Tensorflow(三)训练自己的数据，分块版本

1.model.py

import tensorflow as tf


def inference(images, batch_size, n_classes):
    with tf.variable_scope('conv1') as scope:
        # 卷积盒的为 3*3 的卷积盒，图片厚度是3，输出是16个featuremap
        weights = tf.get_variable('weights',
                                  shape=[3, 3, 3, 16],
                                  dtype=tf.float32,
                                  initializer=tf.truncated_normal_initializer(stddev=0.1, dtype=tf.float32))
        biases = tf.get_variable('biases',
                                 shape=[16],
                                 dtype=tf.float32,
                                 initializer=tf.constant_initializer(0.1))
        conv = tf.nn.conv2d(images, weights, strides=[1, 1, 1, 1], padding='SAME')
        pre_activation = tf.nn.bias_add(conv, biases)
        conv1 = tf.nn.relu(pre_activation, name=scope.name)

    with tf.variable_scope('pooling1_lrn') as scope:
        pool1 = tf.nn.max_pool(conv1, ksize=[1, 3, 3, 1], strides=[1, 2, 2, 1], padding='SAME', name='pooling1')
        norm1 = tf.nn.lrn(pool1, depth_radius=4, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name='norm1')

    with tf.variable_scope('conv2') as scope:
        weights = tf.get_variable('weights',
                                  shape=[3, 3, 16, 16],
                                  dtype=tf.float32,
                                  initializer=tf.truncated_normal_initializer(stddev=0.1, dtype=tf.float32))
        biases = tf.get_variable('biases',
                                 shape=[16],
                                 dtype=tf.float32,
                                 initializer=tf.constant_initializer(0.1))
        conv = tf.nn.conv2d(norm1, weights, strides=[1, 1, 1, 1], padding='SAME')
        pre_activation = tf.nn.bias_add(conv, biases)
        conv2 = tf.nn.relu(pre_activation, name='conv2')

        # pool2 and norm2
    with tf.variable_scope('pooling2_lrn') as scope:
        norm2 = tf.nn.lrn(conv2, depth_radius=4, bias=1.0, alpha=0.001 / 9.0, beta=0.75, name='norm2')
        pool2 = tf.nn.max_pool(norm2, ksize=[1, 3, 3, 1], strides=[1, 1, 1, 1], padding='SAME', name='pooling2')

    with tf.variable_scope('local3') as scope:
        reshape = tf.reshape(pool2, shape=[batch_size, -1])
        dim = reshape.get_shape()[1].value
        weights = tf.get_variable('weights',
                                  shape=[dim, 128],
                                  dtype=tf.float32,
                                  initializer=tf.truncated_normal_initializer(stddev=0.005, dtype=tf.float32))
        biases = tf.get_variable('biases',
                                 shape=[128],
                                 dtype=tf.float32,
                                 initializer=tf.constant_initializer(0.1))
    local3 = tf.nn.relu(tf.matmul(reshape, weights) + biases, name=scope.name)

    # local4
    with tf.variable_scope('local4') as scope:
        weights = tf.get_variable('weights',
                                  shape=[128, 128],
                                  dtype=tf.float32,
                                  initializer=tf.truncated_normal_initializer(stddev=0.005, dtype=tf.float32))
        biases = tf.get_variable('biases',
                                 shape=[128],
                                 dtype=tf.float32,
                                 initializer=tf.constant_initializer(0.1))
        local4 = tf.nn.relu(tf.matmul(local3, weights) + biases, name='local4')

        # softmax
    with tf.variable_scope('softmax_linear') as scope:
        weights = tf.get_variable('softmax_linear',
                                  shape=[128, n_classes],
                                  dtype=tf.float32,
                                  initializer=tf.truncated_normal_initializer(stddev=0.005, dtype=tf.float32))
        biases = tf.get_variable('biases',
                                 shape=[n_classes],
                                 dtype=tf.float32,
                                 initializer=tf.constant_initializer(0.1))
        softmax_linear = tf.add(tf.matmul(local4, weights), biases, name='softmax_linear')

    return softmax_linear


def losses(logits, labels):
    with tf.variable_scope('loss') as scope:
        cross_entropy = tf.nn.sparse_softmax_cross_entropy_with_logits \
            (logits=logits, labels=labels, name='xentropy_per_example')
        loss = tf.reduce_mean(cross_entropy, name='loss')
        tf.summary.scalar(scope.name + '/loss', loss)
    return loss


