---
license: cc-by-4.0
datasets:
- Mitsua/color-multi-fractal-db-1k
tags:
- vision
- image-classification
library_name: transformers
---
# Model Card for Swin Base Multi Fractal 1k

Swin Transformer model pre-trained on Color Multi Fractal DB 1k (1 million images, 1k classes) at resolution 224x224 for 300 epochs, developed by [ELAN MITSUA Project](https://elanmitsua.com/en/) / Abstract Engine. 

This model is trained exclusively on 1 million fractal images which relies solely on mathematical formulas, so no real images or pretrained models are used for this training.

## Model Details

### Model Description

The Swin Transformer is a type of Vision Transformer and can be utilized for various downstream tasks.
It was introduced in the paper [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://arxiv.org/abs/2103.14030) by Liu et al. and first released in [this repository](https://github.com/microsoft/Swin-Transformer).

- **Developed by:** [ELAN MITSUA Project](https://elanmitsua.com/en/) / Abstract Engine
- **Model type:** Image Classification
- **License:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)

## Training Details

### Training Data

- [Color Multi Fractal DB 1k](https://huggingface.co/datasets/Mitsua/color-multi-fractal-db-1k) / CC BY 4.0
  - **Curated by:** [ELAN MITSUA Project](https://elanmitsua.com/en/) / Abstract Engine
  -  Paper: [Improving Fractal Pre-training](https://catalys1.github.io/fractal-pretraining/) by Connor Anderson and Ryan Farrell
  -  Code : [Multi-Fractal-Dataset](https://github.com/FYGitHub1009/Multi-Fractal-Dataset) by FYSignate1009