LibfacedetectionAn open source library for face detection in images. The face detection speed can reach 1000FPS.
HyperdensenetThis repository contains the code of HyperDenseNet, a hyper-densely connected CNN to segment medical images in multi-modal image scenarios.
Lenet 5PyTorch implementation of LeNet-5 with live visualization
3d Densenet3D Dense Connected Convolutional Network (3D-DenseNet for action recognition)
DeepwayThis project is an aid to the blind. Till date there has been no technological advancement in the way the blind navigate. So I have used deep learning particularly convolutional neural networks so that they can navigate through the streets.
SppnetSpatial Pyramid Pooling on top of AlexNet using tensorflow. ***New updates for SPPnet in Pytorch**
Aspect ExtractionAspect extraction from product reviews - window-CNN+maxpool+CRF, BiLSTM+CRF, MLP+CRF
Yolo V3 IouYOLO3 动漫人脸检测 (Based on keras and tensorflow) 2019-1-19
Id Card Detector💳 Detecting the National Identification Cards with Deep Learning (Faster R-CNN)
DeepfaceKeras implementation of the renowned publication "DeepFace: Closing the Gap to Human-Level Performance in Face Verification" by Taigman et al. Pre-trained weights on VGGFace2 dataset.
DeepgazeComputer Vision library for human-computer interaction. It implements Head Pose and Gaze Direction Estimation Using Convolutional Neural Networks, Skin Detection through Backprojection, Motion Detection and Tracking, Saliency Map.
Tf2An Open Source Deep Learning Inference Engine Based on FPGA
Mobilenet YoloMobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB🔥🔥🔥
Pwc Net pytorchpytorch implementation of "PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume"
Mnist ClassificationPytorch、Scikit-learn实现多种分类方法,包括逻辑回归(Logistic Regression)、多层感知机(MLP)、支持向量机(SVM)、K近邻(KNN)、CNN、RNN,极简代码适合新手小白入门,附英文实验报告(ACM模板)
Places365The Places365-CNNs for Scene Classification
Min nlp practiceChinese & English Cws Pos Ner Entity Recognition implement using CNN bi-directional lstm and crf model with char embedding.基于字向量的CNN池化双向BiLSTM与CRF模型的网络,可能一体化的完成中文和英文分词,词性标注,实体识别。主要包括原始文本数据,数据转换,训练脚本,预训练模型,可用于序列标注研究.注意:唯一需要实现的逻辑是将用户数据转化为序列模型。分词准确率约为93%,词性标注准确率约为90%,实体标注(在本样本上)约为85%。
Awesome Deep Learning ResourcesRough list of my favorite deep learning resources, useful for revisiting topics or for reference. I have got through all of the content listed there, carefully. - Guillaume Chevalier
Self Driving CarA End to End CNN Model which predicts the steering wheel angle based on the video/image
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.
CodesearchnetDatasets, tools, and benchmarks for representation learning of code.
LesrcnnLightweight Image Super-Resolution with Enhanced CNN (Knowledge-Based Systems,2020)
Etaggerreference tensorflow code for named entity tagging
FacedetectorA re-implementation of mtcnn. Joint training, tutorial and deployment together.
CaptcharecognitionEnd-to-end variable length Captcha recognition using CNN+RNN+Attention/CTC (pytorch implementation). 端到端的不定长验证码识别
Pytorch Pos TaggingA tutorial on how to implement models for part-of-speech tagging using PyTorch and TorchText.
Hyperopt Keras Cnn Cifar 100Auto-optimizing a neural net (and its architecture) on the CIFAR-100 dataset. Could be easily transferred to another dataset or another classification task.
Grad Cam🌈 📷 Gradient-weighted Class Activation Mapping (Grad-CAM) Demo
Libgdl一个移动端跨平台的gpu+cpu并行计算的cnn框架(A mobile-side cross-platform gpu+cpu parallel computing CNN framework)
Snail PytorchImplementation of "A Simple Neural Attentive Meta-Learner" (SNAIL, https://arxiv.org/pdf/1707.03141.pdf) in PyTorch