owllight11
Follow
Stars
[ISSN 0168-1699, COMPUT ELECTRON AGR 2024] FastSegFormer: A knowledge distillation-based method for real-time semantic segmentation of surface defects in navel oranges.
《Pytorch实用教程》（第二版）无论是零基础入门，还是CV、NLP、LLM项目应用，或是进阶工程化部署落地，在这里都有。相信在本书的帮助下，读者将能够轻松掌握 PyTorch 的使用，成为一名优秀的深度学习工程师。
PyTorch implementation of over 30 realtime semantic segmentations models, e.g. BiSeNetv1, BiSeNetv2, CGNet, ContextNet, DABNet, DDRNet, EDANet, ENet, ERFNet, ESPNet, ESPNetv2, FastSCNN, ICNet, LEDN…
Official PyTorch implementation of SegFormer
Pretrained DeepLabv3 and DeepLabv3+ for Pascal VOC & Cityscapes
PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/Docker/Zotero
A DCGAN implementing all the tricks from recent papers up to 2020 and from all over the internet. Trained on CelebA at 157x128. "GAN Hacks 2", if you will.
A scalable template for PyTorch projects, with examples in Image Segmentation, Object classification, GANs and Reinforcement Learning.
Code for evaluating data augmentation methods for GANs
PyTorch deep learning projects made easy.
Multiscale Attention Based Efficient U-Net for Crack Segmentation, segments a RGB image into 2 classes crack and non-crack, this method obtained SOTA results on Crack500 dataset
Neural feels with neural fields: Visuo-tactile perception for in-hand manipulation
《Effective Modern C++》- 完成翻译
A curated list of awesome C++ (or C) frameworks, libraries, resources, and shiny things. Inspired by awesome-... stuff.
An opinionated list of awesome Python frameworks, libraries, software and resources.
Publication-ready NN-architecture schematics.
Latex code for making neural networks diagrams
The book every data scientist needs on their desk.
An open-source cross-platform alternative to AirDrop
Omnivore is a complete, open source read-it-later solution for people who like reading.
Simplified Implementation of SOTA Deep Learning Papers in Pytorch
Dynamic-Pix2Pix: Noise Injected cGAN for Modeling Input and Target Domain Joint Distributions with Limited Training Data
👿 收录了一些能够免费下载油管、B 站、抖音等平台视频的下载工具。Some download tools that can freely download videos from platforms such as YouTube, Bilibili, Douyin, etc. have been included.
📃 开箱即用的 Markdown 简历，支持 VSCode / Obsidian / Typora
CV算法岗知识点及面试问答汇总，主要分为计算机视觉、机器学习、图像处理和 C++基础四大块，一起努力向offers发起冲击！