Skip to content

Latest commit

 

History

History
52 lines (32 loc) · 1.49 KB

README.md

File metadata and controls

52 lines (32 loc) · 1.49 KB
Raw

text-image-super-resolution-0001

Use Case and High-Level Description

A tiny model to upscale scanned images with text. The model used the ConvTranspose2d layer instead of the PixelShuffle layer. As a result, the model can be launched on GPU device and support the reshape function.

Example

Low Resolution

Bicubic Interpolation

Super Resolution

Specification

Metric Value
PSNR 20.318 dB
GFlops 1.379
MParams 0.003
Source framework PyTorch*

Inputs

Image, name: 0, shape: 1, 1, 360, 640 in the format B, C, H, W, where:

  • B - batch size
  • C - number of channels
  • H - image height
  • W - image width

Outputs

One blob with shapes 1, 1, 1080, 1920. The blob contains an image after super resolution.

Demo usage

The model can be used in the following demos provided by the Open Model Zoo to show its capabilities:

Legal Information

[*] Other names and brands may be claimed as the property of others.