Bad quality of "eye" landmarks when eyes are closed.

[HungVS]

Hello, great work there!!!

I executed the camera.py file with your pre-trained model at "./checkpoint/snapshot/checkpoint.pth.tar".

I realize that eye landmarks generated when eyes are closed are very bad (shown in the below figure). Is this behavior normal? if "not", can you give me some advice to overcome this? Thanks in advance.

[sainisanjay]

@HungVS If do you have idea then could you help me on issue #75 I am trying to train PFLDInference network with 192x192 image size. I get error while training: RuntimeError: mat1 and mat2 shapes cannot be multiplied (256x4656 and 176x196)