Compile & Training

# compile model
model.compile(loss='binary_crossentropy',
              optimizer=tf.keras.optimizers.Adam(learning_rate = 0.0001, decay=1e-6),
              metrics=['accuracy', 'Recall', 'Precision'])


# make directory for logs
logdir = os.path.join('/content/gdrive/MyDrive/Image Dataset/logs', model_name)
# os.mkdir(logdir)

from math import floor
N_FOLDS = 5
INIT_LR = 3e-4
T_BS = 16
V_BS = 16
decay_rate = 0.95
decay_step = 1


# early stopping
cp = EarlyStopping(monitor ='val_loss', mode = 'min', verbose = 2, patience = PATIENCE, restore_best_weights=True)

mc = ModelCheckpoint(model_name, monitor = 'val_loss', mode = 'min', verbose = 2, save_best_only = True)

tsb = TensorBoard(log_dir=logdir)

lrs = LearningRateScheduler(lambda epoch : INIT_LR * pow(decay_rate, floor(epoch / decay_step))), 

# training
start = timer()

# Fit the model 
history= model.fit(train_g, 
                   epochs=EPOCHS,
                   steps_per_epoch=len(train_g),
                   validation_data=val_g,
                   validation_steps=len(val_g), 
                   callbacks= [cp, mc, tsb, lrs])


end = timer()
elapsed = end - start
print('Total Time Elapsed: ', int(elapsed//60), ' minutes ', (round(elapsed%60)), ' seconds')