fast-neural-style-mosaic-onnx

Use Case and High-Level Description

The fast-neural-style-mosaic-onnx model is one of the style transfer models designed to mix the content of an image with the style of another image. The model uses the method described in Perceptual Losses for Real-Time Style Transfer and Super-Resolution along with Instance Normalization. Original ONNX models are provided in the repository.

Specification

Metric

Value

Type

Style Transfer

GFLOPs

15.518

MParams

1.679

Source framework

PyTorch*

Accuracy

Accuracy metrics are obtained on Common Objects in Context (COCO) val2017 dataset. Images were resized to input size.

Metric

Original model

Converted model (FP32)

Converted model (FP16)

PSNR

12.03dB

12.03dB

12.04dB

Input

Original model

Image, name - input1, shape - 1, 3, 224, 224, format is B, C, H, W, where:

  • B - batch size

  • C - channel

  • H - height

  • W - width

Expected color order: RGB.

Converted model

Image, name - input1, shape - 1, 3, 224, 224, format is B, C, H, W, where:

  • B - batch size

  • C - channel

  • H - height

  • W - width

Expected color order: BGR.

Output

Original model

Image, name - output1, shape - 1, 3, 224, 224, format is B, C, H, W, where:

  • B - batch size

  • C - channel

  • H - height

  • W - width

Expected color order: RGB.

Converted model

Image, name - output1, shape - 1, 3, 224, 224, format is B, C, H, W, where:

  • B - batch size

  • C - channel

  • H - height

  • W - width

Expected color order: RGB.

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: