mobilenet-v1-0.25-128

Use Case and High-Level Description

mobilenet-v1-0.25-128 is one of MobileNets - small, low-latency, low-power models parameterized to meet the resource constraints of a variety of use cases. They can be built upon for classification, detection, embeddings and segmentation similar to how other popular large scale models are used. For details, see paper.

Specification

Metric

Value

Type

Classification

GFlops

0.028

MParams

0.468

Source framework

TensorFlow*

Accuracy

Metric

Value

Top 1

40.54%

Top 5

65%

Input

Original Model

Image, name: input, shape: 1, 128, 128, 3, format: B, H, W, C, where:

  • B - batch size

  • H - image height

  • W - image width

  • C - number of channels

Expected color order: RGB. Mean values: [127.5, 127.5, 127.5], scale factor for each channel: 127.5

Converted Model

Image, name: input, shape: 1, 128, 128, 3, format: B, H, W, C, where:

  • B - batch size

  • H - image height

  • W - image width

  • C - number of channels

Expected color order: BGR.

Output

Original Model

Probabilities for all dataset classes in [0, 1] range (0 class is background). Name: MobilenetV1/Predictions/Reshape_1.

Converted Model

Probabilities for all dataset classes in [0, 1] range (0 class is background). Name: MobilenetV1/Predictions/Softmax, shape: 1, 1001, format: B, C, where:

  • B - batch size

  • C - vector of probabilities.

Download a Model and Convert it into OpenVINO™ IR Format

You can download models and if necessary convert them into OpenVINO™ IR format using the Model Downloader and other automation tools as shown in the examples below.

An example of using the Model Downloader:

omz_downloader --name <model_name>

An example of using the Model Converter:

omz_converter --name <model_name>

Demo usage

The model can be used in the following demos provided by the Open Model Zoo to show its capabilities: