def compile(name,
model: Sequential,
train_samples: pd.DataFrame,
validation_samples: pd.DataFrame,
gen,
type='img'):
# model.add(Reshape((-1, num_classes), name=RESHAPED))
size = 5
steps_per_epoch = len(train_samples) // size
validation_steps = len(validation_samples) // size
train_generator = gen(train_samples, type)(size, infinite=True)
validation_generator = gen(validation_samples, type)(size, infinite=True)
adam = optimizers.Adam(lr=0.0001)
model.compile(loss='categorical_crossentropy', optimizer=adam)
history_object = model.fit_generator(train_generator,
validation_data=validation_generator,
epochs=5,
callbacks=None,
validation_steps=validation_steps,
steps_per_epoch=steps_per_epoch)
model.save_weights(name)
# model.save('fcn_model.h5')
print(history_object.history.keys())
print('Loss')
print(history_object.history['loss'])
print('Validation Loss')
print(history_object.history['val_loss'])
verbose=1,
save_best_only=True)
esCallBack = EarlyStopping(monitor='val_loss',
min_delta=1e-4,
patience=20,
verbose=1,
mode='auto')
rlrPlateau = ReduceLROnPlateau(monitor='val_loss',
factor=0.5,
patience=10,
verbose=1,
mode='auto',
epsilon=0.0001,
cooldown=0,
min_lr=0)
print("Starting to fit the model...")
model.fit_generator(generator=train_datagen.flow(x_train,
y_train,
batch_size=32),
steps_per_epoch=len(x_train) / 32,
verbose=1,
validation_data=valid_datagen.flow(x_valid,
y_valid,
batch_size=32),
validation_steps=len(x_valid) / 32,
workers=4,
epochs=500,
callbacks=[tbCallBack, mcCallBack, esCallBack, rlrPlateau])
