search

dusty-nv / jetson-inference

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.
https://developer.nvidia.com/embedded/twodaystoademo
MIT License
7.89k stars 2.99k forks source link

model-specific fps #497

Closed gpqls closed 1 year ago

gpqls commented 4 years ago

There are many models for facial recognition, as shown here. I will use Jetson TX2 among them. I want to know the model fps at Jetson. Because I want to use the best performance model available at Jetson TX2. Please let me know how to investigate this or if you have a model to recommend. Thanks.

dusty-nv commented 4 years ago

Hi @gpqls , if you run the models through one of the programs in jetson-inference, it will print out the time to the console log that it takes to process the network with TensorRT.