Vinayak N Baddi
Vinayak N Baddi
Thank you for reply btomtom5. I understand that, But since the base code for bnn.torch is written in Nvidia Cuda. Can I atleast convert it to "cudnn." So then I...
Yeah. So the only alternative would be writing a CPU equivalent of bnn.torch?
@Jason-xin . User ONNX as exchange format to convert to tensorflow model. With model structure and model input dimensions, you can convert it.
The input to detector is 3 channel, please refer the detector code [here](https://github.com/1adrianb/face-alignment/blob/master/face_alignment/detection/sfd/detect.py) make changes accordingly