tensorflow - Validation accuracy not changing while loss is decreasing in keras image classification?

Question

Closed. This question is opinion-based. It is not currently accepting answers. question from:https://stackoverflow.com/questions/65859726/validation-accuracy-not-changing-while-loss-is-decreasing-in-keras-image-classif

Answer 1

in model.compile your loss is incorrect. It should be

loss='BinaryCrossentropy'

In your model the last layer should be

tf.keras.layers.Dense(1,activation='sigmoid')

Alternatively you can keep everything as is but change class_mode in the train_data_gen and val_data_gen to

class_mode='sparse'