dog-qiuqiu

qiuqiuqiuqiu ...球

BTBUGuangzhou

Pinned Repositories

Android_MobileNetV2-YOLOV3-Nano-NCNN
MobileNetV2-YOLOV3-Nano NCNN sample
Language:C++21 5 213
Android_NCNN_yolov4-tiny
yolov4-tiny ncnn android sample
Language:C++38 5 517
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
Language:Python745 12 38131
MobileNet-Yolo
MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire:
Language:C1.7k 34 34275
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
Language:C++41 3 16
Simple-TensorRT
Secondary encapsulation of NVIDIA TensorRT interface to simplify the calling process
Language:C++8 2 01
Ultralight-SimplePose
Ultra-lightweight human body posture key point CNN model. ModelSize:2.3MB HUAWEI P40 NCNN benchmark: 6ms/img,
Language:Python275 13 1063
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+
Language:C2k 49 72428
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+
Language:Python784 16 76191
yolov3
支持MobileNetV2-YOLO训练
Language:Jupyter Notebook23 2 08

dog-qiuqiu's Repositories

dog-qiuqiu/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+
Language:C2k 49 72428
dog-qiuqiu/MobileNet-Yolo
MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire:
Language:C1.7k 34 34275
dog-qiuqiu/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+
Language:Python784 16 76191
dog-qiuqiu/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
Language:Python745 12 38131
dog-qiuqiu/Ultralight-SimplePose
Ultra-lightweight human body posture key point CNN model. ModelSize:2.3MB HUAWEI P40 NCNN benchmark: 6ms/img,
Language:Python275 13 1063
dog-qiuqiu/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
Language:C++41 3 16
dog-qiuqiu/libopencv
Opencv ARM Linux precompiled library
Language:C++11 2 05
dog-qiuqiu/Simple-TensorRT
Secondary encapsulation of NVIDIA TensorRT interface to simplify the calling process
Language:C++8 2 01
dog-qiuqiu/ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Language:C++3 1 0
dog-qiuqiu/darknet
YOLOv4 - Neural Networks for Object Detection (Windows and Linux version of Darknet )
Language:C2 1 01
dog-qiuqiu/dog-qiuqiu
2 2 01
dog-qiuqiu/openpose
OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation
Language:C++2 1 01
dog-qiuqiu/insightface
Face Analysis Project on MXNet and PyTorch
Language:Python1 1 0
dog-qiuqiu/RepViT
RepViT: Revisiting Mobile CNN From ViT Perspective
Language:Python1 1 0
dog-qiuqiu/websocketpp
C++ websocket client/server library
Language:C++1 1 0
dog-qiuqiu/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/
Language:Python1 1 0
dog-qiuqiu/clean-fid
PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]
Language:Python1 0
dog-qiuqiu/cmdbug
😊 Hello
1 0
dog-qiuqiu/cocoapi
COCO API - Dataset @ http://cocodataset.org/
Language:Jupyter Notebook1 0
dog-qiuqiu/ComputeLibrary
The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.
dog-qiuqiu/Deep3DFaceRecon_pytorch
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019). A PyTorch implementation.
Language:Python0 0
dog-qiuqiu/FaceFormer
[CVPR 2022] FaceFormer: Speech-Driven 3D Facial Animation with Transformers
Language:Python1 0
dog-qiuqiu/metaRTC
A cross-platform WebRTC SDK
Language:C1 0
dog-qiuqiu/minio-cpp
MinIO C++ Client SDK for Amazon S3 Compatible Cloud Storage
Language:C++0 0
dog-qiuqiu/ncnn-android-yolox
Real time yolox Android demo by ncnn
Language:C++1 02
dog-qiuqiu/nvidia-container-toolkit
Build and run containers leveraging NVIDIA GPUs
Language:Go1 0
dog-qiuqiu/pear
WebRTC Library for IoT/Embedded Device using C
Language:C1 0
dog-qiuqiu/PFLD-pytorch
PFLD pytorch Implementation
Language:Python1 0
dog-qiuqiu/visdom
A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.
Language:Python1 0
dog-qiuqiu/Wav2Lip
This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020.
Language:Python1 0