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 and MYRIAD devices and support the
0, shape: [1x3x768x1280] - An input image in the format [BxCxHxW], where:
One blob with shapes [1, 1, 1080, 1920]. The blob contains an image after super resolution.
[*] Other names and brands may be claimed as the property of others.