Reviews: Conditional Image Generation with PixelCNN Decoders

The paper solves a significant problem in generative modeling and the paper is quite interesting. However, reviewer feels the current version is not polished well due to several issues in the experimental section. For rebuttal, please focus on the (*), (**), (***) and (***) mentioned in the following paragraphs. Reviewer is willing to change the score if all the concerns are addressed in the rebuttal. Novelty: The proposed model is technically novel in the sense that it explores the conditional modeling with the recent pixel (R/C)NN framework.