Open-weight model
Classification-6Bands-Models
by Danesh Selwal DaneshSelwal/Classification-6Bands-Models
Classification-6Bands-Models is an open-weight model from Danesh Selwal, released under MIT License. Its published files total 1.2 GB.
This repository hosts deep neural network checkpoints trained on the 6-band hyperspectral benchmark dataset (330x307x6, 7 classes) for conformal uncertainty quantification and high-precision remote sensing classification.
Model Card
By Danesh Selwal, published under mit, revision b87d3c3b8117.
This repository hosts deep neural network checkpoints trained on the 6-band hyperspectral benchmark dataset (330x307x6, 7 classes) for conformal uncertainty quantification and high-precision remote sensing classification. - ViTUNet: Hybrid Vision Transformer and U-Net encoder-decoder architecture - baseline/models/AlexNetCNNbest.keras - baseline/models/GFNetbest.keras - baseline/models/ViTUNetbest.keras - baseline/models/AlexNetCNNfinal.keras - baseline/models/GFNetfinal.keras - baseline/models/ViTUNetfinal.keras
Read Danesh Selwal's full model card
6-Band Hyperspectral Classification Model Registry
This repository hosts deep neural network checkpoints trained on the 6-band hyperspectral benchmark dataset (330x307x6, 7 classes) for conformal uncertainty quantification and high-precision remote sensing classification.
Benchmark Architectures
- AlexNet CNN Backbone: 6-channel convolutional feature extractor
- GFNet (Global Filter Network): Frequency-domain 2D FFT global spatial interaction network
- ViT_UNet: Hybrid Vision Transformer and U-Net encoder-decoder architecture
Checkpoints Included
baseline/models/AlexNet_CNN_best.kerasbaseline/models/GFNet_best.kerasbaseline/models/ViT_UNet_best.kerasbaseline/models/AlexNet_CNN_final.kerasbaseline/models/GFNet_final.kerasbaseline/models/ViT_UNet_final.keras
Authors & Attribution
- Principal Author: Danesh Selwal (
[email protected]) - Co-authored by: Claude (
[email protected])
Identity and Version
- Repository
- DaneshSelwal/Classification-6Bands-Models
- Publisher
- Danesh Selwal
- Task
- Not stated by the source
- Modality
- Other
- Library
- keras
- Parameters
- Not stated by the source
- Languages
- en
- Revision
- b87d3c3b81171c9e33954f80cf26a9e7a4df8ca4
- First published
- 2026-10-12
- Last updated
- 2026-10-12
Files and Weights
8 files, 1.2 GB in total.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| README.md | Documentation | 1.2 KB | — |
| baseline/models/AlexNet_CNN_best.keras | Other | 272.1 MB | 4d9ba02e2084 |
| baseline/models/AlexNet_CNN_final.keras | Other | 272.1 MB | 46556c3ab353 |
| baseline/models/GFNet_best.keras | Other | 127.3 MB | 1ab7b52da065 |
| baseline/models/GFNet_final.keras | Other | 127.3 MB | 8ae8d61ebfe8 |
| baseline/models/ViT_UNet_best.keras | Other | 194.1 MB | 2a728f46618b |
| baseline/models/ViT_UNet_final.keras | Other | 194.1 MB | 57753555a812 |
| .gitattributes | Repository | 2.0 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
Released by Danesh Selwal through its official repository on Hugging Face. Read the license.
Questions About Classification-6Bands-Models
Can I use Classification-6Bands-Models commercially?
Yes. Classification-6Bands-Models is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.