Hahn-Schickard / AutoFlow
Bring your AI to the Edge - Starting from building the ML model to the selection of the target platform to the optimization and implementation of the model on the target platform.
☆50Updated last year
Related projects: ⓘ
- generate tflite micro code which bypasses the interpreter (directly calls into kernels)☆77Updated 2 years ago
- Deep Compression for PyTorch Model Deployment on Microcontrollers☆17Updated 3 years ago
- INT-Q Extension of the CMSIS-NN library for ARM Cortex-M target☆20Updated 4 years ago
- ☆191Updated last year
- A Plug-and-play Lightweight tool for the Inference Optimization of Deep Neural networks☆31Updated this week
- MLPerf™ Tiny is an ML benchmark suite for extremely low-power systems such as microcontrollers☆339Updated this week
- Portable C++ library for signal processing and machine learning inferencing☆77Updated this week
- We have implemented a framework that supports developers to structured prune neural networks of Tensorflow Models☆26Updated 2 years ago
- Quick-start machine learning projects on microcontrollers with help of TensorFlow Lite and LibOpenCM3☆31Updated 3 years ago
- ☆29Updated 4 years ago
- TFLite model analyzer & memory optimizer☆120Updated 7 months ago
- A Python package with command-line utilities and scripts to aid the development of machine learning models for Silicon Lab's embedded pl…☆49Updated 2 months ago
- FInd arena size for TensorFlow Lite models☆26Updated last year
- The EEMBC EnergyRunner application framework for the MLPerf Tiny benchmark.☆14Updated last year
- muRISCV-NN is a collection of efficient deep learning kernels for embedded platforms and microcontrollers.☆57Updated last week
- Lightweight C implementation of CNNs for Embedded Systems☆53Updated last year
- A library to train and deploy quantised Deep Neural Networks☆17Updated 6 months ago
- AI applications and tools☆25Updated this week
- NEural Minimizer for pytOrch☆39Updated last month
- QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX☆121Updated this week
- A tool to deploy Deep Neural Networks on PULP-based SoC's☆75Updated 6 months ago
- Pure C ONNX runtime with zero dependancies for embedded devices☆189Updated 10 months ago
- μNAS is a neural architecture search (NAS) system that designs small-yet-powerful microcontroller-compatible neural networks.☆75Updated 3 years ago
- Open Neural Network Exchange to C compiler.☆204Updated last month
- ☆30Updated 6 months ago
- Floating-Point Optimized On-Device Learning Library for the PULP Platform.☆25Updated last week
- ☆29Updated 3 years ago
- Mobilenet v1 trained on Imagenet for STM32 using extended CMSIS-NN with INT-Q quantization support☆85Updated 4 years ago
- Tool for the deployment and analysis of TinyML applications on TFLM and MicroTVM backends☆29Updated last week
- Fork of upstream onnxruntime focused on supporting risc-v accelerators☆77Updated last year