emptysoal

TensorRT-YOLO11. Based on tensorrt v8.0+, deploy detection, pose, segment, tracking of YOLO11 with C++ and python api.

TensorRT-YOLOv8-ByteTrack. An object tracking project with YOLOv8 and ByteTrack, speed up by C++ and TensorRT.

TensorRT-YOLOv8. Based on tensorrt v8.0+, deploy detect, pose, segment, tracking of YOLOv8 with C++ and python api.

cuda-image-preprocess. Speed up image preprocess with cuda when handle image or tensorrt inference

tensorrt-experiment. Base on tensorrt version 8.2.4, compare inference speed for different tensorrt api.

VideoRestore. Enhance video resolution

Deepsort-YOLOv5-TensorRT. An object tracking project with YOLOv5-v5.0 and Deepsort, speed up by C++ and TensorRT.

YOLOv5-TensorRT-lib-Python. The code of YOLOv5 inferencing with TensorRT C++ api is packaged into a dynamic link library , then called through Python.

TensorRT-v8-YOLOv5-v5.0. Based on TensorRT v8.2, build network for YOLOv5-v5.0 by myself, speed up YOLOv5-v5.0 inferencing

keypoint-resnet50. Based on ResNet50, detect keypoint, and use keypoint perspective transform image.

vit-tensorrt. Python

LLM-TRAINING. LLM SFT and RLHF

lstm-torch2trt. Build a simple LSTM example using pytorch, and then convert the model in pytorch format to onnx and tensorrt format, in turn.

Coco-Mask-Transform. Coco标注格式和Mask标注格式相互转换

concurrent_communion. python socket concurrent mysql

vLLM-Milvus-RAG. Implement RAG using vLLM + Milvus

PyTorch-Resnet. PyTorch-Resnet

Kafka-Docker-Python. 使用docker构建kafka环境，并通过python调用kafka接口

mask-rcnn-pytorch. Python

Flask-Gunicorn-Nginx. Flask配合Nginx部署示例

text-generation-webui-customized. text generation webui customized

RabbitMQ-Docker-Python. 在docker中分别构建rabbitMQ和python环境，并通过python调用rabbitMQ

MultiModal-RAG. A multimodal RAG system that achieves a complete closed loop of mixed understanding of text and images, intelligent routing, and visual interaction.

Advanced-RAG. A variety of different rag schemes have been implemented using workflow and agent