2239891257 Goto Github PK

aicity2021_track2_dmt

The 1st place solution of track2 (Vehicle Re-Identification) in the NVIDIA AI City Challenge at CVPR 2021 Workshop.

baby-llama2-chinese

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

citypersons

bounding box annotations, python evaluation code, and a benchmark for CityPersons

deep-learning-for-image-processing

deep learning for image processing including classification and object-detection etc.

deep-person-reid

Torchreid: Deep learning person re-identification in PyTorch.

external-attention-pytorch

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

gpt-computer-assistant

gpt-4o for windows, macos and ubuntu

ibn-net

Instance-Batch Normalization Networks (ECCV2018)

imgaug

Image augmentation for machine learning experiments.

market1501evaluation

Evaluation codes for Market-1501 Person Re-ID Dataset

mfd

Multispectral Feature Descriptor (MFD).

myreidproject

paddleocr

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

pedestron

[Pedestron] Generalizable Pedestrian Detection: The Elephant In The Room. @ CVPR2021

piafusion

This is official tensorflow implementation of “PIAFusion: A Progressive Infrared and Visible Image Fusion Network Based on Illumination Aware”

superyolo

SuperYOLO

tensorrt-for-yolo-series

tensorrt for yolo series (YOLOv10,YOLOv9,YOLOv8,YOLOv7,YOLOv6,YOLOX,YOLOv5), nms plugin support

ultra-fast-lane-detection

Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)

yoloair

🔥🔥🔥YOLOAir：Including YOLOv5, YOLOv7, Transformer, YOLOX, YOLOR and other networks... Support to improve backbone, head, loss, IoU, NMS...The original version was created based on YOLOv5

yolov5_research

add yolov7 core ,improvement research based on yolov5,SwintransformV2 and Attention Series. training skills, business customization, engineering deployment C