is an open-source platform for edge deep learning models on GPU, TPU, and more.
- Jetson Nano
- Edge TPU
- More
Run image classification and object detection models based on MobileNet, EfficientNet, and other state-of-the-art architectures optimized using TensorRT on NVIDIA Jetson Nano Developer Kits. See our Smart Social Distancing application based on MobileNet SSD V2. More models coming soon.
Run highly optimized image classification and object detection models based on mobile-net, efficient-net and other state of the art architectures on Google's Coral Edge TPU. Support for more applications coming soon. Support is now available forCoral Dev Board andAMD64 + Coral USB Accelerator.
Neuralet is in beta and under active development. Help us support more models and hardware platforms by reaching out to ourGitHub repository orcontacting us.
Why Neuralet?
Neuralet can accelerate your evaluation and customization of popular deep learning models on edge devices by providing familiar and straightforward docker container packages that run with minimal effort.
Our Blog
-
Image source This is the first part of a two-part series on Adaptive Deep Learning on the edge by Neuralet.… Read more…
-
What is Neuralet? Neuralet is an open-source platform for edge deep learning models on GPU, TPU, and more. With Neuralet,… Read more…
-
Quantization of TensorFlow Object Detection API Models
Image source In this tutorial, we will examine various TensorFlow tools for quantizing object detection models. We start off by… Read more…
-
Deploying a Custom SSD MobileNet Model on the NVIDIA Jetson Nano
Embedded devices, such as NVIDIA Jetson Nano, enables powerful AI-based applications in real-time at very low power and cost. However,… Read more…
-
Smart Social Distancing Tutorial
This open-source solution has been developed into a mature product, check out our product at Lanthorn.ai As a response to… Read more…
Subscribe
Get the latest news about Neuralet by subscribing to our newsletter.