classifier = tf.keras.models.Sequential()
classifier.add(tf.keras.layers.Conv2D(32, (3, 3), input_shape = (224, 224, 3), activation = 'relu'))
classifier.add(tf.keras.layers.MaxPooling2D(pool_size = (2, 2)))
classifier.add(tf.keras.layers.Conv2D(32, (3, 3), activation = 'relu'))
classifier.add(tf.keras.layers.MaxPooling2D(pool_size = (2, 2)))
classifier.add(tf.keras.layers.Flatten())
classifier.add(tf.keras.layers.Dense(units = 128, activation = 'relu'))
classifier.add(tf.keras.layers.Dense(units = 1, activation = 'sigmoid'))
classifier.compile(optimizer = 'adam', loss = 'BinaryCrossentropy', metrics = ['accuracy'])
train_datagen = ImageDataGenerator(rescale = 1./255, shear_range = 0.2, zoom_range = 0.2, horizontal_flip = False)
test_datagen = ImageDataGenerator(rescale = 1./255)
training_set = train_datagen.flow_from_directory('/content/drive/MyDrive/Training/Training Data',
target_size = (224, 224),
batch_size = 50,
class_mode = 'sparse')
test_set = test_datagen.flow_from_directory('/content/drive/MyDrive/Training/Validation Data',
target_size = (224, 224),
batch_size = 50,
class_mode = 'sparse')
classifier.fit(training_set,
steps_per_epoch = 4132/50,
epochs = 10,
validation_data = test_set,
validation_steps = 978/50)
validation loss is changing but validation accuracy remain same. can anyone here tell me why this happens?
I have dataset with two classes while training data of 4132 and validation data of 978.
question from:
https://stackoverflow.com/questions/65861658/validation-acccuracy-not-improving 与恶龙缠斗过久,自身亦成为恶龙;凝视深渊过久,深渊将回以凝视…