Skip to content

Latest commit

 

History

History
79 lines (52 loc) · 2.56 KB

README.md

File metadata and controls

79 lines (52 loc) · 2.56 KB
Raw

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 Inference Engine Format

You can download models and if necessary convert them into Inference Engine 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>

Legal Information

The original model is distributed under the Apache License, Version 2.0. A copy of the license is provided in <omz_dir>/models/public/licenses/APACHE-2.0-TF-Models.txt.