tenggyut

the tensorlayer's Droupout layer has trouble working with tf.placeholder?

7

line 138 in L_Resnet_E_IR_MGPU.py: net = tl.layers.DropoutLayer(net, keep=keep_rate, name='E_Dropout') will throw some errors related with placeholders..

Does it possible add GPU support?

1

Is there any way that this library support gpu decoding?

Is it applicable to add landmark detection in this network

6

According to the paper, Faceboxes seems a good replacement of MTCNN in Face Detection Area. But MTCNN has a built in landmark detection, I wonder it is applicable to change...

Dataset?

4

Which dataset are you guys using, public or private?

it seems the model dosen't support down_ratio != 4, the scale calculated by down_ratio is not used....

Hi, line 466 in hardnet.py iterates self.heads which is a dict. but the iterating order may differ in differ python command which will result in different parameter order in model....

poor performance on Asian faces

49

I'm try to compute the cosine similarity of a couple of Asian faces, but it seems facenet can be confused by these faces (two total different faces can have 0.7...