Here is a link to a video of me riding around town with a jetson nano strapped to roof of my car.
I am running the resnet model out of the samples folder.
I am testing out cameras for a project I am working on.
Here is a link to a video of me riding around town with a jetson nano strapped to roof of my car.
I am running the resnet model out of the samples folder.
I am testing out cameras for a project I am working on.
Hi,
Thanks for sharing.
The results looks good.
Do you meet anything that we can help?
Thanks.
Can someone point me to the info on how to retrain the deepstream resnet model for my custom images.
I have been working with the YOLO models but it seems if I want speed I will have to switch over to the deepstream resnet model.
Hi,
We have a Transfer Learning Toolkit for Deepstream models:
https://devblogs.nvidia.com/accelerating-video-analytics-tlt/
You can apply the early access here.
Thanks.
Hi, adventuredaisy
Is everything okay for the retrain job?
Currently, you can retrain the resnet-10 directly with our docker image on the host, and copy the model into device for Deepstream inference.
Here is a HowTo tutorial for your reference:
https://medium.com/dataseries/build-and-deploy-accurate-deep-learning-models-for-intelligent-image-and-video-analytics-8ad755213c06
Thanks.