In this blog, we demonstrate how to analyze a Machine Learning model on a layer-by-layer basis.
How audio development platforms can take advantage of accelerated ML processing
Join DSP Concepts and Alif Semiconductor at Arm DevSummit 2022 to discuss ML techniques commonly used for audio. Discover the features and benefits of the Audio Weaver platform.
How to Deploy PaddlePaddle on Arm Cortex-M with Arm Virtual Hardware
This blog introduces how to deploy a PP-OCRv3 English text recognition model on Arm Cortex-M55 processor with Arm Virtual Hardware.
Usability, performance, and new technologies for Machine Learning: Arm NN in 2021
In this blog post, read about advancements in ML with Arm NN 2021.
Vela Complier: The first step to deploy your NN model on the Arm Ethos-U microNPU
As first step to deploy your NN model on Ethos-U, Vela Complier is open-source and easy-use. Try it out and embrace the improvement of ML ability brought by Ethos-U to embedded system.
Optimize a ML model for fast inference on Ethos-U microNPU
This blog post explains how to optimize a trained deep neural network model to run on Ethos-U55 and Ethos-U65.
Arm DevSummit: Sustainable Innovation – Jewel Beetle’s Wildfire Detection Solution
This year’s Arm DevSummit Developer Competition winner explains how his wildfire detection solution uses tech to tackle real-life sustainability issues.
Paddle-Lite improves performance of mobile devices with Arm technology
This Blog mainly introduced how Paddle-Lite improves performance of mobile devices with Arm technology, especially for CPU and Mali GPU.
The future of smart cameras is 64-bit processing
Learn more about how the future of smart camera technology will bring with it profound transformations in the way we interact with each other and the world around us.
Arm ML Embedded Evaluation Kit
Build and deploy embedded machine learning applications for Arm Cortex-M55 CPU and Arm Ethos-U55 NPU with Arm ML Embedded Evaluation Kit.
Using Arm Streamline for profiling ML workloads
Learn more about how to use Arm Streamline to profile different machine learning workloads for your applications.
Unrolling RNN models for Arm Ethos-U55 and U65
This blog will show you how to train and quantize a recurrent neural network using TensorFlow, then unroll it ready for deployment on Arm Ethos-U55.
On-device face recognition with RGB camera on DTVs
On-device face recognition with RGB cameras on digital televisions (DTVs) is set to become an increasingly important feature for users. Read more in this post.
Image recognition on Arm powered microcontrollers
In this blog we present a TinyML image recognition demo, on an Arm Cortex-M processor, using TensorFlow along with CMSIS-NN for optimized performance.
Advancing interactive intelligence
In this guest blog post, from Kentaro Niikura, read about how Renesas is implementing an advancement in AI.
PyTorch to TensorFlow Lite for deploying on Arm Ethos-U55 and U65
How to convert models to run Ethos-U55 and Ethos-U65 for models trained in PyTorch.
The growing power and influence of smartwatches
This blog discusses the growth of smartwatches and how Arm is delivering processor power and efficiency capabilities for these devices.
Targeting carbon net zero through workflow efficiency
Demand for compute is increasing, yet carbon emissions must be reduced. Machine learning can make workflows more efficient, reducing their carbon footprint.
Porting SSE to Neon: Are libraries the way forward?
Moving from SSE to Arm Neon is a transition many developers are looking to make, with many already making the jump to Neon. In this blog we look at an easier way to achieve this process, and the steps…
Managing the Peaks for Commercial-Grade SLAM
How do you enable your robot to navigate the complexities of world and be successful with the tasks & jobs you give them? Think about the elements that go into SLAM and learn about best practices for deployment…
Improve PyTorch App Performance with Android NNAPI Support
This blog post is about sharing our experience in running PyTorch Mobile with NNAPI on various mobile devices. I hope that this will provide developers with a sense of how these models are executed on…