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  : 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.

Python vs. C  : Memory Management and ControlPython vs. C : Memory Management and ControlApr 19, 2025 am 12:17 AM

Python and C have significant differences in memory management and control. 1. Python uses automatic memory management, based on reference counting and garbage collection, simplifying the work of programmers. 2.C requires manual management of memory, providing more control but increasing complexity and error risk. Which language to choose should be based on project requirements and team technology stack.

Python for Scientific Computing: A Detailed LookPython for Scientific Computing: A Detailed LookApr 19, 2025 am 12:15 AM

Python's applications in scientific computing include data analysis, machine learning, numerical simulation and visualization. 1.Numpy provides efficient multi-dimensional arrays and mathematical functions. 2. SciPy extends Numpy functionality and provides optimization and linear algebra tools. 3. Pandas is used for data processing and analysis. 4.Matplotlib is used to generate various graphs and visual results.

Python and C  : Finding the Right ToolPython and C : Finding the Right ToolApr 19, 2025 am 12:04 AM

Whether to choose Python or C depends on project requirements: 1) Python is suitable for rapid development, data science, and scripting because of its concise syntax and rich libraries; 2) C is suitable for scenarios that require high performance and underlying control, such as system programming and game development, because of its compilation and manual memory management.

Python for Data Science and Machine LearningPython for Data Science and Machine LearningApr 19, 2025 am 12:02 AM

Python is widely used in data science and machine learning, mainly relying on its simplicity and a powerful library ecosystem. 1) Pandas is used for data processing and analysis, 2) Numpy provides efficient numerical calculations, and 3) Scikit-learn is used for machine learning model construction and optimization, these libraries make Python an ideal tool for data science and machine learning.

Learning Python: Is 2 Hours of Daily Study Sufficient?Learning Python: Is 2 Hours of Daily Study Sufficient?Apr 18, 2025 am 12:22 AM

Is it enough to learn Python for two hours a day? It depends on your goals and learning methods. 1) Develop a clear learning plan, 2) Select appropriate learning resources and methods, 3) Practice and review and consolidate hands-on practice and review and consolidate, and you can gradually master the basic knowledge and advanced functions of Python during this period.

Python for Web Development: Key ApplicationsPython for Web Development: Key ApplicationsApr 18, 2025 am 12:20 AM

Key applications of Python in web development include the use of Django and Flask frameworks, API development, data analysis and visualization, machine learning and AI, and performance optimization. 1. Django and Flask framework: Django is suitable for rapid development of complex applications, and Flask is suitable for small or highly customized projects. 2. API development: Use Flask or DjangoRESTFramework to build RESTfulAPI. 3. Data analysis and visualization: Use Python to process data and display it through the web interface. 4. Machine Learning and AI: Python is used to build intelligent web applications. 5. Performance optimization: optimized through asynchronous programming, caching and code

Python vs. C  : Exploring Performance and EfficiencyPython vs. C : Exploring Performance and EfficiencyApr 18, 2025 am 12:20 AM

Python is better than C in development efficiency, but C is higher in execution performance. 1. Python's concise syntax and rich libraries improve development efficiency. 2.C's compilation-type characteristics and hardware control improve execution performance. When making a choice, you need to weigh the development speed and execution efficiency based on project needs.

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

AI Hentai Generator

AI Hentai Generator

Generate AI Hentai for free.

Hot Tools

MantisBT

MantisBT

Mantis is an easy-to-deploy web-based defect tracking tool designed to aid in product defect tracking. It requires PHP, MySQL and a web server. Check out our demo and hosting services.

SublimeText3 Linux new version

SublimeText3 Linux new version

SublimeText3 Linux latest version

SublimeText3 Chinese version

SublimeText3 Chinese version

Chinese version, very easy to use

Atom editor mac version download

Atom editor mac version download

The most popular open source editor

SublimeText3 Mac version

SublimeText3 Mac version

God-level code editing software (SublimeText3)