search
HomeBackend DevelopmentPython TutorialAbout the tf.train.batch function in Tensorflow

About the tf.train.batch function in Tensorflow

Apr 24, 2018 pm 02:13 PM
tensorflowfunction

This article mainly introduces the use of the tf.train.batch function in Tensorflow. Now I will share it with you and give you a reference. Let's take a look together

I have been looking at the queue for reading data in tensorflow for the past two days. To be honest, it is really difficult to understand. Maybe I have no experience in this area before. I used Theano at the beginning and wrote everything myself. After these two days of reviewing documents and related information, I also consulted with junior fellow students in China. I have a little bit of a feeling today. To put it simply, the calculation graph reads data from a pipeline. The input pipeline uses a ready-made method, and the same is used for reading. In order to ensure that reading data from a pipe will not be messy when using multiple threads, thread management-related operations are required when reading at this time. Today I did a simple operation in the lab, which was to give an ordered data and see if it was ordered. It turned out that it was in order, so I gave the code directly:

import tensorflow as tf
import numpy as np

def generate_data():
  num = 25
  label = np.asarray(range(0, num))
  images = np.random.random([num, 5, 5, 3])
  print('label size :{}, image size {}'.format(label.shape, images.shape))
  return label, images

def get_batch_data():
  label, images = generate_data()
  images = tf.cast(images, tf.float32)
  label = tf.cast(label, tf.int32)
  input_queue = tf.train.slice_input_producer([images, label], shuffle=False)
  image_batch, label_batch = tf.train.batch(input_queue, batch_size=10, num_threads=1, capacity=64)
  return image_batch, label_batch

image_batch, label_batch = get_batch_data()
with tf.Session() as sess:
  coord = tf.train.Coordinator()
  threads = tf.train.start_queue_runners(sess, coord)
  i = 0
  try:
    while not coord.should_stop():
      image_batch_v, label_batch_v = sess.run([image_batch, label_batch])
      i += 1
      for j in range(10):
        print(image_batch_v.shape, label_batch_v[j])
  except tf.errors.OutOfRangeError:
    print("done")
  finally:
    coord.request_stop()
  coord.join(threads)

Remember the slice_input_producer method, which requires shuffle by default.

Besides, I would like to comment this code.

1: there is a parameter 'num_epochs' in slice_input_producer, which controls how many epochs the slice_input_producer method would work. when this method runs the specified epochs, it would report the OutOfRangeRrror. I think it would be useful for our control the training epochs.

2: the output of this method is one single image, we could operate this single image with tensorflow API, such as normalization, crops, and so on, then this single image is feed to batch method, a batch of images for training or testing wouldbe received.

tf The difference between .train.batch and tf.train.shuffle_batch

tf.train.batch([example, label], batch_size=batch_size, capacity=capacity): [example, label ] represents a sample and a sample label, which can be a sample and a sample label, and batch_size is the number of samples in a batch sample set returned. capacity is the capacity in the queue. This is mainly combined into a batch in order

tf.train.shuffle_batch([example, label], batch_size=batch_size, capacity=capacity, min_after_dequeue). The parameters here have the same meaning as above. The difference is the parameter min_after_dequeue. You must ensure that this parameter is smaller than the value of the capacity parameter, otherwise an error will occur. This means that when the elements in the queue are larger than it, a disordered batch will be output. In other words, the output result of this function is a batch of samples arranged out of order, not arranged in order.

The above function return values ​​are all samples and sample labels of a batch, but one is in order and the other is random

Related recommendations:

tensorflow How to use flags to define command line parameters

Usage of Tensorflow's Saver

The above is the detailed content of About the tf.train.batch function in Tensorflow. For more information, please follow other related articles on the PHP Chinese website!

Statement
The content of this article is voluntarily contributed by netizens, and the copyright belongs to the original author. This site does not assume corresponding legal responsibility. If you find any content suspected of plagiarism or infringement, please contact admin@php.cn
Python vs. C  : Understanding the Key DifferencesPython vs. C : Understanding the Key DifferencesApr 21, 2025 am 12:18 AM

Python and C each have their own advantages, and the choice should be based on project requirements. 1) Python is suitable for rapid development and data processing due to its concise syntax and dynamic typing. 2)C is suitable for high performance and system programming due to its static typing and manual memory management.

