Wow, that is amazing.
New tutorial on http://keras.io : training a deep learning model (MIRNet) to enhance low-light images -- with much nicer results than what you'd get from a simple auto-contrast correction. https://keras.io/examples/vision/mirnet/ …pic.twitter.com/pjWIf3qeKq
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Amazing results, thanks for sharing!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
That's great.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks,
@fchollet for the reviews
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
So many applications for@this kind of things !! Thanks for sharing
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Have known about Soumik's implementation of it since the day he open-sourced it (a few months back). So I decided to build on top of his amazing work and tried to run it in near real-time.https://github.com/sayakpaul/MIRNet-TFLite-TRT …
-
@RisingSayak I tried using your models on an Android device. I was using a device with Samsung Exynos 7870 ( 8 core ) and it too long to produce an output. It would have been nice to have a 'lite' architecture of MIRNet optimized for low power devices. - Show replies
New conversation -
-
-
Where are the ground truth images? What the scene actually looks like with full lighting.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Great results
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.