xiaosuzhang

Thank you,but i don't quiet understand what you mean.you say i don't need to install the original Matconvnet. What is the $MATCONVNET/matlab path?

I download the pre-trained model named“biggan-deep-256-pytorch_model.bin”

face.prototxt文件中输入图像分辨率和模型的那个分辨率尺寸不一样也可以直接用吗？

@shyamala-methy Can you send me the ArcFace pretrained caffemode, I haven't found that. Thank you

@shyamala-methy Can you send me the converted prototxt and caffemodel files? My environment could not work. Thanks

Thanks again

@maxteleg 将编译好的哪些boost文件替换过去呢？boost全部文件夹吗？？

@maxteleg 您好，可以把您编译过得基于python3.5的thirdparty发我一份吗？？谢谢

My classes=1 and the anchors boxs per cell is 3. And I also change the values of variable variable num_classes,and set the num_classes=1.

Yes! I use the yolov3.cfg based on the the model from https://pjreddie.com/darknet/yolo/, only change the num_classes=1 and filters=18 to train on my own dataset.