.png&w=640&q=75)
Swin-Small: Image Classification
Swin-Small is a lightweight variant of the Swin Transformer family, designed with a hierarchical Transformer architecture and shifted window attention. It computes attention within local windows and shifts them across layers to enable global context modeling efficiently. With fewer parameters and lower computational cost than Swin-Base, Swin-Small is suitable for deployment in resource-constrained environments while still achieving strong performance in tasks like image classification, object detection, and semantic segmentation.
Source model
- Input shape: 1x3x224x224
- Number of parameters: 47.31M
- Model size: 193.92M
- Output shape: 1x1000
The source model can be found here
Performance Reference
Please search model by model name in Model Farm
Inference & Model Conversion
Please search model by model name in Model Farm
License
Source Model: BSD-3-CLAUSE
Deployable Model: APLUX-MODEL-FARM-LICENSE
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support