TensorRT_yolo3_module icon indicating copy to clipboard operation
TensorRT_yolo3_module copied to clipboard

Why pytorch?

Open zhzhang747 opened this issue 5 years ago • 1 comments

In file trt_yolo3_module_1batch.py: Ln 49 a = torch.cuda.FloatTensor() #pytorch必须首先占用部分CUDA Why need pytorch first? Thank you.

zhzhang747 avatar Mar 25 '20 08:03 zhzhang747

你解决了吗?我到这一行报错: TypeError: type torch.cuda.FloatTensor not available. Torch not compiled with CUDA enabled.

Scheaven avatar Apr 13 '20 08:04 Scheaven