Stars
Kubernetes-native AI serving platform for scalable model serving.
C++ library based on tensorrt integration
Implementation of popular deep learning networks with TensorRT network definition API
🤘 awesome-semantic-segmentation
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
mean Average Precision - This code evaluates the performance of your neural net for object recognition.
yolov5 + csl_label.(Oriented Object Detection)（Rotation Detection）（Rotated BBox）基于yolov5的旋转目标检测
All-in-One Development Tool based on PaddlePaddle
Spatio-Temporal Action Localization System
Set of methods to ensemble boxes from different object detection models, including implementation of "Weighted boxes fusion (WBF)" method.
The world's simplest facial recognition api for Python and the command line
Context-aware RCNN: a Baseline for Action Detection in Videos
YOLO5Face: Why Reinventing a Face Detector (https://arxiv.org/abs/2105.12931) ECCV Workshops 2022)
Long-Term Feature Banks for Detailed Video Understanding
You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization
label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful
torch-optimizer -- collection of optimizers for Pytorch
Repository for NeurIPS 2020 Spotlight "AdaBelief Optimizer: Adapting stepsizes by the belief in observed gradients"
Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125
Official PyTorch implementation of ACTION-Net: Multipath Excitation for Action Recognition (CVPR'21)
⏬ Download AVA dataset (A Large-Scale Database for Aesthetic Visual Analysis)
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
TensorRT int8 量化部署 yolov5s 模型，实测3.3ms一帧！