Wayne Wu

Hi Tim, 71pts come from annotated landmarks. In this version of evaluation code, annotated landmarks only play the role of detection rectangle to crop the face. Please refer to #8...

@edubois Hi, we do not do face rotation when testing. Because we augment data with rotation during training, we think the model is robust to deal with most of the...

Hi, We are sorry that some details are missed in our original version of the paper. The inconsistency is caused by the different stacks of hourglass are used in the...

@e-sarkis To my knowledge, most of the methods used mean error for evaluation rather than distribution comparison. Maybe because it is more direct than distribution. Wondering how to guarantee that...

Hi, for the video demo, we use the released "WFLW_final" model which trained on 7500 images of WFLW training set.

Hi, thanks for your interest! Since we do not know the detail of the annotation process of the 68-landmarks of 300W, we do not have the **explicit** corresponding between 98pt...

Hi, if you want to train it, you can try to use batch-size as 2 or 1.

> @wywu thanks for sharing your great work! > I would like to evaluate on the pretrained model to get face landmark on some new face data without annotation. Will...

@yangdashi888 Please check the paper carefully. For more detail please refer to the code or contact us.

Hi, It can be used as the same way of '.caffemodel' file.