single-image-super-resolution-1032¶
Use Case and High-Level Description¶
An Attention-Based Approach for Single Image Super Resolution but with reduced number of channels and changes in network architecture. It enhances the resolution of the input image by a factor of 4.
Specification¶
Metric |
Value |
---|---|
PSNR |
29.29 dB |
GFlops |
11.654 |
MParams |
0.030 |
Source framework |
PyTorch* |
For reference, PSNR for bicubic upsampling on test dataset is 26.79 dB.
Inputs¶
Image, name:
0
, shape:1, 3, 270, 480
in the formatB, C, H, W
, where:B
- batch sizeC
- number of channelsH
- image heightW
- image width
Bicubic interpolation of the input image, name:
1
, shape:1, 3, 1080, 1920
in the formatB, C, H, W
, where:B
- batch sizeC
- number of channelsH
- image heightW
- image width
Expected color order is
BGR
.
Outputs¶
The net output is a blob with shapes 1, 3, 1080, 1920
that contains 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.