search

ceccocats / tkDNN

Deep neural network library and toolkit to do high performace inference on NVIDIA jetson platforms
GNU General Public License v2.0
718 stars 209 forks source link

Whether Yolov4-CSP and Yolov4-Large models are tested using FP32 or FP16? #161

Closed mls1999725 closed 2 years ago

mls1999725 commented 3 years ago

Hi, I wonder whether Yolov4-CSP and Yolov4-Large models are tested using FP32 or FP16 ? Looking forward to your reply.

mive93 commented 3 years ago

Hi @mls1999725 what do you mean? You can do both, just enable one or other mode using env variable TKDNN_MODE.

mive93 commented 2 years ago

Closing for inactivity. Feel free to reopen.