model-zoo

NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥

A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.

Pre-trained Deep Learning models and demos (high quality and extremely fast)

Open Source Pre-training Model Framework in PyTorch & Pre-trained Model Zoo

Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo

Model Zoo For OpenCV DNN and Benchmarks.

An efficient PyTorch library for deep generative modeling.

RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]

[CVPR 2021] VirTex: Learning Visual Representations from Textual Annotations

Downloadable models and conversion recipes for Apple's Core AI on iPhone and Mac. Chat, vision, speech and generative models with per-model validation records, Swift examples through CoreAIKit, and a downloadable Mac app.

Spatio-Temporal Action Localization System

Securade.ai HUB - A generative AI based edge platform for computer vision that connects to existing CCTV cameras and makes them smart.

The NNEF Tools repository contains tools to generate and consume NNEF documents

Keras Model Zoo

[CVPR 2021] Actor-Context-Actor Relation Network for Spatio-temporal Action Localization

The Model Zoo of Cognitive Diagnosis Models, including classic Item Response Ranking (IRT), Multidimensional Item Response Ranking (MIRT), Deterministic Input, Noisy "And" model(DINA), and advanced Fuzzy Cognitive Diagnosis Framework (FuzzyCDF), Neural Cognitive Diagnosis Model (NCDM) and Item Response Ranking framework (IRR).

Pytorch model zoo for human, include all kinds of 2D CNN, 3D CNN, and CRNN

【AAAI'2021】MVFNet: Multi-View Fusion Network for Efficient Video Recognition

A PaddlePaddle version image model zoo.

An open-source platform for automating tasks using machine learning models