search

nwesem / mtcnn_facenet_cpp_tensorRT

Face Recognition on NVIDIA Jetson (Nano) using TensorRT
GNU General Public License v3.0
200 stars 72 forks source link

Question of inputsize #11

Closed mel0615 closed 4 years ago

mel0615 commented 4 years ago

hi I had an error while running this program and I wonder if there's any solution. The setting-inputsize of the model are 640 and 480, and the minsize of mtcnn is 60. But when I change the two parameters, the program doesnot run successfully. According to the model, it build a image pyramid so that any size of images should work. Is there any rule when setting the parameters? I check the program and cannot find the reason so I wonder if you could give some advices. Thanks a lot.

nwesem commented 4 years ago

Hey @mel0615, what was the problem?

mel0615 commented 4 years ago

@nwesem Oh it's a small mistake. Finally I found that the program didnot create a NEW trt-engine when it built with a new group of parameters. It found the path of the PRIOR engine created by prior parameters, and loaded it. I just need to recreate it. Thank u anyway. I should be more careful, lol.