This repository shares VGG16 weights pre-trained by FractalDB (2020, Kataoka).
The implementation has been rewritten in TensorFlow based on the following GitHub repository: FractalDB-Pretrained-ResNet-PyTorch
The following are the differences from the original implementation:
- Dropout ratio is set to 0.2(The original was 0.8, but this value showed no loss reduction at all)
- Automatic Mixed Precision was used.
The code used for the training is shown in the train.py of this repository.
The training took about 30 hours with single RTX4090.
Loss curve(loss: 0.0400 - accuracy: 0.9894 at the 90 epoch):
The data(FractalDB-1k (1k categories x 1k instances; Total 1M images). [Dataset (13GB)]) used for training, downloaded from here:.
Reference:
@article{KataokaIJCV2022,
author={Kataoka, Hirokatsu and Okayasu, Kazushige and Matsumoto, Asato and Yamagata, Eisuke and Yamada, Ryosuke and Inoue, Nakamasa and Nakamura, Akio and Satoh, Yutaka},
title={Pre-training without Natural Images},
article={International Journal on Computer Vision (IJCV)},
year={2022},
}
@inproceedings{KataokaACCV2020,
author={Kataoka, Hirokatsu and Okayasu, Kazushige and Matsumoto, Asato and Yamagata, Eisuke and Yamada, Ryosuke and Inoue, Nakamasa and Nakamura, Akio and Satoh, Yutaka},
title={Pre-training without Natural Images},
booktitle={Asian Conference on Computer Vision (ACCV)},
year={2020},
}