MediaPipe

A cross-platform framework for building customizable on-device machine learning pipelines for vision, audio and text, deployable to mobile, web, desktop and edge devices.

Visit website ai.google.dev

MediaPipe Solutions provides cross-platform APIs and libraries (MediaPipe Tasks) for deploying pre-trained, ready-to-run vision, text and audio models, MediaPipe Model Maker for customizing those models with a user's own data, and MediaPipe Studio for visualizing, evaluating and benchmarking solutions directly in a browser.

Underneath the premade solutions, MediaPipe Framework is a lower-level graph-based system for building efficient on-device machine learning pipelines from packets, graphs and calculators, targetable from C++, Android and iOS. When an application uses MediaPipe Tasks, input data such as images, video or text is processed on the device itself and is not sent to any server.

It is written in C++ and licensed under Apache-2.0.

More in Models

See all 405

mini-AGI
github.com
A continual learning language model that trains from scratch on a single 8 GB VRAM GPU, assembling its own architecture and adapting its size to the hardware and data available rather than shipping as a fixed pretrained model.
- Models
Applied Inference Lab: Compliance Control Embedding Stack
github.com
An open-source contrastive-embedding pipeline that maps technical CVE vulnerability descriptions to formal cybersecurity compliance controls in NIST SP 800-53 and CMMC, published with its model generation, fine-tuning and evaluation code.
- Models
- Security
peekaboolean
github.com
A small vision-language model, fine-tuned with LoRA on a 500-million-parameter backbone, that answers typed multiple-choice, ordinal-score and yes/no questions about an image with calibrated probabilities, in about 400 milliseconds on a laptop.
- Models
- Inference

More in Models

mini-AGI

Applied Inference Lab: Compliance Control Embedding Stack

peekaboolean

Cookies