|
|
--- |
|
|
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-to-image |
|
|
tags: |
|
|
- AIoT |
|
|
- QNN |
|
|
--- |
|
|
|
|
|
 |
|
|
|
|
|
## ESRGAN：Image Super Resolution |
|
|
|
|
|
ESRGAN (Enhanced Super-Resolution Generative Adversarial Networks) is an efficient and user-friendly deep learning framework designed for performing image super-resolution tasks. It adopts a SRResNet-based architecture and incorporates residual, contextual loss, perceptual loss, and adversarial loss. The aim is to train the generator and discriminator networks to restore image details while making the generated images more realistic. |
|
|
|
|
|
### Source model |
|
|
|
|
|
- Input shape: 128x128 |
|
|
- Number of parameters: 16.69M |
|
|
- Model size: 63.8MB |
|
|
- Output shape: 1x3x512x512 |
|
|
|
|
|
Source model repository: [ESRGAN](https://github.com/xinntao/ESRGAN/) |
|
|
|
|
|
## 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: [APACHE-2.0](https://github.com/xinntao/ESRGAN/blob/master/LICENSE) |
|
|
|
|
|
- Deployable Model: [APLUX-MODEL-FARM-LICENSE](https://aiot.aidlux.com/api/v1/files/license/model_farm_license_en.pdf) |
