Pinned Repositories
3d-ai-powered-pose-tracking
Adam-experiments
Experiments with Adam/AdamW/amsgrad
Algorithm_Interview_Notes-Chinese
2018/2019/校招/春招/秋招/算法/机器学习(Machine Learning)/深度学习(Deep Learning)/自然语言处理(NLP)/C/C++/Python/面试笔记
AndroidFaceDetection
Android 平台进行人脸检测的几种方案
annotated_deep_learning_paper_implementations
🧑🏫 59 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
AUNets
Multi-View Dynamic Facial Action Unit Detection
Basic_CNNs_TensorFlow2
A tensorflow2 implementation of some basic CNNs(MobileNetV1/V2/V3, EfficientNet, ResNeXt, InceptionV4, InceptionResNetV1/V2, SENet, SqueezeNet, DenseNet, ShuffleNetV2, ResNet).
face_classification
In this R&D Project we propose to implement a general convolutional neural network (CNN) building framework for designing real-time CNNs. We validate our models by creating a real-time vision system which accomplishes the tasks of face detection, gender classification and emotion classification simultaneously in one blended step using our proposed CNN architecture. After presenting the details of the training procedure setup we proceed to evaluate on standard benchmark sets. We report accuracies of 93% in the IMDB gender dataset and 65.67% in the FER-2013 emotion dataset. The GEMEP-FERA database is a subset of the GEMEP corpus used as database for the FERA 2011 challenge It consists of recordings of 10 actors displaying a range of expressions. There are seven subjects in the training data, and six subjects in the test set. The training set contains 155 image sequences and the testing contains 134 image sequences. There are in total five emotion categories in the database: Anger, Fear, Happiness, Relief and Sadness. We extract static frames from the sequences with six basic expressions, which resulted to in around 7,000 images. We have proposed and tested a general building designs for creating real-time CNNs. Our proposed architectures have been systematically built in order to reduce the number of parameters. We began by eliminating completely the fully connected layers and by reducing the number of parameters in the remaining convolutional layers via depth-wise separable convolutions. We have shown that our proposed models can be stacked for multi-class classifications while maintaining real-time inferences. Specifically, we have developed a vision system that performs face detection, gender classification and emotion classification in a single integrated module. We have achieved human-level performance in our classifications tasks using a single CNN that leverages modern architecture constructs.
FERA_HCOE
yolo-android
CNN YOLO R&D Project for Android
xieshenru's Repositories
xieshenru/FERA_HCOE
xieshenru/yolo-android
CNN YOLO R&D Project for Android
xieshenru/3d-ai-powered-pose-tracking
xieshenru/Adam-experiments
Experiments with Adam/AdamW/amsgrad
xieshenru/Algorithm_Interview_Notes-Chinese
2018/2019/校招/春招/秋招/算法/机器学习(Machine Learning)/深度学习(Deep Learning)/自然语言处理(NLP)/C/C++/Python/面试笔记
xieshenru/annotated_deep_learning_paper_implementations
🧑🏫 59 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
xieshenru/AUNets
Multi-View Dynamic Facial Action Unit Detection
xieshenru/Basic_CNNs_TensorFlow2
A tensorflow2 implementation of some basic CNNs(MobileNetV1/V2/V3, EfficientNet, ResNeXt, InceptionV4, InceptionResNetV1/V2, SENet, SqueezeNet, DenseNet, ShuffleNetV2, ResNet).
xieshenru/CenterMulti
基于CenterNet训练的目标检测&人脸对齐&姿态估计模型
xieshenru/Chinese-number-gestures-recognition
基于卷积神经网络的数字手势识别安卓APP，识别数字手势0-10（The number gestures recognition Android APP based on convolutional neural network(CNN), which can recognize the gestures corresponding number 0 to 10）
xieshenru/CNNGestureRecognizer
Gesture recognition via CNN. Implemented in Keras + Theano + OpenCV
xieshenru/cs231n-camp
cs231n training camp
xieshenru/DeepLearning_ObjectRecognition
[Deep Learning] Object Recognition (深度学习:目标检测与识别—复杂环境下的Logo识别) RCNN、TensorFlow
xieshenru/DeepLearning_tutorials
The deeplearning algorithms implemented by tensorflow
xieshenru/docker_practice
Learn and understand Docker technologies, with real DevOps practice!
xieshenru/emotion_classifier
emotion classifier based on kaggle fer2013
xieshenru/eos
A lightweight 3D Morphable Face Model fitting library in modern C++11/14
xieshenru/External-Attention-pytorch
🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐
xieshenru/face-alignment
:fire: 2D and 3D Face alignment library build using pytorch
xieshenru/face-mask-detection-tf2
A face mask detection using ssd with simplified Mobilenet and RFB or Pelee in Tensorflow 2.1. Training on your own dataset. Can be converted to kmodel and run on the edge device of k210
xieshenru/facenet
Face recognition using Tensorflow
xieshenru/FERA17Challenge-Keras
Keras-in-TensorFlow-workflow models for Facial Expression Recognition and Analysis (FERA) challenge 2017.
xieshenru/image-to-image-papers
A collection of image to image papers
xieshenru/imgaug
Image augmentation for machine learning experiments.
xieshenru/JAANet
ECCV 2018 "Deep Adaptive Attention for Joint Facial Action Unit Detection and Face Alignment"
xieshenru/manutdzou.github.io
xieshenru/MaskInsightface
基于人脸关键区域提取的人脸识别（LFW:99.82%+ CFP_FP:98.50%+ AgeDB30:98.25%+）
xieshenru/TF-image
TensorFlow识别物体
xieshenru/transferlearning
Everything about Transfer Learning and Domain Adaptation--迁移学习
xieshenru/YOLOV3-on-Android