regnetx-3.2gf

Use Case and High-Level Description

The regnetx-3.2gf model is one of the RegNetX design space models designed to perform image classification. The RegNet design space provides simple and fast networks that work well across a wide range of flop regimes. This model was pre-trained in PyTorch*. All RegNet classification models have been pre-trained on the ImageNet dataset. For details about this family of models, check out the Codebase for Image Classification Research.

Specification

Metric

Value

Type

Classification

GFLOPs

6.3893

MParams

15.2653

Source framework

PyTorch*

Accuracy

Metric

Original model

Converted model

Top 1

78.15%

78.15%

Top 5

94.09%

94.09%

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 BGR. Mean values - [103.53, 116.28, 123.675], scale values - [57.375, 57.12, 58.395].

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 - prob, shape - 1, 1000, output data format is B, C, where:

  • B - batch size

  • C - predicted probabilities for each class in logits format

Converted model

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

  • B - batch size

  • C - predicted probabilities for each class in logits format

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: