Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, GLM4.5, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, Llava, GLM4v, Ph…

Official implementation for AnomalyCLIP (ICLR 2024)

中文nlp解决方案(大模型、数据、模型、训练、推理)

ChatGPT Plus 共享方案。ChatGPT Plus / OpenAI API sharing solution.

The best performance camera pipeline on jetson device. User arugs and vpi. Data pipeline: isp->gpu->vic|pva->gpu|dla

An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.

The simplest, fastest repository for training/finetuning small-sized VLMs.

诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

A Simple PointPillars PyTorch Implementation for 3D LiDAR(KITTI) Detection.

这是一个segformer-pytorch的源码，可以用于训练自己的模型。

C++/CUDA implementation for semantic segmentation inference using TensorRT and the DeepLabV3 model. The project loads an exported ONNX model, runs inference on images, and generates segmentation ma…

ROS 2 packages based on NVIDIA libArgus library for NVIDIA-accelerated CSI camera support.

code for EdgeNAT

Unofficial implementation of "Remembering Normality: Memory-guided Knowledge Distillation for Unsupervised Anomaly Detection"

Pointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Concerto (NeurIPS'25), Sonata (CVPR'25 Highlight), PTv3 (CVPR'24 Oral)

(IEEE TITS 2024) WHU-Railway3D: A Diverse Dataset and Benchmark for Railway Point Cloud Semantic Segmentation

A YAML parser and emitter in C++

Code release for our NeurIPS 2023 paper "Uni3DETR: Unified 3D Detection Transformer", our ECCV 2024 paper "OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propag…

FFA-Net: Feature Fusion Attention Network for Single Image Dehazing

[ICCV 2019] Monocular depth estimation from a single image

c++与python共享内存实现

A devkit for working with recorded and annotated train ride data from Deutsche Bahn.

A PyTorch implementation of simple Mask R-CNN

Monocular Camera Localization in Prior LiDAR Maps with 2D-3D Line Correspondences

一键安装程序，欢迎大家提交代码和小鱼一起一键安装停止浪费生命

Thesis project for Applied Data Science master. Using GANs to artificially generate fog in images for increasing training data.

C++/CUDA/Python multimedia utilities for NVIDIA Jetson