Pruning on standard darknet model and tensorflow model

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hi,
I have a Yolo darknet model and tensorflow model and I want to prune these model and test it on DeepStream SDK 5.0. Can you kindly help by giving the steps or some kind of reference.

|•|Hardware Platform (Jetson / GPU)T4|
|•|DeepStream Version5.0|
|•|JetPack Version (valid for Jetson only)|
|•|TensorRT Version7.0|
|**•|NVIDIA GPU Driver Version (valid for GPU only)**450.36.06|

3

Hi,

To prune a model for Deeptream, please use our transfer learning toolkit:

Thanks.

4

Hi Aastalll,
Is it possible to prune the standard model (darknet, Tensorflow) which is available in the official sites (eg:
https://pjreddie.com/media/files/yolov3.weights). Kindly share your comments.

5

Hi,

Sorry that TLT only support NVIDIA pre-trained models from NGC currently.

For a TensorFlow, you can try to find some pruning sample from the website.
Ex. Pruning in Keras example  |  TensorFlow Model Optimization

Thanks.