shufflenet-v2-x0.5

Use Case and High-Level Description

Shufflenet V2 x0.5 is a light-weight classification model based on channel split and channel shuffle operations. This is Caffe* implementation based on architecture described in paper “ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design”. For details about implementation, check out the repository. The model was pre-trained on the ImageNet dataset.

The model input is a blob that consists of a single image of 1, 3, 224, 224 in RGB order.

The model output is typical object classifier for the 1000 different classifications matching with those in the ImageNet dataset.

Specification

Metric

Value

Type

Classification

GFLOPs

0.08465

MParams

1.363

Source framework

Caffe*

Accuracy

Metric

Value

Top 1

58.80%

Top 5

81.13%

Input

Original model

Image, name - data, shape - 1, 3, 224, 224, format is B, C, H, W, where:

  • B - batch size

  • C - channel

  • H - height

  • W - width

Channel order is RGB. Scale factor - 255.

Converted model

Image, name - data, shape - 1, 3, 224, 224, format is B, C, H, W, where:

  • B - batch size

  • C - channel

  • H - height

  • W - width

Channel order is BGR

Output

Original model

Object classifier according to ImageNet classes, name - fc, shape - 1, 1000, output data format is B, C, where:

  • B - batch size

  • C - predicted probabilities for each class in [0, 1] range

Converted model

The converted model has the same parameters as the original model.

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: