BrightenWu
Results
2
comments of
BrightenWu
Try com.cpu() in the end.
Python to C++. ```C++ auto device = torch::Device("cuda"); auto precision = torch::kFloat16; auto downsampleRatio = 0.4; c10::optional tensorRec0; c10::optional tensorRec1; c10::optional tensorRec2; c10::optional tensorRec3; auto model = torch::jit::load("rvm_mobilenetv3_fp16.torchscript"); //! freeze...