--- license: apache-2.0 library_name: litert pipeline_tag: object-detection tags: - mediapipe - litert - tflite - object-detection - on-device - android - ios - web - python - flutter - coco - ssd - mobilenet-v2 - fp16 - fp32 - arxiv:1512.02325 --- # MediaPipe SSD-MobileNet-V2 (Object Detector) SSD-MobileNet-V2 object detection model(s) (`ssd_mobilenet_v2_float16.tflite` [5.9 MB], `_float32.tflite` [11.3 MB]) trained on COCO (1.5M instances, 80 classes / 90 COCO label slots) and packaged with `TFLITE_METADATA` and embedded labels for the [MediaPipe Object Detector (`ObjectDetector`)](https://developers.google.com/edge/mediapipe/solutions/vision/object_detector) task and [LiteRT](https://developers.google.com/edge/litert).

Documentation: MediaPipe Object Detector Docs

Samples: Android · iOS · Python Colab · Web · Flutter

Try live: Web Demo

SSD-MobileNet-V2 combines a MobileNetV2 backbone with an SSD detection head at `256 x 256` input resolution, prioritizing lower latency and memory footprint over EfficientDet. Input resolution is `256 x 256` RGB. Unlike EfficientDet-Lite (90 lines), `ssd_mobilenet_v2_*.tflite` embeds a **91-line** `labels.txt` (index `0` is `background`, followed by the 90 COCO slots matching `[1, 12276, 91]`). For standalone reference, this repository includes the official MediaPipe [`labelmap.txt`](./labelmap.txt) (90 lines, `person` through `toothbrush`). ## Files | File in Repo Root | Upstream Google Path | Precision | Size | SHA-256 | |---|---|---|---:|---| | [`ssd_mobilenet_v2_float16.tflite`](https://huggingface.co/litert-community/MediaPipe-ObjectDetector-SSD-MobileNet-V2/blob/main/ssd_mobilenet_v2_float16.tflite) | `object_detector/ssd_mobilenet_v2/float16/latest/ssd_mobilenet_v2.tflite` | `float16` | 5.92 MB (5,918,749 B) | `ee21e12bfdc464100c6008c865ab8294f6a04162e6ed2e11986f1175b02cfab2` | | [`ssd_mobilenet_v2_float32.tflite`](https://huggingface.co/litert-community/MediaPipe-ObjectDetector-SSD-MobileNet-V2/blob/main/ssd_mobilenet_v2_float32.tflite) | `object_detector/ssd_mobilenet_v2/float32/latest/ssd_mobilenet_v2.tflite` | `float32` | 11.32 MB (11,316,189 B) | `b8ccb1a25d45455ba52e85f26531948e1cb75efeb94c7c3d456d54fd4d6fbdd2` | ### Companion Files in Repo Root | File | Role | Size | SHA-256 | |---|---|---:|---| | [`labelmap.txt`](./labelmap.txt) | Label map | 0.7 KB (661 B) | `f8803ef7900160c629d570848dfda4175e21667bf7b71f73f8ece4938c9f2bf2` | ### Download ```bash pip install -U huggingface_hub hf download litert-community/MediaPipe-ObjectDetector-SSD-MobileNet-V2 ssd_mobilenet_v2_float16.tflite --local-dir . hf download litert-community/MediaPipe-ObjectDetector-SSD-MobileNet-V2 ssd_mobilenet_v2_float32.tflite --local-dir . ``` ## Inputs, Outputs, and Model Specifications ### `ssd_mobilenet_v2_float16.tflite` - Embedded `TFLITE_METADATA`: name `ObjectDetector` · version `1` · author `MediaPipe` · packed associated files: `labels.txt` | Direction | Tensor | Shape | Type | Notes | |---|---|---|---|---| | Input | `serving_default_inputs:0` | `[1, 256, 256, 3]` | `float32` | image — Input image to be processed. — Normalization: `mean=[127.5], std=[127.5]` | | Output | `StatefulPartitionedCall:0` | `[1, 12276, 4]` | `float32` | location — The locations of the detected boxes. | | Output | `StatefulPartitionedCall:1` | `[1, 12276, 91]` | `float32` | score — The scores of the detected boxes. — Labels: `labels.txt` | ### `ssd_mobilenet_v2_float32.tflite` - Embedded `TFLITE_METADATA`: name `ObjectDetector` · version `1` · author `MediaPipe` · packed associated files: `labels.txt` | Direction | Tensor | Shape | Type | Notes | |---|---|---|---|---| | Input | `serving_default_inputs:0` | `[1, 256, 256, 3]` | `float32` | image — Input image to be processed. — Normalization: `mean=[127.5], std=[127.5]` | | Output | `StatefulPartitionedCall:0` | `[1, 12276, 4]` | `float32` | location — The locations of the detected boxes. | | Output | `StatefulPartitionedCall:1` | `[1, 12276, 91]` | `float32` | score — The scores of the detected boxes. — Labels: `labels.txt` | ## Use with MediaPipe Tasks ### Python Quickstart ```bash pip install -U mediapipe huggingface_hub ``` ```python import mediapipe as mp from huggingface_hub import hf_hub_download model_path = hf_hub_download( repo_id="litert-community/MediaPipe-ObjectDetector-SSD-MobileNet-V2", filename="ssd_mobilenet_v2_float16.tflite", ) BaseOptions = mp.tasks.BaseOptions ObjectDetector = mp.tasks.vision.ObjectDetector