Please install and setup AIMET before proceeding further. This evaluation was run using AIMET 1.22.2 for TensorFlow 2.4 i.e. please set release_tag="1.22.2" and AIMET_VARIANT="tf_gpu" in the above instructions.
pip install scikit-image==0.16.2
pip install mmcv==1.2.0
pip install tensorflow-gpu==2.4.0- Clone the krasserm repo:
git clone https://github.com/krasserm/super-resolution.git
cd super-resolution - Append the repo location to your
PYTHONPATHwith the following:
export PYTHONPATH=<path to super-resolution repo>/super-resolution:$PYTHONPATH
export PYTHONPATH=$PYTHONPATH:<path to parent>/aimet-model-zoo
- The original SRGAN model is available at:
python3 srgan_quanteval.py --dataset-path <path to dataset>- We only support 4x super resolution on .png images. So make sure your high resolution images are 4x the dimension of your low resolution images. If you are using one of the benchmark datasets, please use images under
image_SRF_4directory. - We assume low and high resolution images are both present under the same directory, with images that follow the below naming conventions:
- low resolution images will have file name suffix:
LR.png- e.g.
people_LR.png
- e.g.
- high resolution images will have file name suffix:
HR.png- e.g.
people_HR.png
- e.g.
- low resolution images will have file name suffix:
- Weight quantization: 8 bits, per tensor asymmetric quantization
- Bias parameters are not quantized
- Activation quantization: 16 bits, asymmetric quantization
- Model inputs are quantized
- Bias Correction and Cross Layer Equalization have been applied
| Model | Dataset | PSNR | SSIM |
|---|---|---|---|
| FP32 | Set5 / Set14 / BSD100 | 29.17 / 26.17 / 25.45 | 0.853 / 0.719 / 0.668 |
| INT8 / ACT8 | Set5 / Set14 / BSD100 | 28.31 / 25.55 / 24.78 | 0.821 / 0.684 / 0.628 |
| INT8 / ACT16 | Set5 / Set14 / BSD100 | 29.12 / 26.15 / 25.41 | 0.851 / 0.719 / 0.666 |