Shenzhen

duoduo.cat

Elite
@dog-qiuqiu

qiuqiuqiuqiu ...球

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+

2.1k

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

1.7k

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+

937

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

856

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

315

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.

153

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

47

Android_NCNN_yolov4-tiny. yolov4-tiny ncnn android sample

38

yolov3. 支持MobileNetV2-YOLO训练

25

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

22

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

14

libopencv. Opencv ARM Linux precompiled library

14

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。

13

dog-qiuqiu.

3

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

3

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

2

caffe. Add yolov3 upsampler layer

2

websocketpp. C++ websocket client/server library

2

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

2

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

2

RepViT. RepViT: Revisiting Mobile CNN From ViT Perspective

1

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

1

insightface. Face Analysis Project on MXNet and PyTorch

1

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/

1

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

1

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

1

metaRTC. A cross-platform WebRTC SDK

1

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

1

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

1

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

1
30
Apply