| library_name: pytorch | |
|  | |
| FSRCNN is a lightweight super-resolution network that accelerates single-image upscaling by performing feature extraction and reconstruction directly in the low-resolution space, significantly reducing computational cost compared to earlier approaches. | |
| Original paper: [Accelerating the Super-Resolution Convolutional Neural Network](https://arxiv.org/abs/1608.00367) | |
| # FSRCNNx4 | |
| This model uses the FSRCNN ×4 variant, which is trained to reconstruct a high-resolution image at four times the input resolution. It is well suited for applications such as image enhancement, video upscaling, surveillance imagery, and edge devices where fast super-resolution inference is required. | |
| Model Configuration: | |
| - Reference implementation: [FSRCNN](https://github.com/yjn870/FSRCNN-pytorch) | |
| - Original Weight: [FSRCNNx4_Weights.91-image](https://www.dropbox.com/s/vobvi2nlymtvezb/91-image_x4.h5?dl=0) | |
| - Resolution: 1x1x128x128 | |
| - Support Cooper version: | |
| - Cooper SDK: [2.5.4] | |
| - Cooper Foundry: [2.3] | |
| | Model | Device | compression | Model Link | | |
| | :-----: | :-----: | :-----: | ------- | | |
| | FSRCNNx4 | N1-655 | Activation_fp16 | [Model_Link](https://huggingface.co/Ambarella/FSRCNN/blob/main/n1-655_fsrcnnx4_act16.bin) | | |
| | FSRCNNx4 | CV7 | Activation_fp16 | [Model_Link](https://huggingface.co/Ambarella/FSRCNN/blob/main/cv7_fsrcnnx4_act16.bin) | | |
| | FSRCNNx4 | CV72 | Activation_fp16 | [Model_Link](https://huggingface.co/Ambarella/FSRCNN/blob/main/cv72_fsrcnnx4_act16.bin) | | |
| | FSRCNNx4 | CV75 | Activation_fp16 | [Model_Link](https://huggingface.co/Ambarella/FSRCNN/blob/main/cv75_fsrcnnx4_act16.bin) | | |