Created by @RisingSayak and based on a recent paper by Talebi et al.
Show this thread
New code example on http://keras.io : learning to resize images. Use a small convnet to learn an optimal interface between a large image and a classification convnet that expects smaller images.https://keras.io/examples/vision/learnable_resizer/ …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This Tweet is unavailable.
-
Interesting!
End of conversation
-
-
-
There is a small bug when creating the res_blocks: they all have the bottleneck as input. You'll always only have zero or one res_blocks, no matter of the input
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.