CU-Net

CU-Net copied to clipboard

Im trying to predict on the full image but in the dataloader there is cropping and augmentation going on. Is there a way to paste the cropped result with landmarks...

waleedrazakhan92

hi, can you please provide weight files?

bokey007

Code does not work

1

Hello, this paper is really good, but I made a mistake when I resurfaced face_prev. I checked a lot of information, but I couldn't solve it. I don't know how...

iam-zhanghongliang

Error in table 8 of the paper with the 300W NME?

1

Hi, I have looked into table 8 in your paper and all the measures you put there from the literature computes the NME dividing by the interpupil distance. On the...

jmbuena

Hello, thank you very much for sharing the code, but I have problems running the code for the facial landmarks localization. I can't get the result 3.34% in Fullset mentioned...

NEUAM

Thank you for making the code available. If we look into line 106 and 107 of the ```data/face_bbx.py```, the code tries to get the random scale and rotation ```python s...

abhi1kumar

Thanks for making the code available! Could you explain how you split the data in MPII's "annot"? Based on the provided code, the training image number is 25925 and the...

jingyang2017

Questions about Iterative forward pass.

1

Hi, thank u for your shared code, I have read 'models/cu-net.py' carefully, but I can't find any code about iterative refinement, can you tell me where it is. Since I...

yzldw333

zouxuelian

Hi, I have read your paper recently. Great work! It seems that you haven't mentioned the forward computation speed of this algorithm. In my opinion，most binary computation would speed up...

yzldw333