Source: https://seerepo.com/compare/PaddlePaddle/PaddleDetection/vs/tensorflow/models
Markdown source: https://seerepo.com/compare/PaddlePaddle/PaddleDetection/vs/tensorflow/models.md
Description: PaddleDetection and models share 5 technologies: scikit-learn, opencv-python, pycocotools, pillow, and psutil. Both are written in Python.

# PaddleDetection vs models

PaddleDetection and models share 5 technologies: scikit-learn, opencv-python, pycocotools, pillow, and psutil. Both are written in Python.

- [PaddlePaddle/PaddleDetection](https://seerepo.com/r/PaddlePaddle/PaddleDetection): Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.
- [tensorflow/models](https://seerepo.com/r/tensorflow/models): Models and examples built with TensorFlow

## What they share and what sets them apart

- In common: scikit-learn, opencv-python, pycocotools, pillow, psutil
- Only in PaddleDetection: PaddlePaddle, sklearn, paddleslim, onnxruntime, ONNX
- Only in models: FastAPI, google-cloud-core, pandas-gbq, Google, Google Cloud Storage, Apache, matplotlib, seaborn, google-auth-oauthlib, oauth2client, ai-edge-litert, cuml-cu12, cupy-cuda12x, einops, tf-nightly, torchmetrics, TensorFlow, tf-keras, tf-slim, torch, tensorflow-model-optimization, tensorflow-datasets, torchvision, sentencepiece, supervision, scikit-image, sam3, nltk, trackers, trackpy, tritonclient, sacrebleu, tensorflow-probability, tensorflow-transform, ffmpeg-python, mediapy, sox

## Side by side

| | PaddleDetection | models |
|---|---|---|
| Size | 146,603 lines written, 432 code files | 644,066 lines written, 1,864 code files |
| Who writes it | 0% of its commits signed by AI. With Claude Code | 0% of its commits signed by AI |
| Activity | Last push May 28, 2026, 2,329 commits, 14,462 stars | Last push November 2, 2026, 8,558 commits, 77,635 stars |
| Tests | 14 test files. 2.3% of its code files have a test that imports them | 777 test files. 45.2% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, PaddleDetection or models?

models, with 644,066 lines written; PaddleDetection has 146,603.

The proof: [tensorflow/models's code at commit 19f2877](https://github.com/tensorflow/models/tree/19f287775ae950e22a9b5fb82727e72cff2e3664)

### Which has more GitHub stars, PaddleDetection or models?

models, with 77,635 stars; PaddleDetection has 14,462.

The proof: [tensorflow/models on GitHub](https://github.com/tensorflow/models)

### Which has more tests, PaddleDetection or models?

models, with 777 test files; PaddleDetection has 14.

The proof: [tensorflow/models's code at commit 19f2877](https://github.com/tensorflow/models/tree/19f287775ae950e22a9b5fb82727e72cff2e3664)

### Which was updated more recently, PaddleDetection or models?

models: its last push was on November 2, 2026, and PaddleDetection's on May 28, 2026.

The proof: [tensorflow/models's commits on GitHub](https://github.com/tensorflow/models/commits)

## Sources

- PaddlePaddle/PaddleDetection: Read on November 9, 2026, at commit b25522a (https://github.com/PaddlePaddle/PaddleDetection/tree/b25522a0f4bde8c80603f3ba5e3472059972e3b5)
- tensorflow/models: Read on November 12, 2026, at commit 19f2877 (https://github.com/tensorflow/models/tree/19f287775ae950e22a9b5fb82727e72cff2e3664)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.
