Image ATM is a one-click tool that automates the workflow of a typical image classification pipeline in an opinionated way, this includes:
- Preprocessing and validating input images and labels
- Starting/terminating cloud instance with GPU support
- Training
- Model evaluation
Read the documentation at: https://idealo.github.io/imageatm/
Image ATM is compatible with Python 3.6 and is distributed under the Apache 2.0 license.
There are two ways to install Image ATM:
- Install Image ATM from PyPI (recommended):
pip install imageatm
- Install Image ATM from the GitHub source:
git clone https://github.com/idealo/imageatm.git
cd imageatm
python setup.py install
Run this in your terminal
imageatm pipeline config/config_file.yml
Run the data preparation:
from imageatm.components import DataPrep
dp = DataPrep(
image_dir = 'sample_dataset/',
samples_file = 'sample_configfile.json',
job_dir='sample_jobdir/'
)
dp.run(resize=True)
Run the training:
from imageatm.components import Training
trainer = Training(dp.image_dir, dp.job_dir)
trainer.run()
Run the evaluation:
from imageatm.components import Evaluation
evaluater = Evaluation(image_dir=dp.image_dir, job_dir=dp.job_dir)
evaluater.run()
Please cite Image ATM in your publications if this is useful for your research. Here is an example BibTeX entry:
@misc{idealods2019imageatm,
title={Image ATM},
author={Christopher Lennan and Malgorzata Adamczyk and Gunar Maiwald and Dat Tran},
year={2019},
howpublished={\url{https://github.com/idealo/imageatm}},
}
- Christopher Lennan, github: clennan
- Malgorzata Adamczyk, github: gosia-malgosia
- Gunar Maiwald: github: gunarmaiwald
- Dat Tran, github: datitran
See LICENSE for details.
- We are currently using Keras 2.2. The plan is to use tf.keras once TF 2.0 is out. Currently tf.keras is buggy, especially with model saving/loading (tensorflow/tensorflow#22697)