resnet-34-pytorch

Use Case and High-Level Description

ResNet 34 is image classification model pre-trained on ImageNet dataset. This is PyTorch* implementation based on architecture described in paper “Deep Residual Learning for Image Recognition” in TorchVision package (see here).

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 database.

Specification

Metric

Value

Type

Classification

GFLOPs

7.3409

MParams

21.7892

Source framework

PyTorch*

Accuracy

Metric

Value

Top 1

73.30%

Top 5

91.42%

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

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: