Austin Xiao's Projects
Learning a Unified Classifier Incrementally via Rebalancing
Dive into Deep Learning Compiler
Resources for Data Centric AI
Baseline code for DCASE 2023 task 4 B
《Designing Data-Intensive Application》DDIA中文翻译
In this repository, I will share some useful notes and references about deploying deep learning-based models in production.
A best practice for deep learning project template architecture.
Code for coreset selection methods
Repo associated to the DESED dataset, download and creation of data
Domestic environment sound event detection task
基于 Python3.5 和 Django 1.10 的 Django Blog 项目。
📜 Generates table of contents for markdown files inside local git repository. Links are compatible with anchors generated by github or other sites.
📁 This repo makes it easy to download the raw audio files from AudioSet (32.45 GB, 632 classes).
Edge-aware Graph Representation Learning and Reasoning for Face Parsing (ECCV 2020)
随着移动云计算和边缘计算的快速发展,以及人工智能的广泛应用,产生了边缘智能(Edge Intelligence)的概念。深度神经网络(例如CNN)已被广泛应用于移动智能应用程序中,但是移动设备有限的存储和计算资源无法满足深度神经网络计算的需求。神经网络压缩与加速技术可以加速神经网络的计算,例如剪枝、量化、卷积核分解等。但是这些技术在实际应用非常复杂,并且可能导致模型精度的下降。在移动云计算或边缘计算中,任务卸载技术可以突破移动终端的资源限制,减轻移动设备的计算负载并提高任务处理效率。通过任务卸载技术优化深度神经网络成为边缘智能研究中的新方向。Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge这篇文章提出了协同推断的**,将深度神经网络进行分区,一部分层在移动端计算,而另一部分在云端计算。根据硬件平台、无线网络以及服务器负载等因素实现动态分区,降低时延以及能耗。本项目给出了边缘智能方面的相关论文,并且给出了一个Python语言实现的卷积神经网络协同推断实验平台。关键词:边缘智能(Edge Intelligence),计算卸载(Computing Offloading),CNN模型分区(CNN Partition),协同推断(Collaborative Inference),移动云计算(Mobile Cloud Computing)
This repository aims at providing efficient CNNs for Audio Tagging. We provide AudioSet pre-trained models ready for downstream training and extraction of audio embeddings.
Enhance Your English Writing
End-to-End Speech Processing Toolkit
A Pytorch implementation face parsing model trained by CelebAMask-HQ, based on EHANet.
Framework for Analysis of Class-Incremental Learning with 12 state-of-the-art methods and 3 baselines.
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Transformer related optimization, including BERT, GPT
A fast MoE impl for PyTorch
Flops counter for convolutional networks in pytorch framework
Free course for Resume, 整理和搜集网络免费的项目实战课程,包括 Java 项目实战,Python 项目实战,C++ 项目实战等
:key: :unlock:免费开源的科学上网工具
Official repository for Few-Shot Class-Incremental Learning (FSCIL)