1:核对GPU的计算能力
地址:https://developer.nvidia.com/cuda-gpus
For example, GTX1060 is 6.1, RTX 2070 is 7.5.
2:核对硬件支持的精度
地址:https://docs.nvidia.com/deeplearning/tensorrt/support-matrix/index.html#hardware-precision-matrix
6.1 supports FP
1:核对GPU的计算能力
地址:https://developer.nvidia.com/cuda-gpus
For example, GTX1060 is 6.1, RTX 2070 is 7.5.
2:核对硬件支持的精度
地址:https://docs.nvidia.com/deeplearning/tensorrt/support-matrix/index.html#hardware-precision-matrix
6.1 supports FP