JasperRuvik
Follow
Stars
Reproducing RigL (ICML 2020) as a part of ML Reproducibility Challenge 2020
[ICLR 2022] The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training by Shiwei Liu, Tianlong Chen, Xiaohan Chen, Li Shen, Decebal Constantin Mocanu, Z…
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)
[ICML2022] Training Your Sparse Neural Network Better with Any Mask. Ajay Jaiswal, Haoyu Ma, Tianlong Chen, ying Ding, and Zhangyang Wang
[ICLR2023] NTK-SAP: Improving neural network pruning by aligning training dynamics
Comparison of method "Pruning at initialization prior to training" (Synflow/SNIP/GraSP) in PyTorch
Official repository of our work "Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning" accepted at CVPR 2024
Prospect Pruning: Finding Trainable Weights at Initialization Using Meta-Gradients
Iterative Filter Pruning for Concatenation-Based CNN Architectures
A repository in preparation for open-sourcing lottery ticket hypothesis code.
Pytorch implementation of the paper "SNIP: Single-shot Network Pruning based on Connection Sensitivity" by Lee et al.
This repository is the official implementation of the paper Pruning via Iterative Ranking of Sensitivity Statistics and implements novel pruning / compression algorithms for deep learning / neural …
[ICLR 2023] Pruning Deep Neural Networks from a Sparsity Perspective
Add virtual monitors to your windows 10/11 device! Works with VR, OBS, Sunshine, and/or any desktop sharing software.
Awesome Fine-grained Visual Classification
二自由度云台实现人脸追踪。 首先是使用一款名字叫做IP摄像头的APP 采集手机摄像头的图像，在手机上建立一个视频流服务器。在局域网下，PC通过IP还有端口号获取图像。使用OpenCV的人脸检测的API获取人脸在画面中的位置，根据人脸位置距离画面中心的x轴与y轴的偏移量(offset) ，通过P比例控制(PID控制中最简单的一种)控制二自由度云台上臂与下臂的旋转角度，将角度信息通过串口通信UA…
🚀🚀🚀 A collection of some awesome public YOLO object detection series projects.
A curated list of neural network pruning resources.
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…
一些关于目标检测的脚本的改进思路代码，详细请看readme.md