CODEWITHSUNDEEP
pythontensorflowkerasimage-segmentationloss-function
illan
illan

Reputation: 375

How to properly use CategoricalCrossentropy loss for image segmentation in Tensorflow 2.0/Keras?

I am trying to train a U-Net derivative to do single-class image segmentation but am having problems using the tf.keras.losses.SparseCategoricalCrossentropy() and tf.keras.losses.CategoricalCrossentropy() functions in Keras. Which is the more appropriate and how to use it properly?

If I try to use SpareCategoricalCrossentropy, I get the error:

Received a label value of 1 which is outside the valid range of [0, 1)

If I try to use CategoricalCrossentropy, I get:

You are passing a target array of shape (3600, 64, 64, 1) while using as loss categorical_crossentropy. categorical_crossentropy expects targets to be binary matrices (1s and 0s) of shape (samples, classes). If your targets are integer classes, you can convert them to the expected format via: y_binary = tf.keras.utils.to_categorical(y_int)

Using to_categorical for my mask vs background segmentation problem, it increases the last dimension to 2, which should not be necessary. My prediction should be a number between 0 and 1 in a single "channel".

Model definition snippet:

input_x = tf.keras.Input(batch_shape=(batch_size, xsze, ysze, 3), name='input_x') 
predictions = tf.keras.layers.Conv2D(1, [1, 1], activation='linear', name='output_x')(drop11) 

loss = tf.keras.losses.SparseCategoricalCrossentropy()
model.compile(optimizer=tf.keras.optimizers.Adam(),  # Optimizer
              loss=loss, 
              metrics=[tf.keras.metrics.SparseCategoricalAccuracy()]) 

checkpointer = tf.keras.callbacks.ModelCheckpoint(session_name + '_backup.h5', save_best_only=True, monitor = 'acc', verbose = 0)
early_stopper = tf.keras.callbacks.EarlyStopping(monitor='val_loss',patience=5, verbose=1,min_delta=0.005)
history = model.fit(data_train, roi_train,
                    batch_size=batch_size,
                    epochs = 10,
                    validation_data=(data_val, roi_zoom_val),callbacks=[checkpointer,early_stopper])

My roi_train is a numpy array with 0's and 1's of type float32.

Upvotes: 0

Views: 1005

Answers (1)

today
today

Reputation: 33420

Since you only have one class and you want each value in the segmentation map to be between 0 and 1, then you should use sigmoid as the activation of last layer and binary_crossentropy as the loss function. That's because for each pixel you are facing a binary decision: does this pixel belong to foreground or background?

Upvotes: 1

Related Questions