Keras Convolutional Autoencoder blank output

Question

Quick disclaimer: I'm pretty new to Keras, machine learning, and programming in general.

I'm trying to create a basic autoencoder for (currently) a single image. While it seems to run just fine, the output is just a white image. Here's what I've got:

img_height, img_width = 128, 128

input_img = '4.jpg'
output_img = '5.jpg'

# load image
x = load_img(input_img)
x = img_to_array(x)  # array with shape (128, 128, 3)
x = x.reshape((1,) + x.shape)  # array with shape (1, 128, 128, 3)

# define input shape
input_shape = (img_height, img_width, 3)

model = Sequential()
# encoding
model.add(Conv2D(128, (3, 3), activation='relu', input_shape=input_shape, 
padding='same'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))

# decoding
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(UpSampling2D(size=(2,2)))
model.add(Conv2D(64, (3, 3), activation='relu', padding='same'))
model.add(UpSampling2D(size=(2,2)))
model.add(Conv2D(128, (3, 3), activation='relu', padding='same'))
model.add(Conv2D(3, (3, 3), activation='sigmoid', padding='same'))

model.compile(loss='binary_crossentropy', optimizer='adam')
print(model.summary())

checkpoint = ModelCheckpoint("autoencoder-loss-{loss:.4f}.hdf5", monitor='loss', verbose=0, save_best_only=True, mode='min') 
model.fit(x, x, epochs=10, batch_size=1, verbose=1, callbacks=[checkpoint])

y = model.predict(x)

y = y[0, :, :, :]
y = array_to_img(y)
save_img(output_img, y)

I've looked at a handful of tutorials for reference, but I still can't figure out what my issue is.

Any guidance/suggestions/help would be greatly appreciated.

Thanks!

J Doug · Accepted Answer · 2018-12-01 00:44:28Z

2

this solved the problem. The code was just missing

x = x.astype('float32') / 255.

This is a numpy built-in function to convert the values contained in that vector to floats.

This allows us to get decimal values, where the values are divided by 255. RGB values are stored as 8 bit integers, so we divide the values in the vector by 255 (2^8 - 1), to represent the colour as a decimal value between 0.0 and 1.0.

edited Dec 1, 2018 at 0:44

J Doug

917 bronze badges

answered Nov 30, 2018 at 4:33

Dipack

1955 bronze badges

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

5 Comments

J Doug Over a year ago

That's really helpful. I guess what I'm really looking for is essentially the same image as output. For that, it doesn't seem like I should need any label, as the output should "match" the input. Can you point me in the direction as to how I might do that?

Dipack Over a year ago

Oh I see. Looking around on the Keras blog, I was able to find this tutorial on convolutional autoencoders. Perhaps that could be what you're looking for?

J Doug Over a year ago

That tutorial solved the problem (even though I've already seen it about 1000 times). I was missing x = x.astype('float32') / 255. which normalizes pixel values between 0 and 1. Thanks for the help!

Dipack Over a year ago

That's awesome! The astype(..) bit is a numpy built-in function to convert the values contained in that vector to floats. This allows us to get decimal values too when the values are then divided by 255. RGB values are stored as 8 bit integers, so we divide the values in the vector by 255 (2^8 - 1), to represent the colour as a decimal value between 0.0 and 1.0.

dedObed Over a year ago

This answer, though it happened to be useful to the OP, is incorrect: The model.fit(x, x, ...) is exactly the right thing to do, when you're training an autoencoder...

Collectives™ on Stack Overflow

Keras Convolutional Autoencoder blank output

1 Answer 1

5 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

5 Comments

Your Answer

Sign up or log in

Post as a guest

Related