|
|
--- |
|
|
license: other |
|
|
license_name: aplux-model-farm-license |
|
|
license_link: https://aiot.aidlux.com/api/v1/files/license/model_farm_license_en.pdf |
|
|
pipeline_tag: image-segmentation |
|
|
tags: |
|
|
- AIoT |
|
|
- QNN |
|
|
--- |
|
|
|
|
|
 |
|
|
|
|
|
## FFNet-40S: Semantic Segmentation |
|
|
|
|
|
FFNet-40S is a lightweight model in the FFNet (Fully Connected Feature Pyramid Network) family, primarily designed for efficient object detection and feature extraction tasks. FFNet utilizes a Feature Pyramid Network (FPN) structure to extract rich, multi-scale features from images, improving the accuracy of object detection. FFNet-40S is the lightweight version, optimized for reduced computational resources, making it suitable for real-time inference on edge devices or mobile platforms. It strikes a good balance between accuracy and performance, capable of handling object detection and other vision tasks in resource-constrained environments. Applications include smart surveillance, autonomous driving, and real-time image processing. |
|
|
|
|
|
### Source model |
|
|
|
|
|
- Input shape: 1x3x512x1024 |
|
|
- Number of parameters:13.911M |
|
|
- Model size:53.56MB |
|
|
- Output shape: 1x19x64x128 |
|
|
|
|
|
Source model repository: [FFNet-40S](https://github.com/Qualcomm-AI-research/FFNet) |
|
|
|
|
|
## Performance Reference |
|
|
|
|
|
Please search model by model name in [Model Farm](https://aiot.aidlux.com/en/models) |
|
|
|
|
|
## Inference & Model Conversion |
|
|
|
|
|
Please search model by model name in [Model Farm](https://aiot.aidlux.com/en/models) |
|
|
|
|
|
## License |
|
|
|
|
|
- Source Model: [BSD-3-CLAUSE](https://github.com/Qualcomm-AI-research/FFNet/blob/master/LICENSE) |
|
|
|
|
|
- Deployable Model: [APLUX-MODEL-FARM-LICENSE](https://aiot.aidlux.com/api/v1/files/license/model_farm_license_en.pdf) |
