Deepinx

Results 14 comments of Deepinx

You need to download the WIDER face training images and the face annotations from the dataset website. You also need to download the pre-trained VGG-16 ImageNet model. Then you should...

In line 36 of essh_detector.py, I empirically set nms_threshold to 0.3. If you have multiple bounding boxes on one face, you can try adjusting this parameter.

Through my experience, it is the setting of nms_threshold parameter, you can try adjusting it in line 36 of essh_detector.py to see if this problem can be solved.

@weiyichang Thanks for your advice. I have not encountered such a problem on my computer, so I can't test it. I think this problem is related to the configuration of...