Inference on Jetson TX2

mileyan / AnyNet

(ICRA) Anytime Stereo Image Depth Estimation on Mobile Devices

https://mileyan.github.io/AnyNet/

MIT License

491 stars 125 forks source link

Inference on Jetson TX2 #18

Open mzemlyanikin opened 4 years ago

mzemlyanikin commented 4 years ago

Hi, thanks for your great work! What backend did you use to run inference on the device? Have you used PyTorch model as is or converted it to TensorRT?

MJITG commented 4 years ago

Same question. Hope for a reply from author

rodrigoGA commented 3 years ago

Hello, I am also interested in this. Did you do any tests? I am also interested in migrating the model to tensorflow lite

whaor commented 3 years ago

Same question. I can't get the expected FPS running the original pytorch model on TX2. Am I missing some tricky details when using TX2？