MAE

MAE

This is the implementation of "Masked Autoencoder".
Original paper: K. He, X. Chen, S. Xie, Y. Li, P. Dollár, and R. Girshick. Masked Autoencoders Are Scalable Vision Learners. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2022. link

Usage

1. Build

Please build the source file according to the procedure.

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

2. Dataset Setting

Recommendation

• Large-scale CelebFaces Attributes (CelebA) Dataset
  This is a large-scale face attributes dataset with more than 200K celebrity images, each with 40 attribute annotations.
  Link: official

Setting

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 "celebA".

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

3. Training

Setting

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='celebA'

./AE2d \
    --train true \
    --epochs 300 \
    --dataset ${DATA} \
    --size 224 \
    --batch_size 16 \
    --gpu_id 0 \
    --nc 3

Run

Please execute the following to start the program.

$ sh scripts/train.sh

4. Test

Setting

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='celebA'

./AE2d \
    --test true \
    --dataset ${DATA} \
    --test_dir "test" \
    --size 224 \
    --gpu_id 0 \
    --nc 3

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

Run

Please execute the following to start the program.

$ sh scripts/test.sh

Acknowledgments

This code is inspired by mae.