# PINTO0309/PINTO_model_zoo

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.

Repository: https://github.com/PINTO0309/PINTO_model_zoo
Canonical: https://ross.abutalabs.com/products/pinto_model_zoo
Homepage: https://qiita.com/PINTO
Language: Python
License: MIT
License Family: permissive
Topics: tensorflow, tensorflow-lite, openvino, edgetpu, mediapipe, coreml, tensorflowjs, tf-trt, onnx, pytorch, tflite, tfjs, model-zoo, models, keras, computer-vision, caffe, pretrained-models, model, tflite-models
Last push: 2026-08-19T06:02:07+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 98, release rhythm 8, longevity 100
- inputs: {"age_days": 2457, "days_push": 14, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4577, forks 667 (observed 2026-08-28T04:08:53.701656+00:00)

## What it is
A large collection of pre-trained deep learning models that have been inter-converted between frameworks such as TensorFlow, PyTorch, ONNX, OpenVINO, TensorFlow Lite (Float32/16/INT8), EdgeTPU, CoreML, TFJS, and TF-TRT. It includes conversion scripts (MIT licensed) and quantization tooling, with per-model licenses inherited from their original providers.

## Use cases
- download pretrained models converted to tflite or onnx
- convert a pytorch model to tensorflow lite
- quantize a model to int8 for edge devices
- run deep learning models on raspberry pi or coral edge tpu
- find computer vision models in openvino or coreml format
- convert onnx models to tensorflow saved_model

## When to choose
- you need a specific pretrained model in a different framework format
- you target edge devices like Raspberry Pi, EdgeTPU, or mobile and need quantized models
- you want reference conversion scripts between TF, PyTorch, ONNX, and OpenVINO

## When to avoid
- you need production support or guaranteed correctness for every converted model
- you need a model training framework rather than ready-made converted weights
- your required model is not in the zoo and you cannot run conversions yourself

## Facets
- artifact type: dataset
- maturity: active
- function: machine-learning, deep-learning, computer-vision, developer-tools
- domain: machine-learning, deep-learning, computer-vision, developer-tools
- platform: python, cross-platform, embedded
- tags: model-zoo, model-conversion, quantization, tflite, onnx, openvino, coreml, edgetpu, pretrained-models, mediapipe, gpu

## Member repositories
- PINTO0309/PINTO_model_zoo (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:53.701656+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:19:54.878195+00:00, confidence not recorded.
  - readme: https://github.com/PINTO0309/PINTO_model_zoo (fetched 2026-08-28T04:08:53.701656+00:00, sha a175af2c0caa)
  - homepage: https://qiita.com/PINTO (fetched 2026-08-29T09:05:27.188004+00:00, sha b3e8f5142ed9)
  - site_page: https://qiita.com/about (fetched 2026-08-29T09:05:27.196880+00:00, sha cc774e957707)
  - site_page: https://qiita.com/api/v2/docs (fetched 2026-08-29T09:05:27.198709+00:00, sha 4b4c8f2e8b0e)
  - site_page: https://corp.qiita.com/company (fetched 2026-08-29T09:05:27.202020+00:00, sha 15f42516857d)
  - site_page: https://corp.qiita.com/releases (fetched 2026-08-29T09:05:27.204030+00:00, sha b7566fc5e9b5)
- Data as of 2026-08-30T08:39:29.467469+00:00.