def __init__(self, model_file, num_classes, input_image_size):
if not gfile.Exists(model_file) or input_image_size != (224, 224, 3):
print("need download the model")
mobile_net = MobileNet(weights='imagenet',
input_shape=input_image_size)
self.mobile_net_model = models.Model(
inputs=mobile_net.input,
outputs=mobile_net.get_layer(
'global_average_pooling2d').output)
print("save the downloaded model for reuse")
mobile_net.save(model_file)
else:
self.mobile_net_model = models.load_model(model_file)
classes = num_classes
self.inputs = layers.Input(shape=(1024, ))
self.outputs = layers.Dense(classes,
activation='softmax',
name='final_output')(self.inputs)
self.one_layer_model = models.Model(inputs=[self.inputs],
outputs=[self.outputs])
final_output = layers.Dense(classes,
activation='softmax',
name='final_output')(
self.mobile_net_model.output)
self.final_model = models.Model(inputs=self.mobile_net_model.inputs,
outputs=final_output)
def precision_m(y_true, y_pred):
true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
precision = true_positives / (predicted_positives + K.epsilon())
return precision
def f1_m(y_true, y_pred):
precision = precision_m(y_true, y_pred)
recall = recall_m(y_true, y_pred)
return 2 * ((precision * recall) / (precision + recall + K.epsilon()))
model.save('C:/nmb/nmb_data/h5/5s/mobilenet/mobilenet_rmsprop_1.h5')
# 컴파일, 훈련
op = RMSprop(lr=1e-3)
batch_size = 8
es = EarlyStopping(monitor='val_loss',
patience=20,
restore_best_weights=True,
verbose=1)
lr = ReduceLROnPlateau(monitor='val_loss', vactor=0.5, patience=10, verbose=1)
path = 'C:/nmb/nmb_data/h5/5s/mobilenet/mobilenet_rmsprop_1.h5'
mc = ModelCheckpoint(path, monitor='val_loss', verbose=1, save_best_only=True)
model.compile(optimizer=op,
loss="sparse_categorical_crossentropy",
x_test = x_test.reshape(x_test.shape[0], x_test.shape[1], x_test.shape[2], aaa)
print(x_train.shape, y_train.shape) # (3628, 128, 862, 1) (3628,)
print(x_test.shape, y_test.shape) # (908, 128, 862, 1) (908,)
model = MobileNet(
include_top=True,
input_shape=(128, 862, 1),
classes=2,
pooling=None,
weights=None,
)
model.summary()
# model.trainable = False
model.save('C:/nmb/nmb_data/h5/5s/mobilenet_nadam_1.h5')
# 컴파일, 훈련
op = Nadam(lr=1e-3)
batch_size = 8
es = EarlyStopping(monitor='val_loss',
patience=20,
restore_best_weights=True,
verbose=1)
lr = ReduceLROnPlateau(monitor='val_loss', vactor=0.5, patience=10, verbose=1)
path = 'C:/nmb/nmb_data/h5/5s/mobilenet/mobilenet_nadam_1.h5'
mc = ModelCheckpoint(path, monitor='val_loss', verbose=1, save_best_only=True)
model.compile(optimizer=op,
loss="sparse_categorical_crossentropy",
x_test = x_test.reshape(x_test.shape[0], x_test.shape[1], x_test.shape[2], aaa)
print(x_train.shape, y_train.shape) # (3628, 128, 862, 1) (3628,)
print(x_test.shape, y_test.shape) # (908, 128, 862, 1) (908,)
model = MobileNet(
include_top=True,
input_shape=(128, 862, 1),
classes=2,
pooling=None,
weights=None,
)
model.summary()
# model.trainable = False
model.save('C:/nmb/nmb_data/h5/5s/mobilenet_sgd_1.h5')
# 컴파일, 훈련
op = SGD(lr=1e-2)
batch_size = 8
