optimizerActively maintained ONNX Optimizer
Stars: ✭ 383 (+424.66%)
object-trackingMultiple Object Tracking System in Keras + (Detection Network - YOLO)
Stars: ✭ 89 (+21.92%)
keras openvinoHow to run Keras model inference x3 times faster with CPU and Intel OpenVINO
Stars: ✭ 32 (-56.16%)
ZmmagikPost processing video magic with ZoneMinder: find missing objects, blend multiple events, annotate videos, and more
Stars: ✭ 153 (+109.59%)
Gluon2pytorchGluon to PyTorch deep neural network model converter
Stars: ✭ 70 (-4.11%)
ros openvinoA ROS package to wrap openvino inference engine and get it working with Myriad and GPU
Stars: ✭ 57 (-21.92%)
Rotate Yolov3Arbitrary oriented object detection implemented with yolov3 (attached with some tricks).
Stars: ✭ 150 (+105.48%)
concurrent-video-analytic-pipeline-optimization-sample-lCreate a concurrent video analysis pipeline featuring multistream face and human pose detection, vehicle attribute detection, and the ability to encode multiple videos to local storage in a single stream.
Stars: ✭ 39 (-46.58%)
Yolov3yolov3 by pytorch
Stars: ✭ 142 (+94.52%)
safety-gear-detector-pythonObserve workers as they pass in front of a camera to determine if they have adequate safety protection.
Stars: ✭ 54 (-26.03%)
finn-baseOpen Source Compiler Framework using ONNX as Frontend and IR
Stars: ✭ 21 (-71.23%)
object-size-detector-pythonMonitor mechanical bolts as they move down a conveyor belt. When a bolt of an irregular size is detected, this solution emits an alert.
Stars: ✭ 26 (-64.38%)
AnimeGANv3Use AnimeGANv3 to make your own animation works, including turning photos or videos into anime.
Stars: ✭ 878 (+1102.74%)
CullNetCode implementation of our paper "CullNet: Calibrated and Pose Aware Confidence Scores for Object Pose Estimation"
Stars: ✭ 13 (-82.19%)
Pytorch Imagenet Cifar Coco Voc TrainingTraining examples and results for ImageNet(ILSVRC2012)/CIFAR100/COCO2017/VOC2007+VOC2012 datasets.Image Classification/Object Detection.Include ResNet/EfficientNet/VovNet/DarkNet/RegNet/RetinaNet/FCOS/CenterNet/YOLOv3.
Stars: ✭ 130 (+78.08%)
R-YOLOv4This is a PyTorch-based R-YOLOv4 implementation which combines YOLOv4 model and loss function from R3Det for arbitrary oriented object detection.
Stars: ✭ 61 (-16.44%)
Darknet2caffeConvert darknet weights to caffemodel
Stars: ✭ 127 (+73.97%)
Onnxt5Summarization, translation, sentiment-analysis, text-generation and more at blazing speed using a T5 version implemented in ONNX.
Stars: ✭ 143 (+95.89%)
Pytorch face landmarkFast and accurate face landmark detection library using PyTorch; Support 68-point semi-frontal and 39-point profile landmark detection; Support both coordinate-based and heatmap-based inference; Up to 100 FPS landmark inference speed with SOTA face detector on CPU.
Stars: ✭ 388 (+431.51%)
Tengine-Convert-ToolsTengine Convert Tool supports converting multi framworks' models into tmfile that suitable for Tengine-Lite AI framework.
Stars: ✭ 89 (+21.92%)
Deep sort yolov3Real-time Multi-person tracker using YOLO v3 and deep_sort with tensorflow
Stars: ✭ 1,590 (+2078.08%)
pytorch2kerasPyTorch to Keras model convertor
Stars: ✭ 788 (+979.45%)
Deep sort pytorchMOT using deepsort and yolov3 with pytorch
Stars: ✭ 1,948 (+2568.49%)
UdacityThis repo includes all the projects I have finished in the Udacity Nanodegree programs
Stars: ✭ 57 (-21.92%)
AdvboxAdvbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models. Advbox give a command line tool to generate adversarial examples with Zero-Coding.
Stars: ✭ 1,055 (+1345.21%)
Object Detection And Distance MeasurementUsing yolov3 & yolov4 weights objects are being detected from live video frame along with the measurement of the object from the camera without the support of any extra hardware device.
Stars: ✭ 115 (+57.53%)
Paddle-YOLOv4Paddle-YOLOv4,supports training, at least 41.1% mAP.支持训练,至少41.1%mAP。少数的给出精度的复现。
Stars: ✭ 40 (-45.21%)
yolorimplementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)
Stars: ✭ 1,867 (+2457.53%)
Mobilenet YoloMobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB🔥🔥🔥
Stars: ✭ 1,566 (+2045.21%)
NetronVisualizer for neural network, deep learning, and machine learning models
Stars: ✭ 17,193 (+23452.05%)
AgentOCR一个多语言支持、易使用的 OCR 项目。An easy-to-use OCR project with multilingual support.
Stars: ✭ 98 (+34.25%)
yolov3-pytorchannotation and specification for yolov3
Stars: ✭ 48 (-34.25%)
flexible-yolov5More readable and flexible yolov5 with more backbone(resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer) and (cbam,dcn and so on), and tensorrt
Stars: ✭ 282 (+286.3%)
Yolov3 tensorflowComplete YOLO v3 TensorFlow implementation. Support training on your own dataset.
Stars: ✭ 1,498 (+1952.05%)
Yolov5Efficient implementation of YOLOV5 in TensorFlow2
Stars: ✭ 146 (+100%)
yolov5 deepsort tensorrt cppThis repo is a C++ version of yolov5_deepsort_tensorrt. Packing all C++ programs into .so files, using Python script to call C++ programs further.
Stars: ✭ 21 (-71.23%)
yolov5 rotationrotated bbox detection. inspired by https://github.com/hukaixuan19970627/YOLOv5_DOTA_OBB, thanks hukaixuan19970627.
Stars: ✭ 51 (-30.14%)
Mlnet WorkshopML.NET Workshop to predict car sales prices
Stars: ✭ 29 (-60.27%)
onnx-registryIntelligent Component Registry web service for managing and using snn, dnn, and ml models, which is stored in onnx format.
Stars: ✭ 21 (-71.23%)
lightDenseYOLOA real-time object detection app based on lightDenseYOLO Our lightDenseYOLO is the combination of two components: lightDenseNet as the CNN feature extractor and YOLO v2 as the detection module
Stars: ✭ 20 (-72.6%)
OpenseefaceRobust realtime face and facial landmark tracking on CPU with Unity integration
Stars: ✭ 216 (+195.89%)
Kaldi OnnxKaldi model converter to ONNX
Stars: ✭ 174 (+138.36%)
MivisionxMIVisionX toolkit is a set of comprehensive computer vision and machine intelligence libraries, utilities, and applications bundled into a single toolkit. AMD MIVisionX also delivers a highly optimized open-source implementation of the Khronos OpenVX™ and OpenVX™ Extensions.
Stars: ✭ 100 (+36.99%)
DistillerNeural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller
Stars: ✭ 3,760 (+5050.68%)
emnist dl2prodJuPyter Notebooks and Python Package for Deep Learning Model Exploration, Translation and Deployment
Stars: ✭ 31 (-57.53%)
Datasets2DarknetModular tool that extracts images and labels from multiple datasets and parses them to Darknet format.
Stars: ✭ 31 (-57.53%)