NVIDIA Developer Forums

Workspace size for Jetson Nano

Robotics & Edge Computing Jetson & Embedded Systems Jetson Nano

AastaLLL October 19, 2020, 3:36am 5

Hi,

The physical memory of Nano is 4G, so please set the workspace < 4G.

The engine file size is model & platform dependent.
So this may cause the engine file of Nano to become large than other platforms.

Thanks.

Topic		Replies	Views	Activity
Issue regrading size and type of the model during conversion from ONNX to TRT Jetson Nano tensorrt , jetson-inference , onnx	2	436	October 18, 2021
Model file size on jetson nano with 6.0-full-dims is larger than that on desktop PC with 6.0 Jetson Nano onnx	4	768	October 18, 2021
ONNX to TensorRT model conversion failure on Jetson Nano Jetson Nano tensorrt	7	618	November 6, 2023
Tensorrt Engine use too much memory TensorRT tensorrt	1	1618	December 13, 2021
TensorRT TensorRT	1	381	March 9, 2020
Issue regrading size and type of the model during conversion from ONNX to TRT TensorRT tensorrt , cuda , pytorch , onnx	1	519	October 12, 2020
Why dla need so much workspace size? TensorRT tensorrt , jetson-inference	2	813	March 19, 2021
TX2 NX ONNX Convert TensorRT Engine Jetson TX2 tensorrt , hw , jetson-inference	2	622	October 18, 2021
Infer time after conversion and ram usage TensorRT tensorrt	12	1077	February 15, 2022
TensorRT engine cannot be built due to workspace size even if it's set higher TensorRT tensorrt	5	6599	January 28, 2022