Jetson TX2 for production

Autonomous Machines Jetson & Embedded Systems Jetson TX2
1

We are looking for an AI board to run the inference of our DL models (Mainly Mobilenet and MaskRCNN models).
We investigate whether Jetson TX2 could be a good option, but we would like some confirmation that it could run those models at at least 12FPS for Mobilenet 24/7 in a production environment.
Also could it support more than one GigE cameras (with a PCIe card)?

Please feel free to add any documentation that I might missed during my research

Thanks

2

Hi evabeacons,

Sorry for the late reply, I think the TX2 should be capable to run those use cases in 24/7 environment by referring the result at our DeepStream SDK performance, https://developer.nvidia.com/deepstream-sdk

Regarding the camera, please find those partner supported camera from https://developer.nvidia.com/embedded/jetson-partner-supported-cameras