Issue with Deconvolution3D

[changken1]

Hi,

I am trying to run this segment of code from the Deconvolution3D example:

model = Sequential() model.add(Deconvolution3D(3, 3, 3, 3, output_shape=(None, 3, 14, 14, 14), padding='valid', input_shape=(3, 12, 12, 12)))

but am experiencing this error "TypeError: init() got multiple values for keyword argument 'output_shape'". Is this a bug?

Thank you!

[luckustus]

Same issue

[luckustus]

Does anybody know how to make this work?

[luckustus]

OK got it: You have to pass the filters and kernel_size arguements like this: Deconvolution3D(3,(3,3,3),...

[charlesreid1]

Could you add a simple Deconvolution3D example to the examples/ directory? This would be a great pull request!

[jizhang02]

from keras.layers import * Deconvolution3D(number_of_filter, kernel_size=(2, 2, 2), padding='same', data_format = 'channels_last',strides=(2, 2, 2))(last layer) I used the above code, it works for me.