def trainning(loss, learning_rate):
    with tf.name_scope('optimizer'):
        optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
        global_step = tf.Variable(0, name='global_step', trainable=False)
        train_op = optimizer.minimize(loss, global_step=global_step)
    return train_op


def evaluation(logits, labels):
    with tf.variable_scope('accuracy') as scope:
        correct = tf.nn.in_top_k(logits, labels, 1)
        correct = tf.cast(correct, tf.float16)
        accuracy = tf.reduce_mean(correct)
        tf.summary.scalar(scope.name + '/accuracy', accuracy)
    return accuracy

---

2.ReadMyOwnData.py

import numpy as np
import tensorflow as tf



def read_and_decode(filename):  # 读入tfrecords
    filename_queue = tf.train.string_input_producer([filename])  # 生成一个queue队列

    reader = tf.TFRecordReader()
    _, serialized_example = reader.read(filename_queue)  # 返回文件名和文件
    features = tf.parse_single_example(
        serialized_example,
        features={
            'label': tf.FixedLenFeature([], tf.int64),
            'img_raw': tf.FixedLenFeature([], tf.string),
        }
    )  # 将image数据和label取出来

    image = tf.decode_raw(features['img_raw'], tf.uint8)
    image = tf.reshape(image, [128, 128, 3])
    image = tf.cast(image, tf.float32) * (1. / 255) - 0.5    #归一化
    label = tf.cast(features['label'], tf.int32)

    return image, label

---

3.just_train.py

import tensorflow as tf
import numpy as np
import os
import ReadMyOwnData
import model


n_classes = 2 #猫和狗
image_W = 128  # resize图像，太大的话训练时间久
image_H = 128
batch_size = 4
CAPACITY = 256
MAX_STEP = 1000 # 一般大于10K
learning_rate = 0.001 # 一般小于0.0001

train_dir = '/home/cae_b8/Documents/project2/data_set/train/'
logs_train_dir = '/home/cae_b8/Documents/project2/data_set/train/log/'

train_record_path = '/home/cae_b8/Documents/project2/data_set/train/train.tfrecords'
test_record_path = '/home/cae_b8/Documents/project2/data_set/train/test.tfrecords'
train_images, train_labels = ReadMyOwnData.read_and_decode(train_record_path)
#test_images, test_labels = ReadMyOwnData.read_and_decode(test_record_path)
train_batch, train_label_batch = tf.train.batch([train_images, train_labels],
                                                batch_size=batch_size, capacity=128)

#test_batch, test_label_batch = tf.train.batch([test_images, test_labels],
                                                batch_size=1, capacity=128)


train_logits = model.inference(train_batch, batch_size, n_classes)
train_loss = model.losses(train_logits, train_label_batch)
train_op = model.trainning(train_loss, learning_rate)
train_acc = model.evaluation(train_logits, train_label_batch)
summary_op = tf.summary.merge_all() #这个是log汇总记录

sess = tf.Session()
train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph)
saver = tf.train.Saver()
sess.run(tf.global_variables_initializer())

coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)

try:
    #执行MAX_STEP步的训练，一步一个batch
    for step in np.arange(MAX_STEP):
        if coord.should_stop():
                break
        #启动以下操作节点，有个疑问，为什么train_logits在这里没有开启？
        _, tra_loss, tra_acc = sess.run([train_op, train_loss, train_acc])
        #每隔50步打印一次当前的loss以及acc，同时记录log，写入writer
        if step % 50 == 0:
            print('Step %d, train loss = %.2f, train accuracy = %.2f%%' %(step, tra_loss, tra_acc*100.0))
            summary_str = sess.run(summary_op)
            train_writer.add_summary(summary_str, step)
        #每隔2000步，保存一次训练好的模型
        if step % 200 == 0 or (step + 1) == MAX_STEP:
            checkpoint_path = os.path.join(logs_train_dir, 'model.ckpt')
            saver.save(sess, checkpoint_path, global_step=step)

except tf.errors.OutOfRangeError:
    print('Done training -- epoch limit reached')
finally:
    coord.request_stop()