OpenLabeling

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Image augmentation for machine learning experiments.

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.

Most popular metrics used to evaluate object detection algorithms.

mean Average Precision - This code evaluates the performance of your neural net for object recognition.

? Highly Optimized 2D / 3D Graphics Math (glm) for C

YOLO ROS: Real-Time Object Detection for ROS

implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)