|
|
--- |
|
|
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-classification |
|
|
tags: |
|
|
- AIoT |
|
|
- QNN |
|
|
--- |
|
|
|
|
|
 |
|
|
|
|
|
## RegNet: Image Classification |
|
|
|
|
|
RegNet is a convolutional neural network architecture proposed by Facebook AI, designed to optimize performance and computational efficiency through a regularized network structure. Unlike traditional manually designed deep learning models, RegNet uses automated design principles to generate a family of efficient and scalable models. The RegNet family, which includes variants like RegNetX and RegNetY, achieves optimal trade-offs between network width, depth, and grouped convolutions, providing flexibility for different computational resources and task requirements. RegNet excels in tasks such as image classification and object detection, with its scalable design making it ideal for resource-constrained environments and efficient inference. |
|
|
|
|
|
### Source model |
|
|
|
|
|
- Input shape: 224x224 |
|
|
- Number of parameters: 5.24M |
|
|
- Model size: 20.93M |
|
|
- Output shape: 1x1000 |
|
|
|
|
|
Source model repository: [regnet](https://github.com/pytorch/vision/blob/main/torchvision/models/regnet.py) |
|
|
|
|
|
## 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/pytorch/vision/blob/main/LICENSE) |
|
|
|
|
|
- Deployable Model: [APLUX-MODEL-FARM-LICENSE](https://aiot.aidlux.com/api/v1/files/license/model_farm_license_en.pdf) |
