neverUseThisName

Detector fails with gray images

2

When dealing with single channel images, the following error was raised: `Traceback (most recent call last): File "face_align.py", line 5, in lms = fa.get_landmarks_from_directory(dir) File "/usr/local/lib/python3.5/dist-packages/face_alignment/api.py", line 223, in get_landmarks_from_directory...

As I was reading throught the code, I found there's a lot of confusion and unnecessary complication. Can you please simplify?

google drive 下载的resnet152模型和PSENet定义对不上

2

toplayer有3层，模型文件里只有1层 

predicting single image age demo

1

when predicting single image age, why are probs so many 1's? Are these numbers really probilities? And why the class label is 20 while prob for class 20 is low?

phi_theta_ = (self.cur_lambda * cos_theta + phi_theta) / (1 + self.cur_lambda) What is the purpose of this line? It looks like taking a weighted sum of cos and the margined...

The shape of the logits

1

the output 'logits' are of shape (1,768,8,7,7), but it should be (batch, num_class). How to adapt the code to classify videos?