metadata
license: afl-3.0
tags:
- tensorflow
- feature_extraction
- image
- perceptual_metric
datasets:
- tid2008
- tid2013
metrics:
- pearsonr
model_index:
- name: PerceptNet
- task:
type: feature_extraction
name: Perceptual Distance
dataset:
type: image
name: tid2013
metrics:
- type: pearsonr
value: 0.93
name: TID2013
PerceptNet
PercepNet model trained on TID2008 and validated on TID2013, obtaining 0.97 and 0.93 Pearson Correlation respectively.
Link to the run: https://wandb.ai/jorgvt/PerceptNet/runs/28m2cnzj?workspace=user-jorgvt
Usage
As of now to use the model you have to install the PerceptNet repo to get access to the PerceptNet
class where you will load the weights available here like this:
from perceptnet.networks import PerceptNet
weights_path = get_file(fname='perceptnet_rgb.h5',
origin='https://huggingface.co/Jorgvt/PerceptNet/blob/main/final_model_rgb.h5')
model = PerceptNet(kernel_initializer='ones', gdn_kernel_size=1, learnable_undersampling=False)
model.build(input_shape=(None, 384, 512, 3))
model.load_weights(weights_path)