i met the same problem, and hope get ur reply. Is it convenient for you to link with me by wechat(my wechat number: bigbossofwhom).

from pytorch_retinaface.

@biubug6

from pytorch_retinaface.

In general, in order to detect the key points accurately, it is necessary to have a large learning rate for the key points. Through such methods the network can be optimized in the direction of utilizing the key points detection.

from pytorch_retinaface.

@wang-kangkang @takecareofbigboss
have you solved this problem? i meet the same case. the lmk points overlap and always between the eyebrows.

from pytorch_retinaface.

which may because you didn't notice in data argument, if do the mirror operation of this image, the left eye will be right eye, and vice versa. You should read the following code carefully.

def _mirror(image, boxes, landms):
_, width, _ = image.shape
if random.randrange(2):
image = image[:, ::-1]
boxes = boxes.copy()
boxes[:, 0::2] = width - boxes[:, 2::-2]
# landm
landms = landms.copy()
landms = landms.reshape([-1, 5, 2])
landms[:, :, 0] = width - landms[:, :, 0]
tmp = landms[:, 1, :].copy()
landms[:, 1, :] = landms[:, 0, :]
landms[:, 0, :] = tmp
tmp1 = landms[:, 4, :].copy()
landms[:, 4, :] = landms[:, 3, :]
landms[:, 3, :] = tmp1
landms = landms.reshape([-1, 10])

return image, boxes, landms

from pytorch_retinaface.

which may because you didn't notice in data argument, if do the mirror operation of this image, the left eye will be right eye, and vice versa. You should read the following code carefully.

Pytorch_Retinaface/data/data_augment.py

Line 167 in 96b7209

def _mirror(image, boxes, landms):

def _mirror(image, boxes, landms):
_, width, _ = image.shape
if random.randrange(2):
image = image[:, ::-1]
boxes = boxes.copy()
boxes[:, 0::2] = width - boxes[:, 2::-2]

landm

landms = landms.copy()
landms = landms.reshape([-1, 5, 2])
landms[:, :, 0] = width - landms[:, :, 0]
tmp = landms[:, 1, :].copy()
landms[:, 1, :] = landms[:, 0, :]
landms[:, 0, :] = tmp
tmp1 = landms[:, 4, :].copy()
landms[:, 4, :] = landms[:, 3, :]
landms[:, 3, :] = tmp1
landms = landms.reshape([-1, 10])

return image, boxes, landms

thanks very much, i find my code bug in mirror images. the left and right points value is error.

from pytorch_retinaface.