ObjectDetectorOptions = mp.tasks.vision.ObjectDetectorOptions VisionRunningMode = mp.tasks.vision.RunningMode options = ObjectDetectorOptions( base_options=BaseOptions(model_asset_path=model_path), running_mode=VisionRunningMode.IMAGE, score_threshold=0.5, max_results=5, ) with ObjectDetector.create_from_options(options) as runner: mp_image = mp.Image.create_from_file("input.jpg") result = runner.detect(mp_image) for det in result.detections: cat = det.categories[0] print(f"{cat.category_name}: {cat.score:.3f} box={det.bounding_box}") ``` ### Cross-Platform Guides & Samples - **Task overview & options:** [Object Detector documentation](https://developers.google.com/edge/mediapipe/solutions/vision/object_detector) - **Platform setup guides:** [Python](https://developers.google.com/edge/mediapipe/solutions/setup_python) · [Web / JavaScript](https://developers.google.com/edge/mediapipe/solutions/setup_web) · [Android (Kotlin / Java)](https://developers.google.com/edge/mediapipe/solutions/setup_android) · [iOS (Swift)](https://developers.google.com/edge/mediapipe/solutions/setup_ios) · [Flutter (Dart)](https://developers.google.com/edge/mediapipe/solutions/setup_flutter) - **Runnable sample apps:** [Web Demo](https://google-ai-edge.github.io/mediapipe-samples-web/#/vision/object_detector) · [Web Source](https://github.com/google-ai-edge/mediapipe-samples-web/blob/main/src/tasks/object-detector.ts) · [Android](https://github.com/google-ai-edge/mediapipe-samples/tree/main/examples/object_detection/android) · [iOS](https://github.com/google-ai-edge/mediapipe-samples/tree/main/examples/object_detection/ios) · [Python Notebook](https://colab.research.google.com/github/google-ai-edge/mediapipe-samples/blob/main/examples/object_detection/python/object_detector.ipynb) · [Flutter](https://github.com/google/flutter-mediapipe/tree/main/samples/vision/object_detector) ## Latency Benchmarks End-to-end MediaPipe Task pipeline average latency reported by the [Object Detector documentation](https://developers.google.com/edge/mediapipe/solutions/vision/object_detector#benchmarks): | Model Variant | Device | CPU Latency | GPU Latency | |---|---|---:|---:| | SSD MobileNetV2 (float 16) | Pixel 6 | 37.35 ms | 28.16 ms | | SSD MobileNetV2 (float 32) | Pixel 6 | 36.30 ms | 24.01 ms | ## Intended Use, Limitations, and Fairness - **Intended applications:** General-purpose multi-object localization and classification across common COCO categories (people, vehicles, animals, household items, food, etc.) in still images, video, and camera streams. - **Limitations & considerations:** - Closed-vocabulary COCO detector (80 active object classes); objects outside COCO cannot be named. - Small objects, heavy occlusion, motion blur, or non-natural camera angles reduce detection recall. - Not intended for safety-critical perception (autonomous driving, medical imaging, surveillance) without domain-specific fine-tuning and evaluation. - Google does not publish a separate standalone fairness PDF for this model on the MediaPipe documentation page. ## Provenance Every model binary in this repository is byte-identical (unmodified FlatBuffer weights and embedded `TFLITE_METADATA` bytes) to the official artifact served by Google from `storage.googleapis.com/mediapipe-models`. | Repo File | Upstream URL | GCS Generation | Upstream `Last-Modified` | Pinned Bucket Version | |---|---|---|---|---| | `ssd_mobilenet_v2_float16.tflite` | [`ssd_mobilenet_v2.tflite`](https://storage.googleapis.com/mediapipe-models/object_detector/ssd_mobilenet_v2/float16/latest/ssd_mobilenet_v2.tflite) | `1683072060421733` | Wed, 03 May 2023 00:01:00 GMT | `/1/` | | `ssd_mobilenet_v2_float32.tflite` | [`ssd_mobilenet_v2.tflite`](https://storage.googleapis.com/mediapipe-models/object_detector/ssd_mobilenet_v2/float32/latest/ssd_mobilenet_v2.tflite) | `1683072058863267` | Wed, 03 May 2023 00:00:58 GMT | `/1/` | ## License and Citation - License: `apache-2.0` — Distributed under Apache License, Version 2.0 alongside the [MediaPipe](https://github.com/google-ai-edge/mediapipe) release artifacts. ### Citation ```bibtex @inproceedings{liu2016ssd, title = {SSD: Single Shot MultiBox Detector}, author = {Liu, Wei and Anguelov, Dragomir and Erhan, Dumitru and Szegedy, Christian and Reed, Scott and Fu, Cheng-Yang and Berg, Alexander C.}, booktitle = {European Conference on Computer Vision (ECCV)}, year = {2016}, url = {https://arxiv.org/abs/1512.02325} } ```