MediaPipe MobileNet-V3 (Large) Image Embedder

MobileNet-V3 Large image feature extractor (mobilenet_v3_large.tflite, 10.9 MB, 0.75 depth multiplier, FP32 weights) producing 1280-dimensional embedding vectors for visual similarity search and deduplication in the MediaPipe Image Embedder (ImageEmbedder) task.

Documentation: MediaPipe Image Embedder Docs

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

Try live: Web Demo

Trained on ImageNet with a 0.75 channel depth multiplier to balance accuracy and edge latency. Takes normalized 224 x 224 RGB images and outputs a 1280-element feature vector (StatefulPartitionedCall:0), optionally L2-normalized (l2_normalize=True) and scalar-quantized (quantize=True) by MediaPipe ImageEmbedder.

Files

File Precision Size SHA-256
mobilenet_v3_large.tflite float32 10.89 MB (10,889,458 B) 11af3c560dfeed7737cb4c03c23bf52a8403020784192d4dea0b74862a12828d

Download

pip install -U huggingface_hub
hf download litert-community/MediaPipe-ImageEmbedder-MobileNet-V3-Large mobilenet_v3_large.tflite --local-dir .

Inputs, Outputs, and Model Specifications

mobilenet_v3_large.tflite

  • Embedded TFLITE_METADATA: name MobileNetV3 image classifier · version 1 · author MediaPipe · packed associated files: labels.txt
Direction Tensor Shape Type Notes
Input serving_default_inputs:0 [-1, 224, 224, 3] float32 image — Input image to be embedded. The expected image is 224 x 224, with three channels (red, blue, and green) per pixel. Each element in the tensor is a value between min and max, where (per-channel) min is [0.0] and max is [1.0]. — Normalization: mean=[0.0], std=[255.0]
Output StatefulPartitionedCall:0 [-1, 1280] float32 feature — Feature vector of the input image.

Use with MediaPipe Tasks

Python Quickstart

pip install -U mediapipe huggingface_hub
import mediapipe as mp
from huggingface_hub import hf_hub_download

model_path = hf_hub_download(repo_id="litert-community/MediaPipe-ImageEmbedder-MobileNet-V3-Large", filename="mobilenet_v3_large.tflite")

BaseOptions = mp.tasks.BaseOptions
ImageEmbedder = mp.tasks.vision.ImageEmbedder
ImageEmbedderOptions = mp.tasks.vision.ImageEmbedderOptions
VisionRunningMode = mp.tasks.vision.RunningMode

options = ImageEmbedderOptions(
    base_options=BaseOptions(model_asset_path=model_path),
    running_mode=VisionRunningMode.IMAGE,
    l2_normalize=True,
)

with ImageEmbedder.create_from_options(options) as embedder:
    e1 = embedder.embed(mp.Image.create_from_file("input.jpg")).embeddings[0]
    e2 = embedder.embed(mp.Image.create_from_file("other.jpg")).embeddings[0]
    print("Cosine similarity:", ImageEmbedder.cosine_similarity(e1, e2))

Cross-Platform Guides & Samples

Latency Benchmarks

End-to-end MediaPipe Task pipeline average latency reported by the Image Embedder documentation:

Model Variant Device CPU Latency GPU Latency
MobileNet-V3 (large) Pixel 6 9.75 ms 9.08 ms

Intended Use, Limitations, and Fairness

  • Intended applications: Generating dense feature vectors for on-device image similarity comparison, visual search, clustering, and near-duplicate detection via cosine similarity.
  • Limitations & considerations: Pretrained on ImageNet-1K natural photographs; fine-grained domains (medical scans, OCR, specialized industrial parts) or biometric matching are outside its training distribution. No standalone Google fairness PDF is published 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
mobilenet_v3_large.tflite mobilenet_v3_large.tflite 1682480014487254 Wed, 26 Apr 2023 03:33:34 GMT /1/

License and Citation

  • License: apache-2.0 — Stated as Apache License, Version 2.0 (http://www.apache.org/licenses/LICENSE-2.0) in the embedded TFLITE_METADATA block of the .tflite model file(s).

Citation

@inproceedings{howard2019searching,
  title     = {Searching for MobileNetV3},
  author    = {Howard, Andrew and Sandler, Mark and Chu, Grace and Chen, Liang-Chieh and Chen, Bo and Tan, Mingxing and Wang, Weijun and Zhu, Yukun and Pang, Ruoming and Vasudevan, Vijay and Le, Quoc V. and Adam, Hartwig},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  year      = {2019},
  url       = {https://arxiv.org/abs/1905.02244}
}
Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train litert-community/MediaPipe-ImageEmbedder-MobileNet-V3-Large

Collection including litert-community/MediaPipe-ImageEmbedder-MobileNet-V3-Large

Paper for litert-community/MediaPipe-ImageEmbedder-MobileNet-V3-Large