Downloads · 30 days
11
2% of all-time downloads
swin-base-multi-fractal-1k
Mitsua/swin-base-multi-fractal-1k
swin-base-multi-fractal-1k is a image classification model from Mitsua. Use it when you need a label for an image. It is set up for transformers. The card lists the license as cc-by-4.0.
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 / Abstract Engine.
All-time downloads
712
Public
Parameters
87.8M
703 MB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.bin352 MB · 50%
Parameter types
How the weights are stored.
F3287.8M · 100%
Datasets
Model card
From the Hugging Face model README
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 / 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 by Liu et al. and first released in this repository.
- Developed by: ELAN MITSUA Project / Abstract Engine
- Model type: Image Classification
- License: CC BY 4.0
Training Details
Training Data
- Color Multi Fractal DB 1k / CC BY 4.0
- Curated by: ELAN MITSUA Project / Abstract Engine
- Paper: Improving Fractal Pre-training by Connor Anderson and Ryan Farrell
- Code : Multi-Fractal-Dataset by FYSignate1009
- Task
- Image Classification
- Library
- transformers
- Type
- swin
- License
- cc-by-4.0
- Created
- Aug 29, 2024
- Updated
- Sep 5, 2024