eliberis / uNAS
μNAS is a neural architecture search (NAS) system that designs small-yet-powerful microcontroller-compatible neural networks.
☆79Updated 4 years ago
Alternatives and similar repositories for uNAS:
Users that are interested in uNAS are comparing it to the libraries listed below
- CMix-NN: Mixed Low-Precision CNN Library for Memory-Constrained Edge Devices☆41Updated 5 years ago
- [ICLR 2021] HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark☆110Updated 2 years ago
- TFLite model analyzer & memory optimizer☆126Updated last year
- Python library to work with the Visual Wake Words Dataset.☆35Updated 4 years ago
- ☆224Updated 2 years ago
- The official implementation of TinyTrain [ICML '24]☆22Updated 9 months ago
- Binarize convolutional neural networks using pytorch☆146Updated 3 years ago
- ☆76Updated 2 years ago
- This repository containts the pytorch scripts to train mixed-precision networks for microcontroller deployment, based on the memory contr…☆49Updated last year
- [ICLR 2022 Oral] F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization☆94Updated 3 years ago
- MLPerf™ Tiny is an ML benchmark suite for extremely low-power systems such as microcontrollers☆403Updated last week
- A collection of research papers on efficient training of DNNs☆70Updated 2 years ago
- ☆20Updated 3 years ago
- Reference implementations of popular Binarized Neural Networks☆107Updated 3 weeks ago
- The code for paper: Neuralpower: Predict and deploy energy-efficient convolutional neural networks☆21Updated 5 years ago
- Any-Precision Deep Neural Networks (AAAI 2021)☆60Updated 5 years ago
- ☆25Updated 3 years ago
- Official PyTorch Implementation of HELP: Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning (NeurIPS 2021 Spotlight…☆63Updated 9 months ago
- Measuring and predicting on-device metrics (latency, power, etc.) of machine learning models☆66Updated 2 years ago
- Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming☆96Updated 3 years ago
- generate tflite micro code which bypasses the interpreter (directly calls into kernels)☆80Updated 2 years ago
- Implementation of "NITI: Training Integer Neural Networks Using Integer-only Arithmetic" on arxiv☆80Updated 2 years ago
- ☆146Updated 2 years ago
- INT-Q Extension of the CMSIS-NN library for ARM Cortex-M target☆18Updated 5 years ago
- Implementation for the paper "Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization"☆74Updated 5 years ago
- Post-training sparsity-aware quantization☆34Updated 2 years ago
- Official implementation of "Searching for Winograd-aware Quantized Networks" (MLSys'20)☆27Updated last year
- BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization (ICLR 2021)☆40Updated 4 years ago
- PyTorch implementation for the APoT quantization (ICLR 2020)☆272Updated 4 months ago
- Code repo for the paper BiT Robustly Binarized Multi-distilled Transformer☆106Updated last year