deepIQA
deepIQA copied to clipboard
dmaniry
NR and FR IQA models based on Deep Convolutional Neural Networks
File "evaluate.py", line 34, in extract_patches patch_indices_shape = ((np.array(arr.shape) - np.array(patch_shape)) // ValueError: operands could not be broadcast together with shapes (2,) (3,)
problem at line: serializers.load_hdf5(args.model, model) of file evaluate.py
Hello dear Mr. Maniry: First I want to thank you for your work on the NR IQA, then Shall I ask for the training code on UCID database and measuring...
Since I am very interested in your work, could you please provide me with the training code? Thank you!
Hi, Thank you for the nice work. Do you use any pre-trained model to initialize the VGG net? Or the models are trained from scratch? Thanks.
I want to know the result score is more high if the picture is more clear.What is the range of the score interval? （when I run the code,there is many...
Hi, I'm trying to run your great code, but no success. Do you have list or requirements/ Container? Thank you.
I want to test this on my local machine. Is it possible to config and run it without GPU. Please specify detailed steps of you can.
