Pytorch_Retinaface
Pytorch_Retinaface copied to clipboard
biubug6
Retinaface get 80.99% in widerface hard val using mobilenet0.25.
I tried, but it didn't speed up with batches.
Hello, I would like to ask if you have done face alignment in the program. RetainFace's paper describes face alignment, but I only found five key points marked, not alignment....
Hi, Thanks very much for sharing your awesome works. Due to the variation of the dataset ( hard & easy examples in each iteration), the out loss is unstable at...
thank you for your share.The implementation of pytorch help me a lot.however, i have a question about what is 'Pytorch (same parameter with Mxnet)' ,i don't clear which parameter need...
Hi, I noticed that you labeled hard gts as 2 to ignore, but when computing loss those anchors attached to hard gt still be considered. So actually anchors are either...
Many thanks for your great job, I just wondering how can I get embedding vectors for the detected faces?
dear author, iwan to known what the performamnce mean, i.e. Style | easy | medium | hard Pytorch (same parameter with Mxnet) | 88.67% | 87.09% | 80.99% Pytorch (original...
mobilenet-0.25在i7 cpu前传时间60ms左右，与作者给出的VGA图片CPU-1的时间17.2ms相差很多，请问什么原因呢？
When I run the detect.py which the default image size is 624x1024,the inference time is 14ms.And I resize the image size to 256x256,the inference time is also 14ms.So I have...
