eliberis / uNAS
μNAS is a neural architecture search (NAS) system that designs small-yet-powerful microcontroller-compatible neural networks.
☆78Updated 3 years ago
Alternatives and similar repositories for uNAS:
Users that are interested in uNAS are comparing it to the libraries listed below
- [ICLR 2021] HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark☆105Updated last year
- CMix-NN: Mixed Low-Precision CNN Library for Memory-Constrained Edge Devices☆39Updated 4 years ago
- Reference implementations of popular Binarized Neural Networks☆106Updated 2 weeks ago
- ☆213Updated last year
- Binarize convolutional neural networks using pytorch☆137Updated 2 years ago
- This repository containts the pytorch scripts to train mixed-precision networks for microcontroller deployment, based on the memory contr…☆49Updated 8 months ago
- TFLite model analyzer & memory optimizer☆121Updated 11 months ago
- ☆24Updated 2 years ago
- Python library to work with the Visual Wake Words Dataset.☆34Updated 4 years ago
- MLPerf™ Tiny is an ML benchmark suite for extremely low-power systems such as microcontrollers☆368Updated 3 weeks ago
- ☆20Updated 2 years ago
- ☆73Updated 2 years ago
- Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming☆95Updated 3 years ago
- A Plug-and-play Lightweight tool for the Inference Optimization of Deep Neural networks☆38Updated this week
- [ICLR 2022 Oral] F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization☆94Updated 2 years ago
- A collection of research papers on efficient training of DNNs☆69Updated 2 years ago
- The official implementation of TinyTrain [ICML '24]☆21Updated 5 months ago
- INT-Q Extension of the CMSIS-NN library for ARM Cortex-M target☆18Updated 5 years ago
- PyTorch implementation for the APoT quantization (ICLR 2020)☆270Updated last month
- Implementation for the paper "Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization"☆73Updated 5 years ago
- ☆15Updated 2 years ago
- ☆47Updated 4 years ago
- generate tflite micro code which bypasses the interpreter (directly calls into kernels)☆79Updated 2 years ago
- Measuring and predicting on-device metrics (latency, power, etc.) of machine learning models☆66Updated last year
- Post-training sparsity-aware quantization☆34Updated last year
- Reproducing Quantization paper PACT☆59Updated 2 years ago
- Official implementation of "Searching for Winograd-aware Quantized Networks" (MLSys'20)☆27Updated last year
- DNN quantization with outlier channel splitting☆112Updated 4 years ago
- Official PyTorch Implementation of HELP: Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning (NeurIPS 2021 Spotlight…☆60Updated 5 months ago