Adaptive-Wing-Loss-for-Robust-Face-Alignment-via-Heatmap-Regression

Adaptive-Wing-Loss-for-Robust-Face-Alignment-via-Heatmap-Regression copied to clipboard

The function '_nms'. In eval.py, there are two lines of code, "from utils.post_process import _nms out=_nms(out)". There is no "post_process" file here, what is the function of “_nms"? Will the...

jingmingshi

Would you please update the evaluate result on 300W full

Guocode

hi~I have learned your code and gained a lot. And I have two questions. The first one is about the learning rate. The AWing paper mentioned that the initial learning...

Xiaocong6

hi, thanks for your work. I am very interested in it. I have a question about cropping the image in trainset. In face300w.py, line 63, when cropping the image according...

Xiaocong6

RuntimeError: Expected tensor to have cpu DeviceType, but got tensor with cuda DeviceType

1

When I placed 300W and ran train.py, I got the following error. Do you know the solution? ``` > python train.py 11:45:54 train start! Traceback (most recent call last): File...

Keiku

Bug in CoordConv?

1

https://github.com/SeungyounShin/Adaptive-Wing-Loss-for-Robust-Face-Alignment-via-Heatmap-Regression/blob/136e8749b546e3a0fa72916c9f828cc01162164e/models/CoordConv.py#L49 Kindly mention that: ``` ret = torch.cat([ret, xx_channel, yy_channel], dim=1) ``` should be ``` ret = torch.cat([ret, xx_boundary_channel, yy_boundary_channel], dim=1) ``` ?

CuriousCat-7