search

tadax / glcic

Globally and Locally Consistent Image Completion with TensorFlow
MIT License
135 stars 42 forks source link

Add perceptual loss from pre-trained CNN #7

Open RobinCSIRO opened 6 years ago

RobinCSIRO commented 6 years ago

Hi, @tadax, thank you very much for your project. I am new to the task of 'image inpainting', and I noticed that most of papers of this project adopt another loss, called perceptual loss by calculating the difference of reconstructed image and original image with the feature vector extracted from a pre-trained CNN (e.g., VGG16). Could you please show me how to add such loss into your model or recommend me some other implementation you know to realize such tasks? Thank you very much~~

Abhi001vj commented 6 years ago

may be there is no need to use another model for perceptual loss as this network has two discriminators which are doing this already if I understand this correctly . Thats what i thought when I looked at the abstract for the project in the website for the paper.