octave-resnet-101-0.125

Use Case and High-Level Description

The octave-resnet-101-0.125 model is a modification of ResNet-101 with Octave convolutions from Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution with alpha=0.125. Like the original model, this model is designed for image classification. For details about family of Octave Convolution models, check out the repository.

The model input is a blob that consists of a single image of 1, 3, 224, 224 in RGB order. Before passing the image blob into the network, subtract RGB mean values as follows: [124, 117, 104]. In addition, values must be divided by 0.0167.

The model output for octave-resnet-101-0.125 is a typical object-classifier output for 1000 different classifications matching those in the ImageNet database.

Specification

Metric

Value

Type

Classification

GFLOPs

13.387

MParams

44.543

Source framework

MXNet*

Accuracy

Metric

Value

Top 1

79.182%

Top 5

94.42%

Input

Original Model

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

  • B - batch size

  • C - channel

  • H - height

  • W - width

Channel order is RGB. Mean values: [124, 117, 104], scale value: 59.880239521.

Converted Model

Image, name: data, shape: 1, 3, 224, 224, format: 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 [0, 1] range

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 [0, 1] range

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:

python3 <omz_dir>/tools/downloader/downloader.py --name <model_name>

An example of using the Model Converter:

python3 <omz_dir>/tools/downloader/converter.py --name <model_name>