This is the implementation of "PixelCNN" for grayscale image.
Original paper: A. v. d. Oord, N. Kalchbrenner, and K. Kavukcuoglu. Pixel Recurrent Neural Networks. In Proceedings of The 33rd International Conference on Machine Learning, 2016. link

Please build the source file according to the procedure.

$ mkdir build
$ cd build
$ cmake ..
$ make -j4
$ cd ..

• THE MNIST DATABASE of handwritten digits
  This is the dataset of 28x28 grayscale for handwritten digits in 10 classes that has a training set of 60000 images and a test set of 10000 images.
  Link: official

Please create a link for the dataset.
The following hierarchical relationships are recommended.

datasets
|--Dataset1
|    |--train
|    |    |--image1.png
|    |    |--image2.bmp
|    |    |--image3.jpg
|    |
|    |--valid
|    |--test
|
|--Dataset2
|--Dataset3

You should substitute the path of training data for "<training_path>", test data for "<test_path>", respectively.
The following is an example for "MNIST".

$ cd datasets
$ mkdir MNIST
$ cd MNIST
$ ln -s <training_path> ./train
$ ln -s <test_path> ./test
$ cd ../..

Please set the shell for executable file.

$ vi scripts/train.sh

The following is an example of the training phase.
If you want to view specific examples of command line arguments, please view "src/main.cpp" or add "--help" to the argument.

#!/bin/bash

DATA='MNIST'

./PixelCNN-Gray \
    --train true \
    --epochs 300 \
    --dataset ${DATA} \
    --size 64 \
    --batch_size 16 \
    --gpu_id 0

Please execute the following to start the program.

$ sh scripts/train.sh

Please set the shell for executable file.

$ vi scripts/test.sh

The following is an example of the test phase.
If you want to view specific examples of command line arguments, please view "src/main.cpp" or add "--help" to the argument.

#!/bin/bash

DATA='MNIST'

./PixelCNN-Gray \
    --test true \
    --dataset ${DATA} \
    --size 64 \
    --gpu_id 0

Please execute the following to start the program.

$ sh scripts/test.sh

Please set the shell for executable file.

$ vi scripts/sample.sh

The following is an example of the sampling phase.
If you want to view specific examples of command line arguments, please view "src/main.cpp" or add "--help" to the argument.

#!/bin/bash

DATA='MNIST'

./PixelCNN-Gray \
    --sample true \
    --dataset ${DATA} \
    --sample_total 100 \
    --size 64 \
    --gpu_id 0

If you want to generate image, the above settings will work.

Please execute the following to start the program.

$ sh scripts/sample.sh