---
license: mit
---

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](https://github.com/hirokatsukataoka16/FractalDB-Pretrained-ResNet-PyTorch/tree/main)

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):

![loss_curve_dropout02](./loss_curve_dropout02.png)

The data(FractalDB-1k (1k categories x 1k instances; Total 1M images). [Dataset (13GB)]) used for training, downloaded from [here:](https://hirokatsukataoka16.github.io/Pretraining-without-Natural-Images/). 

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},
}
```