Alex S. Liu's repositories
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
AutoShot
AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary Detection - CVPR NAS 2023
bevfusion
BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation
ChatGLM-6B
ChatGLM-6B：开源双语对话语言模型 | An Open Bilingual Dialogue Language Model
Chinese-CLIP
Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.
CLIP
Contrastive Language-Image Pretraining
ColossalAI
Making big AI models cheaper, easier, and scalable
DeepSpeedExamples
Example models using DeepSpeed
DINO
Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"
dolly
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
E2FGVI
Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)
face_recognition
The world's simplest facial recognition api for Python and the command line
frame-interpolation
FILM: Frame Interpolation for Large Motion, In ECCV 2022.
Grounded-Segment-Anything
Marrying Grounding DINO with Segment Anything & Stable Diffusion & BLIP & Whisper & ChatBot - Automatically Detect , Segment and Generate Anything with Image, Text, and Audio Inputs
MOSS
An open-source tool-augmented conversational language model from Fudan University
Open-Assistant
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
open_clip
An open source implementation of CLIP.
PySceneDetect
:movie_camera: Python and OpenCV-based scene cut/transition detection program & library.
recognize-anything
Code for the Recognize Anything Model (RAM) and Tag2Text Model
Segment-Everything-Everywhere-All-At-Once
Official implementation of the paper "Segment Everything Everywhere All at Once"
stanford_alpaca
Code and documentation to train Stanford's Alpaca models, and generate the data.
summarize-from-feedback
Code for "Learning to summarize from human feedback"
Text2LIVE
Official Pytorch Implementation for "Text2LIVE: Text-Driven Layered Image and Video Editing" (ECCV 2022 Oral)
Track-Anything
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.
TransNetV2
TransNet V2: Shot Boundary Detection Neural Network
trlx
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
VideoX
VideoX: a collection of video cross-modal models
Yolov5_DeepSort_Pytorch
Real-time multi-object tracker using YOLO v5 and deep sort