googlenet-v3-pytorch

Use Case and High-Level Description

Inception v3 is image classification model pre-trained on ImageNet dataset. This PyTorch* implementation of architecture described in the paper “Rethinking the Inception Architecture for Computer Vision” in TorchVision package (see here).

The model input is a blob that consists of a single image of 1, 3, 299, 299 in RGB order.

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

Specification

Metric

Value

Type

Classification

GFLOPs

11.469

MParams

23.817

Source framework

PyTorch*

Accuracy

Metric

Value

Top 1

77.69%

Top 5

93.7%

Input

Original model

Image, name - data, shape - 1, 3, 299, 299, format - B, C, H, W, where:

  • B - batch size

  • C - number of channels

  • H - image height

  • W - image width

Expected color order - RGB. Mean values - [123.675, 116.28, 103.53], scale values - [58.395, 57.12, 57.375].

Converted model

Image, name - data, shape - 1, 3, 299, 299, format - B, C, H, W, where:

  • B - batch size

  • C - number of channels

  • H - image height

  • W - image width

Expected color order - BGR.

Output

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

  • B - batch size

  • C - vector of 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: