search

jiny2001 / dcscn-super-resolution

A tensorflow implementation of "Fast and Accurate Image Super Resolution by Deep CNN with Skip Connection and Network in Network", a deep learning based Single-Image Super-Resolution (SISR) model.
https://arxiv.org/abs/1707.05425
MIT License
706 stars 216 forks source link

Scale being ignored? #125

Closed IamManifold closed 3 years ago

IamManifold commented 3 years ago

no matter how i train or process the data, the resolution is only going up by 3.14x? I was originally doing scale 10 and also tried 5 but the output resolution is the same regardless

python train.py --dataset=SRTest --layers=8 --filters=96 --training_images=255 --scale=4 python sr.py --file=MaybellWest.tif --layers=8 --filters=96 --training_images=255 --scale=4

IamManifold commented 3 years ago

Was erroring out after the first output, not the issue i thought i was having.