fly-hub Goto Github PK

3d-resnets-pytorch

3D ResNets for Action Recognition (CVPR 2018)

3dresnet

0.2

3dresnet0.2

0.2

awesome-deeplearning

深度学习入门课、资深课、特色课、学术案例、产业实践案例、深度学习知识百科及面试题库The course, case and knowledge of Deep Learning and AI

bibigpt-v1

BibiGPT v1 · one-Click AI Summary for Audio/Video & Chat with Learning Content: Bilibili | YouTube | Tweet丨TikTok丨Dropbox丨Google Drive丨Local files | Websites丨Podcasts | Meetings | Lectures, etc. 音视频内容 AI 一键总结 & 对话：哔哩哔哩丨YouTube丨推特丨小红书丨抖音丨快手丨百度网盘丨阿里云盘丨网页丨播客丨会议丨本地文件等 (原 BiliGPT 省流神器 & AI课代表)

clip4clip

An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"

deblurganv2

[ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang

deep-image-prior

Image restoration with neural networks but without learning.

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

fastimagerecognition

针对样本量少、类别多、新类别增加比较快，不想重训模型这样的情况，用检索的方式去做识别

fly-hub7

2333

minigpt-4

MiniGPT-4: Enhancing Vision-language Understanding with Advanced Large Language Models

minigpt-4-zh

MiniGPT-4 中文部署翻译 完善部署细节

paddle-inference-demo

paddle2onnx

ONNX Model Exporter for PaddlePaddle

paddleclas

A treasure chest for visual recognition powered by PaddlePaddle

paddledetection

Object detection and instance segmentation toolkit based on PaddlePaddle.

paddleocr

Awesome multilingual OCR toolkits based on PaddlePaddle （practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices）

paddleseg

End-to-End Image Segmentation Kits Based on PaddlePaddle. (『飞桨』图像分割开发套件）

paddlevideo

Comprehensive, latest, and deployable video deep learning algorithm, including video recognition, action localization, and temporal action detection tasks. It's a high-performance, light-weight codebase provides practical models for video understanding research and application

paddlevit

:robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+

videoprocessingframework

Set of Python bindings to C++ libraries which provides full HW acceleration for video decoding, encoding and GPU-accelerated color space and pixel format conversions