47,133 repositories indexed
1–24 of 31 · Most stars
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python
Machine learning, in numpy
Face recognition with deep neural networks.
Face recognition using Tensorflow
TranslatedUltra-lightweight Chinese OCR, supports vertical text recognition, supports ncnn, mnn, and tnn inference (dbnet (1.8M) + crnn (2.5M) + anglenet (378KB)), total model size only 4.7M
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.
Deep Learning and Reinforcement Learning Library for Scientists and Engineers
Statistical Machine Intelligence & Learning Engine
A TensorFlow implementation of DeepMind's WaveNet paper
Translated[Captcha Recognition - Training] This project is based on CNN/ResNet/DenseNet+GRU/LSTM+CTC/CrossEntropy to realize verification code identification. This project is only for training the model.
Deep neural network to extract intelligent information from invoice documents.
simple neural network library in C99
Genetic Programming in Python, with a scikit-learn inspired API
PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)
Library for Fast and Flexible Human Pose Estimation
SuMa++: Efficient LiDAR-based Semantic SLAM (Chen et al IROS 2019)
High level network definitions with pre-trained weights in TensorFlow
PyTorch to Keras model convertor
A toolbox of AI modules written in Swift: Graphs/Trees, Support Vector Machines, Neural Networks, PCA, K-Means, Genetic Algorithms
The MobileNet neural network using Apple's new CoreML framework
Hyperparameter optimization and feature selection for scikit-learn using evolutionary algorithms. A modern alternative to GridSearchCV and RandomizedSearchCV.
Inference module for RangeNet++ (milioto2019iros, chen2019iros)