Graph Based image processing for segmenting images and detecting free spots in crowded scenes.
-
Updated
Oct 3, 2023 - C++
Graph Based image processing for segmenting images and detecting free spots in crowded scenes.
A Post-Training Quantizer for the Design of Mixed Low-Precision DNNs with Dynamic Fixed-Point Representation for Efficient Hardware Acceleration on Edge Devices
Dive into the forefront of Large Language Models (LLMs) with our concise guide on the top 10 hot topics. Explore bias mitigation, efficient training, multimodal models, and more. Stay abreast of the latest advancements shaping the landscape of LLMs.
Compute-efficient reinforcement learning with binary neural networks and evolution strategies.
Repository of the ECML PKDD 2021 tutorial title 'Machine Learning Meets Internet of Things: From Theory to Practice'
Library for Structured Matrices (approximation methods and structured layers for neural networks)
[BMVC 2022] Wide Feature Projection with Fast and Memory-Economic Attention for Efficient Image Super-Resolution
Exploring Variational Deep Q Networks. A study undertaken for the University of Cambridge's R244 Computer Science Masters Course. Inspired by https://arxiv.org/abs/1711.11225/.
Channel-Prioritized Convolutional Neural Networks for Sparsity and Multi-fidelity
Code for IoT paper 'Edge2Train: a framework to train machine learning models (SVMs) on resource-constrained IoT edge devices'
[MicroNet Challenge (NeurIPS 2019 )] "Adjustable Quantization: Jointly Learn the Bit-width and Weight in DNN Training" by Yonggan Fu, Ruiyang Zhao, Yue Wang, Chaojian Li, Haoran You, Zhangyang Wang, Yingyan Lin
Semiparametric efficient rank-based estimation of copula parameters
Official PyTorch training code of Accelerating Deep Neural Networks via Semi-Structured Activation Sparsity (ICCV2023-RCV)
Inference speed / accuracy tradeoff on text classification with transformer models such as BERT, RoBERTa, DeBERTa, SqueezeBERT, MobileBERT, Funnel Transformer, etc.
BLOCKSET: Efficient out of core tree ensemble inference
NeurIPS 2019 MicroNet Challenge
Finding Storage- and Compute-Efficient Convolutional Neural Networks
Extremely light-weight MixNet with Top-1 75.7% and 2.5M params
MDFlow: Unsupervised Optical Flow Learning by Reliable Mutual Knowledge Distillation (TCSVT 2022)
Add a description, image, and links to the efficient-inference topic page so that developers can more easily learn about it.
To associate your repository with the efficient-inference topic, visit your repo's landing page and select "manage topics."