Validation accuracy not changing while loss is decreasing in keras image classification? [closed]

Question

Image classification Problem

I have two classes of images.

• Fake
• Real

Dataset splitting detail is below.

• Total Training FAKE Images 3457

• Total Training REAL Images 675

• Total validation FAKE Images 642

• Total validation REAL Images 336

I have applied CNN on that but my validation accuracy is decreasing while loss is increasing. I have also applied Data Augmentation and preprocessing on data.

train_dir = '/content/drive/MyDrive/Training/Training Data'
validations_dir = '/content/drive/MyDrive/Training/Validation Data'
train_fake_dir = '/content/drive/MyDrive/Training/Training Data/FAKE'
train_real_dir = '/content/drive/MyDrive/Training/Training Data/REAL'

validation_fake_dir = '/content/drive/MyDrive/Training/Validation Data/FAKE'
validation_real_dir = '/content/drive/MyDrive/Training/Validation Data/REAL'
num_fake_train = len(os.listdir(train_fake_dir))
num_real_train = len(os.listdir(train_real_dir))

num_fake_validation = len(os.listdir(validation_fake_dir))
num_real_validation = len(os.listdir(validation_real_dir))
print("Total Training FAKE Images",num_fake_train)
print("Total Training REAL Images",num_real_train)
print("--")
print("Total validation FAKE Images",num_fake_validation)
print("Total validation REAL Images",num_real_validation)
total_train = num_fake_train+num_real_train
total_validation = num_fake_validation+num_real_validation
print("Total Training Images",total_train)
print("--")
print("Total Validation Images",total_validation)

image_gen_train = ImageDataGenerator(rescale = 1./255,rotation_range = 40,width_shift_range=0.3,
                                     height_shift_range=0.3,shear_range = 0.3,zoom_range = 0.2,
                                     horizontal_flip = True,fill_mode = 'nearest')
train_data_gen = image_gen_train.flow_from_directory(batch_size = batch_size,
                                                     directory = train_dir,
                                                     shuffle= True,
                                                     target_size = (img_height,img_width),
                                                     class_mode = 'binary')
image_generator_validation = ImageDataGenerator(rescale=1./255)
val_data_gen = image_generator_validation.flow_from_directory(batch_size=batch_size,
                                                 directory=validations_dir,
                                                 target_size=(img_height,img_width),
                                                 shuffle= True,
                                                 class_mode='binary')
classifier = tf.keras.Sequential([
        tf.keras.layers.Conv2D(16,(3,3),activation='relu',input_shape=(img_width,img_height, 3)),
        tf.keras.layers.Dropout(0.5),
        tf.keras.layers.BatchNormalization(),
        tf.keras.layers.MaxPooling2D(2,2),
        tf.keras.layers.Flatten(),
        tf.keras.layers.Dense(128,activation= 'relu'),
        tf.keras.layers.Dense(2,activation='softmax')  
])
classifier.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['acc'])
history_classifier = classifier.fit(train_data_gen,epochs = epochs,validation_data=val_data_gen,verbose = 1)

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'