Type: Framework
Google framework with optimized 32-bit and 8-bit NEON routines for Arm CPUs.
Includes an OpenCL backend supporting Arm Mali GPU via SYCL.
Type: Framework
Facebook framework with optimized routines for Arm CPUs with Neon.
Type: Framework
Apache framework with optimized routines for Arm CPUs.
Open AI version optimized with the Arm Compute Library for CPUs and GPUs.
Type: Framework
Microsoft framework with optimized routines for Arm CPUs with Neon.
Type: Framework
Berkley Vision and Learning Centre framework with several options for running on Arm.
CaffeOnACL is a version optimized with the Arm Compute Library for CPUs and GPUs.
Type: API
A high-level neural networks API, written in Python and capable of running on top of several framework backends including TensorFlow and Microsoft Cognitive Toolkit (CNTK).
Learn moreType: Keras backend
Vertex.ai OpenCL framework compatible with Keras API with support for Arm Mali GPU.
Arm Keil MDK is the most comprehensive software development solution for Arm-based microcontrollers and includes all components that you need to create, build, and debug embedded applications.
Learn moreArm NN is the Arm inference engine. Arm NN is designed to optimally run networks that are trained on popular frameworks, like TensorFlow and Caffe, on Arm IP.
Learn moreArm Compute Library optimizes low-level functions for computer vision and machine learning. Arm Compute Library focuses on Convolutional Neural Networks for 32-bit float and 9-bit integers across an array of Arm CPUs and GPUs.
Learn moreCMSIS-NN is the Arm library of efficient neural network kernels for Arm Cortex-M CPUs.
Learn moreCortex-M processors with DSP provide a high level of signal processing and integer performance, while maintaining the energy-efficiency and ease-of-use hallmarks of the Cortex-M family.
Learn moreThis instruction set for Cortex-R processors includes enhanced DSP instructions that improve execution performance for arithmetic operations.
| Suggested answer | [armnn20.02] Running the NeuralNetworksTest_shared_partial case of Android nn will cause the tombstone problem. The source code path of the Android nn case is in the framework\ml\nn\runtime\test directory. Is there a solution to this problem? | 0 votes | 169 views | 2 replies | Latest yesterday by Ben Clark | Answer this |
| Not answered | Object Detection using deep learning | 0 votes | 223 views | 0 replies | Started 28 days ago by Krishna Patel | Answer this |
| Suggested answer | Pytorch framework for Arm NN (CMSIS) | 0 votes | 3071 views | 3 replies | Latest 1 months ago by Karl Fezer | Answer this |
| Suggested answer | A good ML Conference | 0 votes | 3151 views | 4 replies | Latest 1 months ago by asksolutions01 | Answer this |
| Suggested answer | [armnn20.02] Running the NeuralNetworksTest_shared_partial case of Android nn will cause the tombstone problem. The source code path of the Android nn case is in the framework\ml\nn\runtime\test directory. Is there a solution to this problem? Latest yesterday by Ben Clark | 2 replies 169 views |
| Not answered | Object Detection using deep learning Started 28 days ago by Krishna Patel | 0 replies 223 views |
| Suggested answer | Pytorch framework for Arm NN (CMSIS) Latest 1 months ago by Karl Fezer | 3 replies 3071 views |
| Suggested answer | A good ML Conference Latest 1 months ago by asksolutions01 | 4 replies 3151 views |