I have trained SSD using the Transfer Learning Toolkit on Ubuntu 20.0.4 via the docker container. I have two questions,
The development environment is in Ubuntu 20.0.4. In the Jupyter Notebook, I’m able to infer the images using the following script,
!ssd inference --gpu_index=$GPU_INDEX
Now, How do I write business logic on top of it by feeding images from the OpenCV? Where is this file that has got the inference code?
In Jetson, I have used Deepstream to deploy. But I couldn’t find a simple implementation that shows how I could deploy the custom model on the Jetson using Python API? I have both
.tlt,.etlt,.enginefiles but the documentation is extremely worse and scattered so it’s hard to understand. And how do I see the output as we would with OpenCV using