search

marcoslucianops / DeepStream-Yolo

NVIDIA DeepStream SDK 7.0 / 6.4 / 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models
MIT License
1.4k stars 345 forks source link

Where can I set the generated engine to FP16? #372

Closed lrjj closed 1 year ago

lrjj commented 1 year ago

Where can I set the generated engine to FP16?

marcoslucianops commented 1 year ago

You need to set

model-engine-file=model_b1_gpu0_fp16.engine

and

network-mode=2

In the config_infer_primary file (according to the model you are using). Delete the old engine and regenerate it.

lrjj commented 1 year ago

You need to set

model-engine-file=model_b1_gpu0_fp16.engine

and

network-mode=2

In the config_infer_primary file (according to the model you are using). Delete the old engine and regenerate it.

Thank you very much, it's already working!