This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization" ICCV 2023
Repository Index
140,194 visible repositories in the index
73–96 of 229 · Most stars
Accurately separates a URL’s subdomain, domain, and public suffix, using the Public Suffix List (PSL).
- python
- tldextract
- country-codes
- suffix
Baidu's open-source Sentiment Analysis System.
- natural-language-processing
- sentiment-analysis
- sentiment-classification
- paddlepaddle
Official implementation of "Separate Anything You Describe"
高清仪表盘图标(1024x1024 分辨率)
- dashboard
- high-definition
- icons
- icons-pack
基于PaddleOCR重构,并且脱离PaddlePaddle深度学习训练框架的轻量级OCR,推理速度超快 —— A lightweight OCR system based on PaddleOCR, decoupled from the PaddlePaddle deep learning training framework, with ultra-fast inference speed.
- document-layout-analysis
- license-plate-recognition
- ocr
- onnx-models
Scalable data pre processing and curation toolkit for LLMs
- data-curation
- llm
- data
- data-prep
Web interface for managing Haproxy, Nginx, Apache and Keepalived servers
- haproxy-servers
- web-interface
- management
- web-manager
An unofficial client for the Google Keep API.
- google-keep
- python
- google-api
novel deep learning research works with PaddlePaddle
- deep-learning
- computer-vision
- nlp
- knowledge-graph
Speedy Wavenet generation using dynamic programming :zap:
- deep-learning
- machine-learning
- tensorflow
- wavenet
FSL-Mate: A collection of resources for few-shot learning (FSL).
- few-shot-learning
- one-shot-learning
- meta-learning
- low-shot
Vocal Remover using Deep Neural Networks
- deep-learning
- spectrogram
- audio
- pytorch
[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
- diffusion-models
- diffusion
The official collection of Notepad++ plugins.
Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video tagging and sport action detection.
- video-recognition
- tsm
- slowfast
- tsn
The repository host gives no description.
Machine learning with dataframes
- machine-learning
- data-science
- data-cleaning
- data
Repository for training models for music source separation.
Open-source AI video replacement workflow by TEIN. Combine depth maps, SAM segmentation, face meshes, and audio processing to replace characters and objects with Seedance. Includes a local web UI to prepare inputs, review masks, preview generations, and export with original audio.
PaddleSlim is an open-source library for deep model compression and architecture search.
- pruning
- quantization
- nas
- bert
AuK: An Open-Source Foundational Model for Speech Generation and Editing
- foundation-models
- python
- pytorch
- separation
Allows you to maintain all the necessary cruft for packaging and building projects separate from the code you intentionally write. Built on-top of, and fully compatible with, CookieCutter.
- python
- cruft
- python3
- cookiecutter
make ASCII Art by Deep Learning
- deep-learning
- keras
- tensorflow
- ascii-art