TinySam
TinySAM 通过全阶段知识蒸馏、在线硬提示采样、量化等系列优化策略,构建轻量级 “万物分割” 模型,解决了原始 SAM 模型计算量大、部署困难的痛点,助力高效分割任务在资源受限场景下的应用。
Mirror Metadata
- Hugging Face repo: shadow-cann/hispark-modelzoo-tinysam
- Portal model id: i9t43v4pec00
- Created at: 2025-12-26 16:38:13
- Updated at: 2025-12-30 20:02:17
- Category: 计算机视觉
Framework
- PyTorch
Supported OS
- OpenHarmony
- Linux
Computing Power
- Hi3403V100 SVP_NNN
Tags
- 分割
Detail Parameters
- 输入: 448*448
- 参数量: 5.739M
- 计算量: 15.423GFLOPs
Files In This Repo
- prompt_encoder_deploy_model.onnx (源模型 / 源模型下载; 源模型 / 源模型元数据)
- image_encoder_deploy_model.onnx (源模型 / 源模型下载; 源模型 / 源模型元数据)
- tinysam.pth (源模型 / 源模型下载; 源模型 / 源模型元数据)
- mask_decoder_deploy_model.onnx (源模型 / 源模型下载; 源模型 / 源模型元数据)
- SVP_NNN_PC_V1.0.6.0.tgz (附加资源 / 附加资源)
Upstream Links
- Portal card: https://gitbubble.github.io/hisilicon-developer-portal-mirror/model-detail.html?id=i9t43v4pec00
- Upstream repository: https://gitee.com/HiSpark/modelzoo/tree/master/samples/built-in/segmentation/TinySam
- License reference: https://github.com/xinghaochen/TinySAM/blob/main/LICENSE
Notes
- This repository was mirrored from the HiSilicon Developer Portal model card and local downloads captured on 2026-03-27.
- File ownership follows the portal card mapping, not just filename similarity.
- Cover image: 1719774851694593_realquant_201909262051154_0.jpg
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support