I’m trying to run an object detection model(mobilenet ssd v2) on my jetson nano 2GB. I’m following this blog link. unfortunately when I tried to load pb file memory got full and stuck on there. I tried with TF OD API, it also stuck at loading pb file. when I monitor memory usage with jtop initially I have 1.4 GB free after loading pb file I can see memory filling up slowly(30 sec.). any idea why this is happening? How much ram need to run ssd model on jetson nano?
AastaLLL
3
Hi,
The sample is tested with Nano 4GB.
To save memory, maybe you can try pure TensorRT API rather than TF-TRT.
Thanks.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Cannot run Tensorrt demo on jetson Nano Module - Not enough memory space to even install libraries! | 1 | 501 | July 23, 2020 | |
| Problem with limited memory after loading model - Jetson Nano | 1 | 1626 | July 29, 2021 | |
| Jetson Nano Out of Memory running TRT Model | 4 | 2339 | December 3, 2021 | |
| Jetson Nano (2gb) OOM | 5 | 1062 | April 14, 2022 | |
| Tensorflow HELP on Jetson Nano? | 1 | 758 | November 5, 2020 | |
| TensorFlow object detection inference out of memory | 6 | 3248 | September 24, 2019 | |
| Memory usage difference between Jetson Nano vs PC loading the same model | 1 | 853 | March 14, 2022 | |
| Getting CUDA Error while runnin inference in Jetson Nano 2GB | 3 | 592 | December 28, 2020 | |
| Converting tensorflow pb model file to tensorrt GPU memory error | 2 | 1218 | October 17, 2019 | |
| SSD Mobilenet onnx from saved_model trained in tensorflow api | 1 | 1332 | December 28, 2020 |