Keras Oneclassanomalydetection[5 FPS - 150 FPS] Learning Deep Features for One-Class Classification (AnomalyDetection). Corresponds RaspberryPi3. Convert to Tensorflow, ONNX, Caffe, PyTorch. Implementation by Python + OpenVINO/Tensorflow Lite.
Stars: ✭ 102 (+9.68%)
Caffe MobileOptimized (for size and speed) Caffe lib for iOS and Android with out-of-the-box demo APP.
Stars: ✭ 316 (+239.78%)
CnnforandroidThe Convolutional Neural Network(CNN) for Android
Stars: ✭ 245 (+163.44%)
LiteflownetLiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation, CVPR 2018 (Spotlight paper, 6.6%)
Stars: ✭ 474 (+409.68%)
Caffe HrtHeterogeneous Run Time version of Caffe. Added heterogeneous capabilities to the Caffe, uses heterogeneous computing infrastructure framework to speed up Deep Learning on Arm-based heterogeneous embedded platform. It also retains all the features of the original Caffe architecture which users deploy their applications seamlessly.
Stars: ✭ 271 (+191.4%)
Mobilenetv2A Keras implementation of MobileNetV2.
Stars: ✭ 277 (+197.85%)
Hidden Two StreamCaffe implementation for "Hidden Two-Stream Convolutional Networks for Action Recognition"
Stars: ✭ 179 (+92.47%)
FacedetectionC++ project to implement MTCNN, a perfect face detect algorithm, on different DL frameworks. The most popular frameworks: caffe/mxnet/tensorflow, are all suppported now
Stars: ✭ 255 (+174.19%)
Liteflownet2A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization, TPAMI 2020
Stars: ✭ 195 (+109.68%)
Dispnet Flownet DockerDockerfile and runscripts for DispNet and FlowNet1 (estimation of disparity and optical flow)
Stars: ✭ 78 (-16.13%)
Jacinto Ai DevkitTraining & Quantization of embedded friendly Deep Learning / Machine Learning / Computer Vision models
Stars: ✭ 49 (-47.31%)
Face Mask DetectionFace Mask Detection system based on computer vision and deep learning using OpenCV and Tensorflow/Keras
Stars: ✭ 774 (+732.26%)
Mobilenet CaffeCaffe Implementation of Google's MobileNets (v1 and v2)
Stars: ✭ 1,217 (+1208.6%)
Mobilenetv2 SsdliteCaffe implementation of SSD and SSDLite detection on MobileNetv2, converted from tensorflow.
Stars: ✭ 435 (+367.74%)
Object LocalizationObject localization in images using simple CNNs and Keras
Stars: ✭ 130 (+39.78%)
Mobilenet YoloMobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB🔥🔥🔥
Stars: ✭ 1,566 (+1583.87%)
Tf Pose EstimationDeep Pose Estimation implemented using Tensorflow with Custom Architectures for fast inference.
Stars: ✭ 3,856 (+4046.24%)
NoisefaceNoise-Tolerant Paradigm for Training Face Recognition CNNs
Stars: ✭ 132 (+41.94%)
Flownet2 DockerDockerfile and runscripts for FlowNet 2.0 (estimation of optical flow)
Stars: ✭ 137 (+47.31%)
In PrestissimoA very fast neural network computing framework optimized for mobile platforms.QQ group: 676883532 【验证信息输:绝影】
Stars: ✭ 268 (+188.17%)
Flownet2FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Stars: ✭ 938 (+908.6%)
Haddoc2Caffe to VHDL
Stars: ✭ 57 (-38.71%)
SleepeegnetSleepEEGNet: Automated Sleep Stage Scoring with Sequence to Sequence Deep Learning Approach
Stars: ✭ 89 (-4.3%)
Deep Learning Training GuiTrain and predict your model on pre-trained deep learning models through the GUI (web app). No more many parameters, no more data preprocessing.
Stars: ✭ 85 (-8.6%)
Caffe ModelCaffe models (including classification, detection and segmentation) and deploy files for famouse networks
Stars: ✭ 1,258 (+1252.69%)
Mobilenet SsdMobileNet-SSD(MobileNetSSD) + Neural Compute Stick(NCS) Faster than YoloV2 + Explosion speed by RaspberryPi · Multiple moving object detection with high accuracy.
Stars: ✭ 84 (-9.68%)
Mars腾讯移动 Web 前端知识库
Stars: ✭ 9,255 (+9851.61%)
Wb color augmenterWB color augmenter improves the accuracy of image classification and image semantic segmentation methods by emulating different WB effects (ICCV 2019) [Python & Matlab].
Stars: ✭ 89 (-4.3%)
Single Human Parsing LipPSPNet implemented in PyTorch for single-person human parsing task, evaluating on Look Into Person (LIP) dataset.
Stars: ✭ 84 (-9.68%)
CfsrcnnCoarse-to-Fine CNN for Image Super-Resolution (IEEE Transactions on Multimedia,2020)
Stars: ✭ 84 (-9.68%)
Onnx ChainerAdd-on package for ONNX format support in Chainer
Stars: ✭ 83 (-10.75%)
WcdbWCDB is a cross-platform database framework developed by WeChat.
Stars: ✭ 9,264 (+9861.29%)
Core50CORe50: a new Dataset and Benchmark for Continual Learning
Stars: ✭ 91 (-2.15%)
Fast AutoaugmentOfficial Implementation of 'Fast AutoAugment' in PyTorch.
Stars: ✭ 1,297 (+1294.62%)
Ant Design MobileFluent and powerful mobile component library based on React.
Stars: ✭ 9,489 (+10103.23%)
DltkDeep Learning Toolkit for Medical Image Analysis
Stars: ✭ 1,249 (+1243.01%)
Cnn FixationsVisualising predictions of deep neural networks
Stars: ✭ 87 (-6.45%)
MinibaeThe platform-neutral Beatnik Audio Engine, Mini Edition (miniBAE) is an exceptionally mature, well-rounded, and reliable computer music and sound system specially customized for small-footprint and embedded applications.
Stars: ✭ 82 (-11.83%)
PytorchPyTorch tutorials A to Z
Stars: ✭ 87 (-6.45%)
SeganA PyTorch implementation of SEGAN based on INTERSPEECH 2017 paper "SEGAN: Speech Enhancement Generative Adversarial Network"
Stars: ✭ 82 (-11.83%)
SwipeA plugin for Unreal Engine 4 that exposes swipes on mobile devices as events in blueprint.
Stars: ✭ 91 (-2.15%)
Ncnn MtcnnIt is a mtcnn project based on ncnn
Stars: ✭ 91 (-2.15%)
React Native OnesignalReact Native Library for OneSignal Push Notifications Service
Stars: ✭ 1,270 (+1265.59%)
Recursive CnnsImplementation of my paper "Real-time Document Localization in Natural Images by Recursive Application of a CNN."
Stars: ✭ 80 (-13.98%)