Update README.md

README.md

@@ -187,7 +187,7 @@ The model architecture is based on the original Swin2 arcthitecture for Super Re
 ![architecture](architecture.png)
 
 The main component of the model is a [transformers.Swin2SRModel](https://huggingface.co/docs/transformers/model_doc/swin2sr#transformers.Swin2SRModel) which increases x8 the spatial resolution of its inputs (Swin2SR only supports upscaling ratios power of 2).  
-As the real upscale ratio is ~5 and the output shape of the region considered is (160, 240), a Convolutional Neural Network (CNN) is included as a pre-process component which convert the inputs into a (40, 60) feature maps that can be fed to the Swin2SRModel.
+As the real upscale ratio is ~5 and the output shape of the region considered is (160, 240), a Convolutional Neural Network (CNN) is included as a pre-process component which convert the inputs into a (20, 30) feature maps that can be fed to the Swin2SRModel.
 
 This network is trained to learn the residuals of the bicubic interpolation.