Stars
🚀 Transparent proxy injector for Antigravity. Force SOCKS5/HTTP proxy without TUN mode on Windows. | 专为 Antigravity 打造的免 TUN 强制代理工具，支持 DLL 注入与进程流量劫持。
A technical report on convolution arithmetic in the context of deep learning
一站式原生AI PPT生成应用，几分钟内生成一套幻灯片; 支持上传任意模板图片，上传任意素材&智能解析，一句话/大纲/页面描述自动生成PPT，口头修改指定区域、一键导出可编辑ppt、视频等 - An AI-native slides generator based on nano banana pro🍌
[CVPR 2025] StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text
[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale
DeepFaceLab is the leading software for creating deepfakes.
InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥
Code for the ICCV 2021 paper "Pixel Difference Networks for Efficient Edge Detection" (Oral).
CRNN (CNN+RNN) for OCR using Keras / License Plate Recognition
End-to-End Object Detection with Transformers
Random Erasing Data Augmentation. Experiments on CIFAR10, CIFAR100 and Fashion-MNIST
Image augmentation library in Python for machine learning.
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Save, Load Frozen Graph and Run Inference From Frozen Graph in TensorFlow 1.x and 2.x
Image augmentation for machine learning experiments.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
这是一个yolo4-tf2（tensorflow2）的源码，可以用于训练自己的模型。
📈 目前最大的工业缺陷检测数据库及论文集 Constantly summarizing open source dataset and critical papers in the field of surface defect research which are of great importance.
YOLOv3 training, preprocessing, validation, and inference for object detection in xView satellite imagery and the xView detection challenge.
High-Resolution 3D Human Digitization from A Single Image.
🔥 2D and 3D Face alignment library build using pytorch
Simple Online Realtime Tracking with a Deep Association Metric