eliberis / uNAS
μNAS is a neural architecture search (NAS) system that designs small-yet-powerful microcontroller-compatible neural networks.
☆75Updated 3 years ago
Related projects: ⓘ
- [ICLR 2021] HW-NAS-Bench: Hardware-Aware Neural Architecture Search Benchmark☆101Updated last year
- CMix-NN: Mixed Low-Precision CNN Library for Memory-Constrained Edge Devices☆39Updated 4 years ago
- ☆23Updated 2 years ago
- ☆191Updated last year
- MLPerf™ Tiny is an ML benchmark suite for extremely low-power systems such as microcontrollers☆339Updated this week
- ☆20Updated 2 years ago
- TFLite model analyzer & memory optimizer☆120Updated 7 months ago
- This repository containts the pytorch scripts to train mixed-precision networks for microcontroller deployment, based on the memory contr…☆47Updated 4 months ago
- Reference implementations of popular Binarized Neural Networks☆104Updated last week
- Measuring and predicting on-device metrics (latency, power, etc.) of machine learning models☆66Updated last year
- INT-Q Extension of the CMSIS-NN library for ARM Cortex-M target☆20Updated 4 years ago
- Python library to work with the Visual Wake Words Dataset.☆32Updated 3 years ago
- ☆25Updated last year
- Binarize convolutional neural networks using pytorch☆131Updated 2 years ago
- Hardware aware neural architecture search☆12Updated 2 weeks ago
- ☆66Updated this week
- BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization (ICLR 2021)☆36Updated 3 years ago
- Implementation of "NITI: Training Integer Neural Networks Using Integer-only Arithmetic" on arxiv☆75Updated 2 years ago
- ☆15Updated 2 years ago
- A tool to deploy Deep Neural Networks on PULP-based SoC's☆75Updated 6 months ago
- A Plug-and-play Lightweight tool for the Inference Optimization of Deep Neural networks☆31Updated this week
- Official PyTorch Implementation of HELP: Hardware-adaptive Efficient Latency Prediction for NAS via Meta-Learning (NeurIPS 2021 Spotlight…☆59Updated last month
- ☆47Updated 4 years ago
- generate tflite micro code which bypasses the interpreter (directly calls into kernels)☆77Updated 2 years ago
- Official implementation of "Searching for Winograd-aware Quantized Networks" (MLSys'20)☆26Updated 11 months ago
- ☆20Updated 4 years ago
- [ICCAD'22 TinyML Contest] Efficient Heart Stroke Detection on Low-cost Microcontrollers☆15Updated last year
- A collection of research papers on efficient training of DNNs☆67Updated 2 years ago
- [ICLR 2021] "CPT: Efficient Deep Neural Network Training via Cyclic Precision" by Yonggan Fu, Han Guo, Meng Li, Xin Yang, Yining Ding, Vi…☆30Updated 6 months ago
- Implementation for the paper "Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization"☆73Updated 4 years ago