README.md

---
library_name: pytorch
---

![swinv2_logo](resource/SwinV2.png)

Swin Transformer V2 extends the original Swin Transformer with improved attention scaling and positional encoding, enabling stable training and strong performance on very large and high-resolution vision datasets.

Original paper: [Swin Transformer V2: Scaling Up Capacity and Resolution](https://arxiv.org/abs/2111.09883)

# Swin Transformer V2-Tiny

This model uses the Swin Transformer V2-Tiny variant, a compact hierarchical transformer that applies shifted window self-attention for efficient computation. It is well suited for high-resolution image classification and as a backbone for dense vision tasks such as detection and segmentation.

Model Configuration:
- Reference implementation: [torchvision.models.swin_v2_t](https://pytorch.org/vision/0.20/models/swin_transformer.html)
- Original Weight: [Swin_V2_T_Weights.IMAGENET1K_V1](https://download.pytorch.org/models/swin_v2_t-b137f0e2.pth)
- Resolution: 3x256x256
- Support Cooper version:
    - Cooper SDK: [2.5.2]
    - Cooper Foundry: [2.2]

| Model | Device | Model Link |
| :-----: | :-----: | :-----: |
| SwinV2-Tiny | N1-655 | [Model_Link](https://huggingface.co/Ambarella/SwinV2/blob/main/n1-655_swin_tiny_v2.bin) |
| SwinV2-Tiny | CV72 | [Model_Link](https://huggingface.co/Ambarella/SwinV2/blob/main/cv72_swin_tiny_v2.bin) |
| SwinV2-Tiny | CV75 | [Model_Link](https://huggingface.co/Ambarella/SwinV2/blob/main/cv75_swin_tiny_v2.bin) |