer5-fc1'):
        fc1_weights = tf.get_variable("weight", [7 * 7 * 64, FC_SIZE],                                      initializer=tf.truncated_normal_initializer(stddev=0.1))
        if regularizer != None: tf.add_to_collection('losses', regularizer(fc1_weights))
        fc1_biases = tf.get_variable("bias", [FC_SIZE], initializer=tf.constant_initializer(0.1))
        pool2_vector = tf.reshape(pool2, [-1, 7 * 7 * 64])
        fc1 = tf.nn.relu(tf.matmul(pool2_vector, fc1_weights) + fc1_biases)
        if train: fc1 = tf.nn.dropout(fc1, 0.5)
    with tf.variable_scope('layer6-fc2'):
        fc2_weights = tf.get_variable("weight", [FC_SIZE, NUM_LABELS],                                      initializer=tf.truncated_normal_initializer(stddev=0.1))
        if regularizer != None: tf.add_to_collection('losses', regularizer(fc2_weights))
        fc2_biases = tf.get_variable("bias", [NUM_LABELS], initializer=tf.constant_initializer(0.1))
        logit = tf.matmul(fc1, fc2_weights) + fc2_biases
return logit

訓練文件

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import LeNet5_infernece
import os
import numpy as np


BATCH_SIZE = 100
LEARNING_RATE_BASE = 0.01
LEARNING_RATE_DECAY = 0.99
REGULARIZATION_RATE = 0.0001
TRAINING_STEPS = 10000
MOVING_AVERAGE_DECAY = 0.99


def train(mnist):
    # 定義輸出爲4維矩陣的placeholder
    x = tf.placeholder(tf.float32, [None, LeNet5_infernece.INPUT_NODE],name='x-input')
    y_ = tf.placeholder(tf.float32, [None, LeNet5_infernece.OUTPUT_NODE], name='y-input')

   
    regularizer = tf.contrib.layers.l2_regularizer(REGULARIZATION_RATE)
    y = LeNet5_infernece.inference(x,False,regularizer)
    global_step = tf.Variable(0, trainable=False)

    # 定義損失函數、學習率、滑動平均操作以及訓練過程。
    variable_averages = tf.train.ExponentialMovingAverage(MOVING_AVERAGE_DECAY, global_step)
    variables_averages_op = variable_averages.apply(tf.trainable_variables())
    cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.argmax(y_, 1), logits=y)
    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,
        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')

    predict_labels = tf.argmax(y, 1, "output")
    correction_prediction = tf.equal(predict_labels, tf.argmax(y_,1))
    accuracy = tf.reduce_mean(tf.cast(correction_prediction, tf.float32))

    # 初始化TensorFlow持久化類。
    saver = tf.train.Saver()
    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." % (step, loss_value))
                train_accuracy = accuracy.eval(feed_dict={x:xs,y_:ys})
                print("test accuracy %g"%train_accuracy)

            if i == TRAINING_STEPS-1:
                saver.save(sess, "./model.ckpt")
                constant_graph = tf.graph_util.convert_variables_to_constants(sess, sess.graph_def, ["output"])
                with tf.gfile.FastGFile("model.pb", mode='wb') as f:
                    f.write(constant_graph.SerializeToString())
                    print("save model")

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

if __name__ == '__main__':
    main()

 

測試

import tensorflow as tf
import  numpy as np
import PIL.Image as Image
from skimage import io, transform

IMAGE_PATH = "8.bmp"
MODEL_PATH = "model.pb"

def Predict():
    with tf.Graph().as_default():
        output_graph_def = tf.GraphDef()
        with open(MODEL_PATH, "rb") as f:
            output_graph_def.ParseFromString(f.read())
            _ = tf.import_graph_def(output_graph_def, name="")

        with tf.Session() as sess:

            init = tf.global_variables_initializer()
            sess.run(init)

            input_x = sess.graph.get_tensor_by_name("x-input:0")
            print(input_x)
            #out_softmax = sess.graph.get_tensor_by_name("softmax:0")
            #print(out_softmax)
            out_label = sess.graph.get_tensor_by_name("output:0")
            print(out_label)

            img = io.imread(IMAGE_PATH)
            img = transform.resize(img, (28, 28, 1))
            img_out_softmax = sess.run(out_label, feed_dict={input_x:np.reshape(img, [-1,784])})


            print("img_out_softmax:",img_out_softmax)
            prediction_labels = np.argmax(img_out_softmax, axis=0)
            print("label:",prediction_labels)

def main(argv=None):
    Predict()

if __name__ == '__main__':
    main()