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