NVIDIA TAO | deprecated
Last updated
Was this helpful?
Last updated
Was this helpful?
Edge Impulse support of NVIDIA TAO object detection and image classification models has been deprecated. As of February 28th, 2025, these model options will no longer appear within the platform.
The NVIDIA TAO models that were available directly in the Edge Impulse platform have been deprecated by NVIDIA.
Your existing projects that use NVIDIA TAO models will continue to work in Studio, including deployment. However, you will not be able retrain these models.
There are alternative model options with comparable or improved performance available in the Edge Impulse platform.
There are several object detection models currently available to you, including those based on the FOMO and MobileNetV2 SSD architectures, as well as some of the examples in the Custom learning blocks (such as YOLOv5) that can be used as alternatives to the NVIDIA TAO object detection models that were previously available. We might just also have something else in the works that will be ready for a developer preview in the coming weeks. Stay tuned!
These models can be accessed by adding an object detection learning block to your impulse, then selecting your desired model on the settings page for the block.
In addition to existing models available for image classification, the EfficientNet architecture has been added to the platform as an alternative to the NVIDIA TAO image classification models that were previously available.
These models can be accessed by adding a transfer learning (images) learning block to your impulse, then selecting your desired model on the settings page for the block.
Also see the EfficientNet Custom learning block that we made accessible directly from the Image Classification (Transfer Learning) block.
Deprecated feature
This feature has been deprecated. Please see below for additional details.