def test_model1():
features, labels = loadFromPickle()
labels_count = int(len(labels) / MAX_NUM)
# features, labels = augmentData(features, labels)
features, labels = shuffle(features, labels)
labels = prepress_labels(labels)
train_x, test_x, train_y, test_y = train_test_split(features,
labels,
random_state=0,
test_size=0.1)
# train_x = train_x.reshape(train_x.shape[0], 28, 28, 1)
# test_x = test_x.reshape(test_x.shape[0], 28, 28, 1)
model, callbacks_list = keras_model1((28 * 28, ), labels_count)
print_summary(model)
model.fit(train_x,
train_y,
validation_data=(test_x, test_y),
epochs=500,
batch_size=256)
# model.fit(train_x, train_y, validation_data=(test_x, test_y), epochs=500, batch_size=256,
# callbacks=[TensorBoard(log_dir="TensorBoard")])
# 开始评估模型效果 # verbose=0为不输出日志信息
score = model.evaluate(test_x, test_y, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1]) # 准确度
model.save('model1.h5')
def test_model():
features, labels = loadFromPickle()
labels_count = len(load_label_name())
# features, labels = augmentData(features, labels)
features, labels = shuffle(features, labels)
labels = prepress_labels(labels)
train_x, test_x, train_y, test_y = train_test_split(features,
labels,
random_state=0,
test_size=0.2)
train_x = train_x.reshape(train_x.shape[0], 28, 28, 1)
test_x = test_x.reshape(test_x.shape[0], 28, 28, 1)
model, callbacks_list = keras_model((
28,
28,
1,
), labels_count)
print_summary(model)
model.fit(train_x,
train_y,
validation_data=(test_x, test_y),
epochs=40,
batch_size=128)
# 开始评估模型效果 # verbose=0为不输出日志信息
score = model.evaluate(test_x, test_y, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1]) # 准确度
model.save('model.h5')
def validate():
data_dir = ".\\data\\"
label_names = get_labels(data_dir)
model = load_model('asr_model.h5') # 加载训练模型
features, labels = loadFromPickle()
features, labels = shuffle(features, labels)
features=features.reshape(features.shape[0],20,32,1)
labels=prepress_labels(labels)
train_x, test_x, train_y, test_y = train_test_split(features, labels, random_state=0,
test_size=0.3)
print_summary(model)
# 开始评估模型效果 # verbose=0为不输出日志信息
score = model.evaluate(test_x, test_y, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1]) # 准确度
def evaluate(self, data_dir):
x_data, y_label = load_img_from_dir(data_dir,
target_size=(self.IMAGE_SIZE,
self.IMAGE_SIZE),
max_num=60)
for i in range(x_data.shape[0]):
x_data[i] = preprocess_input(x_data[i])
x_data = x_data.reshape(x_data.shape[0], self.IMAGE_SIZE,
self.IMAGE_SIZE, 3)
y_label_one_hot = prepress_labels(y_label)
# 验证应该使用从未见过的图片
train_x, test_x, train_y, test_y = train_test_split(x_data,
y_label_one_hot,
random_state=0,
test_size=0.5)
# 开始评估模型效果 # verbose=0为不输出日志信息
score = model.evaluate(test_x, test_y, verbose=1, steps=1)
print('Test loss:', score[0])
print('Test accuracy:', score[1]) # 准确度
def train(self, data_dir, epochs=3, callback=None, model_name='vgg16'):
"""
train 函数, 训练模型
Keyword arguments::
epochs: int 训练次数
"""
if self.busy:
return 1
self.busy = True
label_names = get_labels(data_dir)
self.NUM_CLASSES = len(label_names)
base_model = self.get_base_model(model_name)
x_data, y_label = load_img_from_dir(data_dir,
target_size=(self.IMAGE_SIZE,
self.IMAGE_SIZE),
max_num=30)
for i in range(x_data.shape[0]):
x_data[i] = self.preprocess_input(x_data[i])
print(x_data.shape)
print(x_data[0].shape)
x_data = x_data.reshape(x_data.shape[0], self.IMAGE_SIZE,
self.IMAGE_SIZE, 3)
y_label_one_hot = prepress_labels(y_label)
