duoduo.cat

Yolo-Fastest. :zap: Based on yolo's ultra-lightweight universal target detection algorithm, the calculation amount is only 250mflops, the ncnn model size is only 666kb, the Raspberry Pi 3b can run up to 15fps+, and the mobile terminal can run up to 178fps+

MobileNet-Yolo. MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire:

Yolo-FastestV2. :zap: Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+

FastestDet. :zap: A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler

Ultralight-SimplePose. Ultra-lightweight human body posture key point CNN model. ModelSize:2.3MB HUAWEI P40 NCNN benchmark: 6ms/img,

invincat. A native Python agent CLI built on DeepAgents CLI, featuring an independent memory Agent that captures learnings after each task and delivers efficient AI coding assistance through hierarchical memory management.

simple-rknn2. The rknn2 API uses the secondary encapsulation of the process, which is easy for everyone to call. It is applicable to rk356x rk3588

Android_NCNN_yolov4-tiny. yolov4-tiny ncnn android sample

yolov3. 支持MobileNetV2-YOLO训练

Android_MobileNetV2-YOLOV3-Nano-NCNN. MobileNetV2-YOLOV3-Nano NCNN sample

Simple-TensorRT. Secondary encapsulation of NVIDIA TensorRT interface to simplify the calling process

libopencv. Opencv ARM Linux precompiled library

YOLOv5_NCNN. 🍅 移动端部署，支持YOLOv5s、YOLOv4-tiny、MobileNetV2-YOLOv3-nano、Simple-Pose与Yolact模型，支持iOS、Android，使用NCNN框架。

dog-qiuqiu.

ncnn. ncnn is a high-performance neural network inference framework optimized for the mobile platform

darknet. YOLOv4 - Neural Networks for Object Detection (Windows and Linux version of Darknet )

caffe. Add yolov3 upsampler layer

websocketpp. C++ websocket client/server library

openpose. OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

DBFace. DBFace is a real-time, single-stage detector for face detection, with faster speed and higher accuracy

RepViT. RepViT: Revisiting Mobile CNN From ViT Perspective

Face-Detector-1MB-with-landmark. 1M人脸检测模型(含关键点)

insightface. Face Analysis Project on MXNet and PyTorch

YOLOX. YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

cocodata_yolo_train. coco2017数据集官方json标签文件转yolo训练的txt标签文件

ComputeLibrary. The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.

metaRTC. A cross-platform WebRTC SDK

nvidia-container-toolkit. Build and run containers leveraging NVIDIA GPUs

3DDFA-V3. The official implementation of 3DDFA_V3 in CVPR2024 (Highlight).

ncnn-android-yolox. Real time yolox Android demo by ncnn