binhmuc

Thank for you reply, bro. Anyway, your work is so great. Do you know WHO also public dataset base on date also ?.

THe same question, how to test with an image for demo

Also your paper said that "A keypoint is considered to be matched correctly if its predicted location is within a distance of α · max(h, w) of the target keypoint...

Thank for you reply :) So, it means that, i just replace "source points" and "target point" in the code and got the natural result ?. But it too weird...

@lixiaolusunshine yes, i understood him. Clearly that, the paper said that source points to target points, but in the source code is totally inverse.

@lixiaolusunshine sorry, i cannot catch up your mean. In his paper, very clear that, use GMM, find a list of parameters, from parameters => warp => loss. The only difference...

I also got this problem. I run in python 3.5.2, tensorflow-gpu 1.8.0, My ubuntu version is 16.04

Thank for your reply. I'm still here :D. My version OS is: Window 10 x64 and Ubuntu 16.04. You can chose one of them and give me the document to...

@ldfinfontainebleau can you give me step by step how to trainning new data, i alreay have my dataset but don't know how to create format in this project and make...