24

There is already an answer wrt to Tensorflow. But the problem is that In my IDE Conv2D is a class while Convolution2D is a variable?

Shashi Tunga
  • 496
  • 1
  • 6
  • 24

1 Answers1

32

From the keras source code, they're the same:
(The source code changes from time to time and the line number in the link above might eventually be wrong)

# Aliases

Convolution1D = Conv1D
Convolution2D = Conv2D
Convolution3D = Conv3D
SeparableConvolution2D = SeparableConv2D
Convolution2DTranspose = Conv2DTranspose
Deconvolution2D = Deconv2D = Conv2DTranspose
Deconvolution3D = Deconv3D = Conv3DTranspose
Daniel Möller
  • 84,878
  • 18
  • 192
  • 214
  • 2
    Why am i getting this warning UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(32, (3, 3), input_shape=(64, 64, 3..., activation="relu")` classifier.add(Conv2D(32,3,3,input_shape=(64,64,3),activation='relu')) – Shashi Tunga Nov 21 '17 at 13:47
  • 2
    Because you're passing parameters in a style that was ok in Keras1, but is not the keras 2 way of doing it. It still supports the old way, but it gives you this message. Notice the `kernel_size=(3,3)`. This is how it should be done in keras 2. – Daniel Möller Nov 21 '17 at 13:51