JieLuChen comments

Repositories
Issues
Comments

Results 2 comments of


                                            JieLuChen

Any chance we can load the onnx model and run it into TensorRT

> Yes I made it work. I am getting 70 ms runtime on 3060 RTX for the 512 upscale model. (GFPGAN 1.4) using TensorRT. (without pre and post processing) However...

infer time

> nice work! > > i run at 4090，the infer time is: 0.6s，a little long. Is this the normal effect? How did you get 0.6s? I am trying with CUDAExecutionProvider...