Keras Convolutional Autoencoder: Layer Shapes

Question

I've got a list of about 70,000 training images, each shaped (no. of colour channels, height width) = (3, 30, 30), and about 20,000 testing images. My convolutional autoencoder is defined as:

 # Same as the code above, but with some params changed
# Now let's define the model. 

# Set input dimensions:
input_img = Input(shape=(3, 30, 30))

# Encoder: define a chain of Conv2D and MaxPooling2D layers
x = Convolution2D(128, 3, 3, 
                  activation='relu', 
                  border_mode='same')(input_img)
x = MaxPooling2D((2, 2), border_mode='same')(x)
x = Convolution2D(64, 3, 3, 
                  activation='relu', 
                  border_mode='same')(x)
x = MaxPooling2D((2, 2), border_mode='same')(x)
x = Convolution2D(64, 3, 3, 
                  activation='relu', 
                  border_mode='same')(x)
encoded = MaxPooling2D((2, 2), border_mode='same')(x)

# at this point, the representation is (8, 4, 4) i.e. 128-dimensional

# Decoder: a stack of Conv2D and UpSampling2D layers
x = Convolution2D(64, 3, 3, 
                  activation='relu', 
                  border_mode='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Convolution2D(64, 3, 3, 
                  activation='relu', 
                  border_mode='same')(x)
x = UpSampling2D((2, 2))(x)
x = Convolution2D(128, 3, 3, 
                  activation='relu')(x)
x = UpSampling2D((2, 2))(x)
decoded = Convolution2D(1, 3, 3, 
                        activation='sigmoid', 
                        border_mode='same')(x)

autoencoder2 = Model(input_img, decoded)
autoencoder2.compile(optimizer='adadelta', loss='mse')

Which is the autoencoder from here.

It throws an error:

Error when checking model target: expected convolution2d_14 to have shape (None, 1, 28, 28) but got array with shape (76960, 3, 30, 30)

which is weird because I've clearly changed the specified the input shape as (3, 30, 30). Is there some implementation technicality I'm missing?

Try out this answer stackoverflow.com/questions/37793144/… — PixelPioneer
– PixelPioneer, Commented Aug 28, 2016 at 17:46

Md Shopon · Accepted Answer · 2016-09-17 19:42:49Z

2

You forgot to add border_mode='same' in the last convnet layer of the decoder .

answered Sep 17, 2016 at 19:42

Md Shopon

8232 gold badges10 silver badges17 bronze badges

Sign up to request clarification or add additional context in comments.

Comments

Nufa · Accepted Answer · 2017-03-03 03:40:00Z

0

In the https://blog.keras.io/building-autoencoders-in-keras.html, they forgot to add the

'border_mode='same''.

For instance, in your 2nd last convolution layer;

x = Convolution2D(128, 3, 3, activation='relu')(x)

answered Mar 3, 2017 at 3:40

Nufa

1221 silver badge11 bronze badges

Comments

random_user · Accepted Answer · 2017-03-10 09:45:02Z

0

You should chage the shape of the last convolutional layer from (1,3,3) to (3,3,3) as follows:

decoded = Convolution2D(3, 3, 3, 
                    activation='sigmoid', 
                    border_mode='same')(x)

answered Mar 10, 2017 at 9:45

random_user

1

Collectives™ on Stack Overflow

Keras Convolutional Autoencoder: Layer Shapes

3 Answers 3

Comments

Comments

Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

3 Answers 3

Comments

Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related