Created by @RisingSayak!
Also check out the original paper:https://arxiv.org/abs/2104.05704
Show this thread
New code walkthrough on http://keras.io : Compact Convolutional Transformers, a computer-vision architecture that combines convolution and self-attention for great efficiency gainshttps://keras.io/examples/vision/cct/ …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks, but how many parameters does this architecture have? For example in comparison to the ResNet family?
-
Our best performing model is 3.76M params. You can compare to different ResNets from Table 1 in our paperhttps://arxiv.org/abs/2104.05704
End of conversation
New conversation -
-
-
@fchollet we found, through continued research, that augmentations and longer training improves the performance of these models (up to 98% on CIFAR-10, beating ResNet).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.