🎨 Automatic Image Colorization using TensorFlow based on Residual Encoder Network
GPL-3.0 License
This is a TensorFlow implementation of the Residual Encoder Network based on Automatic Colorization and the pre-trained VGG16 model from https://github.com/machrisaa/tensorflow-vgg
For latest TensorFlow with estimator support, check tf-1.12 branch. (still under development, the training code is working now)
config.py
: config variables like batch size, training_iters and so onimage_helper.py
: all functions related to image manipulationread_input.py
: all functions related to inputresidual_encoder.py
: the residual encoder modelcommon.py
: the common part for training and testing, which is mainly the workflow for this modeltrain.py
: train the residual encoder model using TensorFlow built-in AdamOptimizertest.py
: test your own images and save the output imagesDownload pre-trained VGG16 model vgg16.npy to vgg folder
Option 1: Use pre-trained residual encoder model
summary_path
(you can change this path in config.py
)Option 2: Train your own model!
batch_size
and training_iters
if you want.training_dir
to your directory that has all your training jpg imagespython train.py
Test
testing_dir
to your directory that has all your testing jpg imagespython test.py
More example output images can be found in sample_output_images folder.
See CONTRIBUTING.md
GNU GPL 3.0 for personal or research use. COMMERCIAL USE PROHIBITED.