cat dog

import tensorflow as tf
import numpy as np
import os
import math


def get_files(file_dir, ratio):
    '''''
    Args:
        file_dir: file directory
    Returns:
        list of images and labels
    '''
    cats = []
    label_cats = []
    dogs = []
    label_dogs = []
    for file in os.listdir(file_dir):
        name = file.split(sep='.')
        if name[0] == 'cat':
            cats.append(file_dir + file)
            label_cats.append(0)
        else:
            dogs.append(file_dir + file)
            label_dogs.append(1)
    print('There are %d cats\nThere are %d dogs' % (len(cats), len(dogs)))

    image_list = np.hstack((cats, dogs))
    label_list = np.hstack((label_cats, label_dogs))

    temp = np.array([image_list, label_list])
    temp = temp.transpose()
    np.random.shuffle(temp)

    all_image_list = temp[:, 0]
    all_label_list = temp[:, 1]

    n_sample = len(all_label_list)
    n_val = math.ceil(n_sample * ratio)  # number of validation samples
    n_train = n_sample - n_val  # number of trainning samples

    tra_images = all_image_list[0:n_train]
    tra_labels = all_label_list[0:n_train]
    tra_labels = [int(float(i)) for i in tra_labels]
    val_images = all_image_list[n_train:-1]
    val_labels = all_label_list[n_train:-1]
    val_labels = [int(float(i)) for i in val_labels]
    print("------------------------------")
    return tra_images, tra_labels, val_images, val_labels


def get_batch(image, label, image_W, image_H, batch_size, capacity):
    '''''
    Args:
        image: list type
        label: list type
        image_W: image width
        image_H: image height
        batch_size: batch size
        capacity: the maximum elements in queue
    Returns:
        image_batch: 4D tensor [batch_size, width, height, 3], dtype=tf.float32
        label_batch: 1D tensor [batch_size], dtype=tf.int32
    '''
    image = tf.cast(image, tf.string)
    label = tf.cast(label, tf.int32)

    # make an input queue
    input_queue = tf.train.slice_input_producer([image, label])

    label = input_queue[1]
    image_contents = tf.read_file(input_queue[0])  # input_queue[0] = /path/filename
    image = tf.image.decode_jpeg(image_contents, channels=3)

    ######################################
    # data argumentation should go to here
    ######################################
    image = tf.image.resize_image_with_crop_or_pad(image, image_W, image_H)
    # if you want to test the generated batches of images, you might want to comment the following line.
    image = tf.image.per_image_standardization(image)
    image_batch, label_batch = tf.train.batch([image, label],
                                              batch_size=batch_size,
                                              num_threads=64,
                                              capacity=capacity)

    label_batch = tf.reshape(label_batch, [batch_size])
    image_batch = tf.cast(image_batch, tf.float32)
    return image_batch, label_batch


# 进行推演
def inference(images, batch_size, n_classes):
    '''''Build the model
    Args:
        images: image batch, 4D tensor, tf.float32, [batch_size, width, height, channels]
    Returns:
        output tensor with the computed logits, float, [batch_size, n_classes]
    '''
    # conv1, shape = [kernel size, kernel size, channels, kernel numbers]

    with tf.variable_scope('conv1') as scope:
        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)

        # pool1 and norm1
    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')

        # conv2
    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')

        # local3
    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):
    '''''Compute loss from logits and labels
    Args:
        logits: logits tensor, float, [batch_size, n_classes]
        labels: label tensor, tf.int32, [batch_size]
    Returns:
        loss tensor of float type
    '''
    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):
    '''''Training ops, the Op returned by this function is what must be passed to
        'sess.run()' call to cause the model to train.
    Args:
        loss: loss tensor, from losses()
    Returns:
        train_op: The op for trainning
    '''
    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):
    """Evaluate the quality of the logits at predicting the label.
    Args:
      logits: Logits tensor, float - [batch_size, NUM_CLASSES].
      labels: Labels tensor, int32 - [batch_size], with values in the
        range [0, NUM_CLASSES).
    Returns:
      A scalar int32 tensor with the number of examples (out of batch_size)
      that were predicted correctly.
    """
    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


N_CLASSES = 2
IMG_W = 208  # resize the image, if the input image is too large, training will be very slow.
IMG_H = 208
RATIO = 0.2  # take 20% of dataset as validation data
BATCH_SIZE = 64
CAPACITY = 2000
MAX_STEP = 6000  # with current parameters, it is suggested to use MAX_STEP>10k
learning_rate = 0.0001  # with current parameters, it is suggested to use learning rate<0.0001


def run_training():
    # you need to change the directories to yours.
    train_dir = 'E:/imageDS/catDog/train/'
    logs_train_dir = 'E:/imageDS/catDog/'
    logs_val_dir = 'E:/imageDS/catDog/'
    train, train_label, val, val_label = get_files(train_dir, RATIO)
    train_batch, train_label_batch = get_batch(train,
                                               train_label,
                                               IMG_W,
                                               IMG_H,
                                               BATCH_SIZE,
                                               CAPACITY)
    val_batch, val_label_batch = get_batch(val,
                                           val_label,
                                           IMG_W,
                                           IMG_H,
                                           BATCH_SIZE,
                                           CAPACITY)

    logits = inference(train_batch, BATCH_SIZE, N_CLASSES)
    loss = losses(logits, train_label_batch)
    train_op = trainning(loss, learning_rate)
    acc = evaluation(logits, train_label_batch)

    x = tf.placeholder(tf.float32, shape=[BATCH_SIZE, IMG_W, IMG_H, 3])
    y_ = tf.placeholder(tf.int16, shape=[BATCH_SIZE])

    with tf.Session() as sess:
        saver = tf.train.Saver()
        sess.run(tf.global_variables_initializer())
        coord = tf.train.Coordinator()
        threads = tf.train.start_queue_runners(sess=sess, coord=coord)

        summary_op = tf.summary.merge_all()
        train_writer = tf.summary.FileWriter(logs_train_dir, sess.graph)
        val_writer = tf.summary.FileWriter(logs_val_dir, sess.graph)

        try:
            for step in np.arange(MAX_STEP):
                if coord.should_stop():
                    break

                tra_images, tra_labels = sess.run([train_batch, train_label_batch])
                _, tra_loss, tra_acc = sess.run([train_op, loss, acc],
                                                feed_dict={x: tra_images, y_: tra_labels})
                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)

                if step % 200 == 0 or (step + 1) == MAX_STEP:
                    val_images, val_labels = sess.run([val_batch, val_label_batch])
                    val_loss, val_acc = sess.run([loss, acc],
                                                 feed_dict={x: val_images, y_: val_labels})
                    print('**  Step %d, val loss = %.2f, val accuracy = %.2f%%  **' % (step, val_loss, val_acc * 100.0))
                    summary_str = sess.run(summary_op)
                    val_writer.add_summary(summary_str, step)

                if step % 2000 == 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()
        coord.join(threads)


run_training()