Tengine is a lite, high performance, modular inference engine for embedded device

Differentiable IoU of rotated bounding boxes using Pytorch

Unofficial implementation of EfficientAD https://arxiv.org/abs/2303.14535

MNN applications by MNN, JNI exec, RK3399. Support tflite\tensorflow\caffe\onnx models.

MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

Industrial Defect Diffusion Model (NOT JUST INDUSTRIAL DEFECT~), support DDPM, DDIM and multi-GPU distributed training. 分布式训练，生成模型，扩散模型

This is an official implementation of the paper : "Target before Shooting: Accurate Anomaly Detection and Localization under One Millisecond via Cascade Patch Retrieval" (Accepted by IEEE TIP)

A controllable image composition model which could be used for image blending, image harmonization, view synthesis.

Paint by Example: Exemplar-based Image Editing with Diffusion Models

[ECCV2022 Oral] Registration based Few-Shot Anomaly Detection

A natural language interface for computers

Official implementation of "Segment Any Anomaly without Training via Hybrid Prompt Regularization (SAA+)".

Holds code for our CVPR'23 tutorial: All Things ViTs: Understanding and Interpreting Attention in Vision.

SOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.

A simple, fully convolutional model for real-time instance segmentation.

[TPAMI 2023] Multimodal Image Synthesis and Editing: The Generative AI Era

Labeling tool with SAM(segment anything model),supports SAM, SAM2, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具

[ICCV2023] Self-supervised Character-to-Character Distillation for Text Recognition

Welcome to the Physics-based Deep Learning Book (v0.2)

An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.

A curated list of awesome anomaly detection resources

This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

[ICCV 2023] Code base for Revisiting Scene Text Recognition: A Data Perspective

Effortless data labeling with AI support from Segment Anything and other awesome models.

Focus on prompting and generating

Inference code for CodeLlama models