Skip to content

A simple wrapper of TensorFlow for Converting, Importing (and Soon, Training) Images in tensorflow.

License

Notifications You must be signed in to change notification settings

HamedMP/ImageFlow

Repository files navigation

Notice - This version of imageflow is no longer under maintenance and major update is required.

The tensorflow version is too old and the library is not working as expected. You are welcome to add your use-cases in the Issues as Feature request to be considered in the new versions. Sorry for the inconvenience.

ImageFlow

A simple wrapper of TensorFlow for Converting, Importing (and Soon, Training) Images in tensorflow.

Installation:

pip install imageflow

Usage:

import imageflow

Convert a directory of images and their labels to .tfrecords

Just calling the following function will make a filename.tfrecords file in the directory converted_data in your projects root(where you call this method).

convert_images(images, labels, filename)

The images should be an array of shape [-1, height, width, channel] and has the same rows as the labels

Read distorted and normal data from .tfrecords in multi-thread manner:

# Distorted images for training
images, labels = distorted_inputs(filename='../my_data_raw/train.tfrecords', batch_size=FLAGS.batch_size,
                                      num_epochs=FLAGS.num_epochs,
                                      num_threads=5, imshape=[32, 32, 3], imsize=32)

# Normal images for validation
val_images, val_labels = inputs(filename='../my_data_raw/validation.tfrecords', batch_size=FLAGS.batch_size,
                                    num_epochs=FLAGS.num_epochs,
                                    num_threads=5, imshape=[32, 32, 3])

Dependencies:

  • TensorFlow ( => version 0.7.0)
  • Numpy
  • Pillow

About

A simple wrapper of TensorFlow for Converting, Importing (and Soon, Training) Images in tensorflow.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages