Stars
Code for "Learning Where To Look – Generative NAS is Surprisingly Efficient"
Neural Network Quantization With Fractional Bit-widths
A Tensorflow Keras implementation (Graph and eager execution) of Mnasnet: MnasNet: Platform-Aware Neural Architecture Search for Mobile.
Implementation of Progressive Neural Architecture Search in Keras and Tensorflow
Keras implementation of Efficient Neural Architecture Search
A collection of tutorials for the fpgaConvNet framework.
Collection of RNN models and quantized RNN models
Scripts to run large scale hls4ml conversion and synthesis jobs on k8s to generate training data for a hls4ml surrogate model, wa-hls4ml
HLSFactory: A Framework Empowering High-Level Synthesis Datasets for Machine Learning and Beyond
Resource Utilization and Latency Estimation for ML on FPGA.
Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours
PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks
PyTorch implementation of EdMIPS: https://arxiv.org/pdf/2004.05795.pdf
A DNN inference latency prediction toolkit for accurately modeling and predicting the latency on diverse edge devices.
[SIGMETRICS 2022] One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search
Harmonic-NAS: Hardware-Aware Multimodal Neural Architecture Search on Resource-constrained Devices (ACML 2023)
HW-PR-NAS is a single surrogate model trained to Pareto rank the architectures based on Accuracy, Latency and energy consumption
Neural Architecture Search (NAS) papers with code
Class Project for 18663 - Implementation of FBNet (Hardware-Aware DNAS)
Learning Efficient Convolutional Networks through Network Slimming, In ICCV 2017.
Official Repo for "Multi-objective Differentiable Neural Architecture Search"
Pytorch Implementation of Neural Architecture Optimization