SE+AI

model of 2017 mainly trained on CASIA-webface, while model of 2018 trained both on CASIA and vggface?

> @xiakj Sorry, check this link: https://drive.google.com/drive/folders/1D6gG2WRvOvUI7NyJLInGl2zBD6zDPcoI thats great! but is there any demo script using this caffemodel? need to normalize input image or some other image operations?

It seems something wrong with the input shape, the authors did not provide the suitable input shape, it always causes the error. By the way, the model is derived by...

@cfrancesco no, it didn't work, the result seems not change.

@cfrancesco sure, both the input and output like the image here [https://github.com/idealo/image-super-resolution/blob/master/figures/baboon-compare.png](url), the output may be slightly different from the input, but one can not figure out with eyes' observation.