#!/usr/bin/env python
# encoding: utf-8
'''
@author: lele Ye
@contact: 1750112338@qq.com
@software: pycharm 2018.2
@file: 13mnist.py
@time: 2018/12/17 10:23
@desc:
'''
import tensorflow as tf
import scipy.misc
import matplotlib.pyplot as plt
import random
 
# 读取图像可任意大小
filenames = ['./tianchi.jpg']
# 创建文件读取队列
filename_queue = tf.train.string_input_producer(filenames)
# 一个阅读器，读取整个文件，返回文件名称key,以及文件中所有的内容value
reader = tf.WholeFileReader()
# Returns the next record (key, value) pair produced by a reader
key, value = reader.read(filename_queue)
images = tf.image.decode_jpeg(value) # tf.image.decode_png(value)
target_width = target_height = 224
 
# 裁切图片
with tf.Session() as sess:
  # Coordinator的使用，用于多线程的协调
  coord = tf.train.Coordinator()
  # 启动所有graph收集到的队列运行器(queuerunners)
  threads = tf.train.start_queue_runners(coord=coord)
  height,width,channels = sess.run(tf.shape(images))
  offset_height = random.randint(0,height-target_height)
  offset_width = random.randint(0,width-target_width)
  reshapeimg = tf.image.crop_to_bounding_box(images, offset_height=offset_height, offset_width=offset_width,
                        target_height=target_height,target_width=target_width)
  print(type(reshapeimg)) # <class 'tensorflow.python.framework.ops.Tensor'>
  reimg1 = reshapeimg.eval() # reimg1的类型是<class 'numpy.ndarray'>
  scipy.misc.imsave('./crop.jpg', reimg1)
  plt.imshow(reimg1)
  plt.axis("off")
  plt.show()
  # 请求线程结束
  coord.request_stop()
  # 等待线程终止
  coord.join(threads)

train_datagen = ImageDataGenerator(
    rescale=1./255, #数据值除以255，[0-255] ->[0,1]
    shear_range=0.2, #剪切强度（逆时针方向的剪切角度，以度为单位）
    zoom_range=0.2, #随机缩放范围
    horizontal_flip=True) #水平翻转

test_datagen = ImageDataGenerator(rescale=1./255)

train_generator = train_datagen.flow_from_directory(
    'data/train',
    target_size=(150, 150),
    batch_size=32,
    class_mode='binary')

validation_generator = test_datagen.flow_from_directory(
    'data/validation',
    target_size=(150, 150),
    batch_size=32,
    class_mode='binary')

model.fit_generator(
    train_generator,
    steps_per_epoch=2000,
    epochs=50,
    validation_data=validation_generator,
    validation_steps=800)