es = EarlyStopping(monitor='val_loss',
patience=20,
restore_best_weights=True,
verbose=1)
lr = ReduceLROnPlateau(monitor='val_loss', vactor=0.5, patience=10, verbose=1)
path = 'C:/nmb/nmb_data/h5/5s/mobilenet/mobilenet_sgd_1.h5'
mc = ModelCheckpoint(path, monitor='val_loss', verbose=1, save_best_only=True)
model.compile(optimizer=op,
loss="sparse_categorical_crossentropy",
def precision_m(y_true, y_pred):
true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
precision = true_positives / (predicted_positives + K.epsilon())
return precision
def f1_m(y_true, y_pred):
precision = precision_m(y_true, y_pred)
recall = recall_m(y_true, y_pred)
return 2 * ((precision * recall) / (precision + recall + K.epsilon()))
model.save('C:/nmb/nmb_data/h5/5s/mobilenet/mobilenet_rmsprop_f80_m20_2.h5')
# 컴파일, 훈련
op = RMSprop(lr=1e-3)
batch_size = 8
es = EarlyStopping(monitor='val_loss',
patience=20,
restore_best_weights=True,
verbose=1)
lr = ReduceLROnPlateau(monitor='val_loss', vactor=0.5, patience=10, verbose=1)
path = 'C:/nmb/nmb_data/h5/5s/mobilenet/mobilenet_rmsprop_f80_m20_2.h5'
mc = ModelCheckpoint(path, monitor='val_loss', verbose=1, save_best_only=True)
model.compile(optimizer=op,
loss="sparse_categorical_crossentropy",
x_train = x_train.reshape(x_train.shape[0], x_train.shape[1], x_train.shape[2],
aaa)
x_test = x_test.reshape(x_test.shape[0], x_test.shape[1], x_test.shape[2], aaa)
print(x_train.shape, y_train.shape) # (3628, 128, 862, 1) (3628,)
print(x_test.shape, y_test.shape) # (908, 128, 862, 1) (908,)
model = MobileNet(
include_top=True,
input_shape=(128, 862, 1),
classes=2,
pooling=None,
weights=None,
)
model.summary()
# model.trainable = False
model.save('C:\\nmb\\nmb_data\\h5\\pre_train\\mobilenet_rmsprop_.h5')
# 컴파일, 훈련
op = RMSprop(lr=1e-4)
batch_size = 32
es = EarlyStopping(monitor='val_loss',
patience=20,
restore_best_weights=True,
verbose=1)
lr = ReduceLROnPlateau(monitor='val_loss', vactor=0.5, patience=10, verbose=1)
path = 'C:\\nmb\\nmb_data\\h5\\pre_train\\mobilenet_rmsprop_1e4.h5'
mc = ModelCheckpoint(path, monitor='val_loss', verbose=1, save_best_only=True)
tb = TensorBoard(log_dir='C:/nmb/nmb_data/graph/' + 'mobilenet_rmsprop_1e4' +
"/",
histogram_freq=0,
write_graph=True,
x_test = x_test.reshape(x_test.shape[0], x_test.shape[1], x_test.shape[2], aaa)
print(x_train.shape, y_train.shape) # (3628, 128, 862, 1) (3628,)
print(x_test.shape, y_test.shape) # (908, 128, 862, 1) (908,)
model = MobileNet(
include_top=True,
input_shape=(128, 862, 1),
classes=2,
pooling=None,
weights=None,
)
model.summary()
# model.trainable = False
model.save('C:/nmb/nmb_data/h5/5s/mobilenet_adadelta_1.h5')
# 컴파일, 훈련
op = Adadelta(lr=1e-3)
batch_size = 8
es = EarlyStopping(monitor='val_loss',
patience=20,
restore_best_weights=True,
verbose=1)
lr = ReduceLROnPlateau(monitor='val_loss', vactor=0.5, patience=10, verbose=1)
path = 'C:/nmb/nmb_data/h5/5s/mobilenet/mobilenet_adadelta_1.h5'
mc = ModelCheckpoint(path, monitor='val_loss', verbose=1, save_best_only=True)
model.compile(optimizer=op,
loss="sparse_categorical_crossentropy",
