Use PEFT or Full-parameter to finetune 450+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek-R1, ...) and 150+ MLLMs (Qwen2.5-VL, Qwen2-Audio, Llama3.2-Vision, Llava, I…

A project demonstrating Lidar related AI solutions, including three GPU accelerated Lidar/camera DL networks (PointPillars, CenterPoint, BEVFusion) and the related libs (cuPCL, 3D SparseConvolution…

[ICCV 2023] DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds

Official PyTorch implementation of FB-BEV & FB-OCC - Forward-backward view transformation for vision-centric autonomous driving perception

This is Pytorch re-implementation of our CVPR 2020 paper "Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation" (https://arxiv.org/abs/1911.10194)

Instant neural graphics primitives: lightning fast NeRF and more

google/draco bindings for Go

An autoregressive character-level language model for making more things

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Research code for ECCV 2020 paper "UNITER: UNiversal Image-TExt Representation Learning"

Learning Superpixels with Segmentation-Aware Affinity Loss

DEL: Deep Embedding Learning for Efficient Image Segmentation

Convolutional Oriented Boundaries

A faster pytorch implementation of faster r-cnn

Direct Sparse Odometry

Pre-trained Deep Learning models and demos (high quality and extremely fast)

Pytorch implementation of FlowNet by Dosovitskiy et al.

Python implementation of paper Active Contour Without Edges

Active contour model (aka snakes) implemented in python.

A Robust and Versatile Monocular Visual-Inertial State Estimator

We are aimed at making a device for shooting real-time HDR (High Dynamic Range) video using FPGA.

A particle filter for tracking multiple humans in high-density crowds

Caffe: a fast open framework for deep learning.

An Open-Source Package for Deep Learning to Hash (DeepHash)

💬 A better WeChat on macOS and Linux. Built with Electron by Zhongyi Tong.

Faster-RCNN in Tensorflow