【笔记】tf中 tf.train.slice_input_producer 和 tf.train.batch 函数：前者每次从tensor列表取出一个tensor放入文件名队列；后者由此构建batch

slice_input_producer(tensor_list, num_epochs=None, shuffle=True, seed=None,
                         capacity=32, shared_name=None, name=None)

import tensorflow as tf
 
images = ['img1', 'img2', 'img3', 'img4', 'img5']
labels= [1,2,3,4,5]
 
epoch_num=8
 
f = tf.train.slice_input_producer([images, labels],num_epochs=None,shuffle=False)
 
with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(sess=sess, coord=coord)
    for i in range(epoch_num):
        k = sess.run(f)
        print '************************'
        print (i,k)
 
    coord.request_stop()
    coord.join(threads)

************************
(0, ['img1', 1])
************************
(1, ['img2', 2])
************************
(2, ['img3', 3])
************************
(3, ['img4', 4])
************************
(4, ['img5', 5])
************************
(5, ['img1', 1])
************************
(6, ['img2', 2])
************************
(7, ['img3', 3])

 

************************
(0, ['img5', 5])
************************
(1, ['img4', 4])
************************
(2, ['img1', 1])
************************
(3, ['img3', 3])
************************
(4, ['img2', 2])
************************
(5, ['img3', 3])
************************
(6, ['img2', 2])
************************
(7, ['img1', 1])

batch(tensors, batch_size, num_threads=1, capacity=32,
          enqueue_many=False, shapes=None, dynamic_pad=False,
          allow_smaller_final_batch=False, shared_name=None, name=None)

 

# -*- coding:utf-8 -*-
import tensorflow as tf
import numpy as np
 
# 样本个数
sample_num=5
# 设置迭代次数
epoch_num = 2
# 设置一个批次中包含样本个数
batch_size = 3
# 计算每一轮epoch中含有的batch个数
batch_total = int(sample_num/batch_size)+1
 
# 生成4个数据和标签
def generate_data(sample_num=sample_num):
    labels = np.asarray(range(0, sample_num))
    images = np.random.random([sample_num, 224, 224, 3])
    print('image size {},label size :{}'.format(images.shape, labels.shape))
 
    return images,labels
 
def get_batch_data(batch_size=batch_size):
    images, label = generate_data()
    # 数据类型转换为tf.float32
    images = tf.cast(images, tf.float32)
    label = tf.cast(label, tf.int32)
 
    #从tensor列表中按顺序或随机抽取一个tensor
    input_queue = tf.train.slice_input_producer([images, label], shuffle=False)
 
    image_batch, label_batch = tf.train.batch(input_queue, batch_size=batch_size, num_threads=1, capacity=64)
    return image_batch, label_batch
 
image_batch, label_batch = get_batch_data(batch_size=batch_size)
 
with tf.Session() as sess:
    coord = tf.train.Coordinator()
    threads = tf.train.start_queue_runners(sess, coord)
    try:
        for i in range(epoch_num):  # 每一轮迭代
            print '************'
            for j in range(batch_total): #每一个batch
                print '--------'
                # 获取每一个batch中batch_size个样本和标签
                image_batch_v, label_batch_v = sess.run([image_batch, label_batch])
                # for k in
                print(image_batch_v.shape, label_batch_v)
    except tf.errors.OutOfRangeError:
        print("done")
    finally:
        coord.request_stop()
    coord.join(threads)

************
--------
((3, 224, 224, 3), array([0, 1, 2], dtype=int32))
--------
((3, 224, 224, 3), array([3, 4, 0], dtype=int32))
************
--------
((3, 224, 224, 3), array([1, 2, 3], dtype=int32))
--------
((3, 224, 224, 3), array([4, 0, 1], dtype=int32))

************
--------
((2, 224, 224, 3), array([3, 0], dtype=int32))
--------
((2, 224, 224, 3), array([4, 1], dtype=int32))
--------
((2, 224, 224, 3), array([2, 3], dtype=int32))
************
--------
((2, 224, 224, 3), array([1, 0], dtype=int32))
--------
((2, 224, 224, 3), array([2, 4], dtype=int32))
--------
((2, 224, 224, 3), array([1, 4], dtype=int32))