EfficientNetv2 on Deepstream

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version Deepstream 6.0
• JetPack Version (valid for Jetson only)
• TensorRT Version 8.0.1
• NVIDIA GPU Driver Version (valid for GPU only) 470.63.01
• Issue Type( questions, new requirements, bugs) Questions
• Requirement details
I want to know if EfficientNetV2 is supported in DeepStream. If yes, could you please guide me on how to integrate it into DeepStream SGIE for image classification?
I am using this EfficientNetV2 model for classification.
Link: efficientnet_v2_s — Torchvision main documentation
Thank you.

2

As of DeepStream 6.0, EfficientNetV2 is not natively supported by DeepStream. You would need to add support following the Using a Custom Model with DeepStream guide

4

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

Nvidia TAO provides EfficientDet backbone in Open Images Pre-trained EfficientDet - NVIDIA Docs, TAO Pretrained EfficientDet | NVIDIA NGC

The EfficientDet DeepStream integration sample is in NVIDIA-AI-IOT/deepstream_tao_apps: Sample apps to demonstrate how to deploy models trained with TAO on DeepStream (github.com)

6

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.