# 验证应该使用从未见过的图片
train_x, test_x, train_y, test_y = train_test_split(x_data,
y_label_one_hot,
random_state=0,
test_size=0.3)
# 自定义FC层以基本模型的输入为卷积层的最后一层
x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(self.FC_NUMS, activation='relu')(x)
prediction = Dense(self.NUM_CLASSES, activation='softmax')(x)
# 构造完新的FC层，加入custom层
model = Model(inputs=base_model.input, outputs=prediction)
# 获取模型的层数
print("layer nums:", len(model.layers))
# 除了FC层，靠近FC层的一部分卷积层可参与参数训练，
# 一般来说，模型结构已经标明一个卷积块包含的层数，
# 在这里我们选择TRAIN_LAYERS为3，表示最后一个卷积块和FC层要参与参数训练
for layer in model.layers:
layer.trainable = False
for layer in model.layers[-self.TRAIN_LAYERS:]:
layer.trainable = True
for layer in model.layers:
print("layer.trainable:", layer.trainable)
# 预编译模型
model.compile(optimizer=SGD(lr=0.0001, momentum=0.9),
loss='categorical_crossentropy',
metrics=['accuracy'])
model.summary()
model.fit(
train_x,
train_y,
validation_data=(test_x, test_y),
# model.fit(x_data, y_label_one_hot,
# validation_split=0.4,
callbacks=[AccuracyLogger(callback)],
epochs=epochs,
batch_size=4,
# steps_per_epoch=1,validation_steps =1 ,
verbose=1,
shuffle=True)
self.model = model
model.save(os.path.join(data_dir, 'model.h5'))
self.label_names = label_names
self.dump_label_name(label_names)
# self.convert_tflite()
self.session = K.get_session()
self.graph = tf.get_default_graph()
self.busy = False
def train(self, data_dir, epochs=3, callback=None):
if self.busy:
return 1
self.busy = True
label_names = get_labels(data_dir)
self.NUM_CLASSES = len(label_names)
from keras.applications.vgg16 import VGG16, preprocess_input
# 采用VGG16为基本模型，include_top为False，表示FC层是可自定义的，抛弃模型中的FC层；该模型会在~/.keras/models下载基本模型
base_model = VGG16(input_shape=(self.IMAGE_SIZE, self.IMAGE_SIZE, 3),
include_top=False,
weights='imagenet')
x_data, y_label = load_img_from_dir(data_dir,
target_size=(self.IMAGE_SIZE,
self.IMAGE_SIZE),
max_num=30)
for i in range(x_data.shape[0]):
x_data[i] = preprocess_input(x_data[i])
print(x_data.shape)
print(x_data[0].shape)
x_data = x_data.reshape(x_data.shape[0], self.IMAGE_SIZE,
self.IMAGE_SIZE, 3)
y_label_one_hot = prepress_labels(y_label)
# 验证应该使用从未见过的图片
train_x, test_x, train_y, test_y = train_test_split(x_data,
y_label_one_hot,
random_state=0,
test_size=0.3)
# 自定义FC层以基本模型的输入为卷积层的最后一层
x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(self.FC_NUMS, activation='relu')(x)
prediction = Dense(self.NUM_CLASSES, activation='softmax')(x)
# 构造完新的FC层，加入custom层
model = Model(inputs=base_model.input, outputs=prediction)
# 获取模型的层数
print("layer nums:", len(model.layers))
# 除了FC层，靠近FC层的一部分卷积层可参与参数训练，
# 一般来说，模型结构已经标明一个卷积块包含的层数，
# 在这里我们选择FREEZE_LAYERS为17，表示最后一个卷积块和FC层要参与参数训练
for layer in model.layers[:self.FREEZE_LAYERS]:
layer.trainable = False
for layer in model.layers[self.FREEZE_LAYERS:]:
layer.trainable = True
for layer in model.layers:
print("layer.trainable:", layer.trainable)
# 预编译模型
model.compile(optimizer=SGD(lr=0.0001, momentum=0.9),
loss='categorical_crossentropy',
metrics=['accuracy'])
model.summary()
model.fit(
train_x,
train_y,
validation_data=(test_x, test_y),
# model.fit(x_data, y_label_one_hot,
# validation_split=0.4,
callbacks=[AccuracyLogger(callback)],
epochs=epochs,
batch_size=4,
# steps_per_epoch=1,validation_steps =1 ,
verbose=1,
shuffle=True)
self.model = model
model.save(os.path.join(data_dir, 'model.h5'))
self.dump_label_name(label_names)
self.session = K.get_session()
self.graph = tf.get_default_graph()
self.busy = False
