PyTorch implementation of the following paper: Kang L, Ye P, Li Y, et al. Convolutional neural networks for no-reference image quality assessment[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2014: 1733-1740.
The optimizer is chosen as Adam here, instead of the SGD with momentum in the paper.
CUDA_VISIBLE_DEVICES=0 python CNNIQA.py 0 config.yaml LIVE CNNIQA
Before training, the im_dir
in config.yaml
must to be specified.
tensorboard --logdir='./logs' --port=6006
- PyTorch
- TensorFlow-TensorBoard if
enableTensorboard
inconfig.yaml
isTrue
.