Python vs. C  : Which Language to Choose for Your Project?Python vs. C : Which Language to Choose for Your Project?Apr 21, 2025 am 12:17 AM

Choosing Python or C depends on project requirements: 1) If you need rapid development, data processing and prototype design, choose Python; 2) If you need high performance, low latency and close hardware control, choose C.

Reaching Your Python Goals: The Power of 2 Hours DailyReaching Your Python Goals: The Power of 2 Hours DailyApr 20, 2025 am 12:21 AM

By investing 2 hours of Python learning every day, you can effectively improve your programming skills. 1. Learn new knowledge: read documents or watch tutorials. 2. Practice: Write code and complete exercises. 3. Review: Consolidate the content you have learned. 4. Project practice: Apply what you have learned in actual projects. Such a structured learning plan can help you systematically master Python and achieve career goals.

Maximizing 2 Hours: Effective Python Learning StrategiesMaximizing 2 Hours: Effective Python Learning StrategiesApr 20, 2025 am 12:20 AM

Methods to learn Python efficiently within two hours include: 1. Review the basic knowledge and ensure that you are familiar with Python installation and basic syntax; 2. Understand the core concepts of Python, such as variables, lists, functions, etc.; 3. Master basic and advanced usage by using examples; 4. Learn common errors and debugging techniques; 5. Apply performance optimization and best practices, such as using list comprehensions and following the PEP8 style guide.

Choosing Between Python and C  : The Right Language for YouChoosing Between Python and C : The Right Language for YouApr 20, 2025 am 12:20 AM

Python is suitable for beginners and data science, and C is suitable for system programming and game development. 1. Python is simple and easy to use, suitable for data science and web development. 2.C provides high performance and control, suitable for game development and system programming. The choice should be based on project needs and personal interests.

Python vs. C  : A Comparative Analysis of Programming LanguagesPython vs. C : A Comparative Analysis of Programming LanguagesApr 20, 2025 am 12:14 AM

Python is more suitable for data science and rapid development, while C is more suitable for high performance and system programming. 1. Python syntax is concise and easy to learn, suitable for data processing and scientific computing. 2.C has complex syntax but excellent performance and is often used in game development and system programming.

2 Hours a Day: The Potential of Python Learning2 Hours a Day: The Potential of Python LearningApr 20, 2025 am 12:14 AM

It is feasible to invest two hours a day to learn Python. 1. Learn new knowledge: Learn new concepts in one hour, such as lists and dictionaries. 2. Practice and exercises: Use one hour to perform programming exercises, such as writing small programs. Through reasonable planning and perseverance, you can master the core concepts of Python in a short time.

Python vs. C  : Learning Curves and Ease of UsePython vs. C : Learning Curves and Ease of UseApr 19, 2025 am 12:20 AM

Python is easier to learn and use, while C is more powerful but complex. 1. Python syntax is concise and suitable for beginners. Dynamic typing and automatic memory management make it easy to use, but may cause runtime errors. 2.C provides low-level control and advanced features, suitable for high-performance applications, but has a high learning threshold and requires manual memory and type safety management.

See all articles

Hot AI Tools

Undresser.AI Undress

Undresser.AI Undress

AI-powered app for creating realistic nude photos

AI Clothes Remover

AI Clothes Remover

Online AI tool for removing clothes from photos.

Undress AI Tool

Undress AI Tool

Undress images for free

Clothoff.io

Clothoff.io

AI clothes remover

Video Face Swap

Video Face Swap

Swap faces in any video effortlessly with our completely free AI face swap tool!

Hot Tools

DVWA

DVWA

Damn Vulnerable Web App (DVWA) is a PHP/MySQL web application that is very vulnerable. Its main goals are to be an aid for security professionals to test their skills and tools in a legal environment, to help web developers better understand the process of securing web applications, and to help teachers/students teach/learn in a classroom environment Web application security. The goal of DVWA is to practice some of the most common web vulnerabilities through a simple and straightforward interface, with varying degrees of difficulty. Please note that this software

VSCode Windows 64-bit Download

VSCode Windows 64-bit Download

A free and powerful IDE editor launched by Microsoft

SublimeText3 Mac version

SublimeText3 Mac version

God-level code editing software (SublimeText3)

SAP NetWeaver Server Adapter for Eclipse

SAP NetWeaver Server Adapter for Eclipse

Integrate Eclipse with SAP NetWeaver application server.

Dreamweaver Mac version

Dreamweaver Mac version

Visual web development tools