search

enazoe / yolo-tensorrt

TensorRT8.Support Yolov5n,s,m,l,x .darknet -> tensorrt. Yolov4 Yolov3 use raw darknet *.weights and *.cfg fils. If the wrapper is useful to you,please Star it.
MIT License
1.18k stars 313 forks source link

DLA #88

Open alicera opened 3 years ago

alicera commented 3 years ago

https://docs.nvidia.com/deeplearning/tensorrt/api/c_api/classnvinfer1_1_1_i_builder.html#a2b2cdcc03e18f412d0e3fd9e018d90c0

请问一下 The DLA core 是指什么？如何去确定数量

--

ismetdagli commented 3 years ago

You need either set 0 or 1, depending on your device. If you have DLA in your device, you can build the engine and set the device type as 0 or 1

alicera commented 3 years ago

I try to use the getNbDLACores() and get the 0. So the GPU doesnt support DLA ?