@jeremyphoward ‘s and http://fast.ai ‘s influence I’m sure ;)
-
Thats means that all CNNs have a minimum input size, which is the minimum size you can call the network on without resulting in empty feature maps. At that size, the output of your network is a 1x1 feature map.
For most nets, this tends to be about ~50% of the input size the network was designed for. Downsampling is absolutely necessary when you have large inputs. To get rid of this limitation, you need to create your own network, where you would do less downsampling.
-
-
For instance, you could edit Xception and 1) remove max pooling layers, 2) use "same" padding in all convolution layers. This would create a version of Xception that would be compatible with smaller input sizes.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Resnet34 and 50 work great on 128x128 px inputs, and quite well on 64x64, FYI.
-
Looking at the Keras code, I see that the minimum input size for ResNet50 is 32x32. So you are right, it would work quite well for 64x64.https://github.com/keras-team/keras-applications/blob/master/keras_applications/resnet50.py#L208 …
- Show replies
New conversation -
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.