I have trained my Nvidia TAO Yolo_v4 resnet-18 object detection model inside a jupyter notebook.
It is in “.hdf5” format. Can I download the model to my local machine to use it inside an streamlit app ?
what are some dependencies I have to be careful of ?
how to implement it to use via an interactive UI ?
User can run inference with the model.
Also, you can export to onnx to run. Or generate tensorrt engine to run inference.
For using in an streamlit app, you can search if there is similar guide for it.
My aim is to use the yolo_v4_object_detection model that is trained in TAO framework and saved in “.hdf5” format to do object detection.
It is giving good results on inferencing inside jupyter notebook.
How can I use one interactive UI to input one image of my choice and
the model will perform object detection and give us back the image with
bounding boxes , class name and confidence score.
Is there any dependencies on TAO framework ?
do I have to use Nvidia platform only, or , I can use any platform.
Basically how do I transfer my model from TAO framework and
integrate it into an interactive UI outside TAO ?
Can I use it directly in “.hdf5” format or do I have to convert it to any other format ?
In summary, I need guidance on converting the model to a compatible format and building an interactive UI to deploy it outside the TAO framework.
For the latest question, let us sync in How to build an ineractive UI on top of Nvidia TAO trained model that is in ".hdf5" format.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.