def test_inceptionresnetv2_variable_input_channels():
global_image_data_format = K.image_data_format()
K.set_image_data_format('channels_first')
input_shape = (1, None, None)
model = applications.InceptionResNetV2(weights=None,
include_top=False,
input_shape=input_shape)
assert model.output_shape == (None, 1536, None, None)
input_shape = (4, None, None)
model = applications.InceptionResNetV2(weights=None,
include_top=False,
input_shape=input_shape)
assert model.output_shape == (None, 1536, None, None)
K.set_image_data_format('channels_last')
input_shape = (None, None, 1)
model = applications.InceptionResNetV2(weights=None,
include_top=False,
input_shape=input_shape)
assert model.output_shape == (None, None, None, 1536)
input_shape = (None, None, 4)
model = applications.InceptionResNetV2(weights=None,
include_top=False,
input_shape=input_shape)
assert model.output_shape == (None, None, None, 1536)
K.set_image_data_format(global_image_data_format)
def model_(self, number=0):
print('=' * 100)
print('Load Model')
print('Model name: ', self.save_name)
print('-' * 100)
if self.self_training:
self.model = models.load_model(self.model_dir + '/' +
self.save_name + '.h5')
adam = op.Adam(lr=0.00001)
self.model.compile(optimizer=adam,
loss='categorical_crossentropy',
metrics=['acc'])
else:
a = app.InceptionResNetV2(include_top=False,
weights='imagenet',
input_shape=(224, 224, 3),
pooling='avg',
classes=10)
x = a.output
output = layers.Dense(10, activation='softmax')(x)
self.model = models.Model(a.input,
output,
name='Pretrain_inception_resnet_v2')
adam = op.Adam(lr=0.0001)
self.model.compile(optimizer=adam,
loss='categorical_crossentropy',
metrics=['acc'])
print('Complete')
print('=' * 100)
def build(width, height, depth, classes):
# model = Sequential()
inputShape = (height, width, depth)
# chanDim = -1
if K.image_data_format() == "channels_first":
inputShape = (depth, height, width)
# chanDim = 1
# model.add(Conv2D(64, (3, 3), padding="same",
# input_shape=inputShape))
base_model = applications.InceptionResNetV2(
weights="imagenet", include_top=False,
input_shape=inputShape) # 预训练的VGG16网络，替换掉顶部网络
print('base_model', base_model.summary())
# for layer in base_model.layers[:15]: layer.trainable = False # 冻结预训练网络前15层
top_model = Sequential() # 自定义顶层网络
top_model.add(
Flatten(input_shape=base_model.output_shape[1:])) # 将预训练网络展平
top_model.add(Dense(2, activation='relu')) # 全连接层，输入像素256
top_model.add(Dropout(0.5)) # Dropout概率0.5
top_model.add(Dense(classes, activation='softmax')) # 输出层，二分类
print('top_model', top_model.summary())
model = Model(inputs=base_model.input,
outputs=top_model(base_model.output))
return model
def base_network(network='InceptionV3'):
if network == 'InceptionV3':
base_model = applications.InceptionV3(weights='imagenet',
include_top=False)
elif network == 'VGG16':
base_model = applications.VGG16(weights='imagenet', include_top=False)
elif network == 'VGG19':
base_model = applications.VGG19(weights='imagenet', include_top=False)
elif network == 'ResNet50':
base_model = applications.ResNet50(weights='imagenet',
include_top=False)
elif network == 'InceptionResNetV2':
base_model = applications.InceptionResNetV2(weights='imagenet',
include_top=False)
elif network == 'MobileNet':
base_model = applications.MobileNet(weights='imagenet',
include_top=False)
elif network == 'DenseNet121':
base_model = applications.DenseNet121(weights='imagenet',
include_top=False)
else:
print('Wrong Model selected.')
return None
return base_model
def save_model_to_file(filename,
architecture,
weights='imagenet',
input_shape=(299, 299, 3)):
base_path = os.getcwd()
model_path = os.path.join(base_path, filename)
# Create and save network file
if not os.path.exists(model_path):
# Initialise Keras object
if architecture == 'inceptionv3':
mymodel = applications.InceptionV3(
weights=weights, input_tensor=Input(shape=input_shape))
elif architecture == 'resnet152v2':
mymodel = applications.ResNet152V2(
weights=weights, input_tensor=Input(shape=input_shape))
elif architecture == 'inceptionresnetv2':
mymodel = applications.InceptionResNetV2(
weights=weights, input_tensor=Input(shape=input_shape))
else:
print('Invalid architecture')
return
mymodel.save(os.path.join(base_path, filename))
def save_bottlebeck_features():
train_datagen = ImageDataGenerator(rescale=1. / 255)
test_datagen = ImageDataGenerator(rescale=1. / 255)
# build the InceptionResNetV2 network
model = applications.InceptionResNetV2(include_top=False,
weights='imagenet')
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size=(img_width, img_height),
batch_size=batch_size,
class_mode=None,
shuffle=False)
bottleneck_features_train = model.predict_generator(
train_generator,
aug_factor * nb_classes * nb_train_samples // batch_size)
train_labels = np.tile(np.repeat(np.arange(nb_classes), nb_train_samples),
aug_factor)
np.savez(bn_train_path, data=bottleneck_features_train, label=train_labels)
test_generator = test_datagen.flow_from_directory(validation_data_dir,
target_size=(img_width,
img_height),
batch_size=batch_size,
class_mode=None,
shuffle=False)
bottleneck_features_validation = model.predict_generator(
test_generator, nb_classes * nb_validation_samples // batch_size)
validation_labels = np.repeat(np.arange(nb_classes), nb_validation_samples)
np.savez(bn_validation_path,
data=bottleneck_features_validation,
label=validation_labels)
def models_factory(model_type, image_size):
if model_type == "vgg16":
base_model = applications.VGG16(weights='imagenet',
include_top=False,
input_shape=(image_size[0],
image_size[1], 3))
elif model_type == "vgg19":
base_model = applications.VGG19(weights='imagenet',
include_top=False,
input_shape=(image_size[0],
image_size[1], 3))
elif model_type == "resnet50":
base_model = applications.ResNet50(weights='imagenet',
include_top=False,
input_shape=(image_size[0],
image_size[1], 3))
elif model_type == "inceptionv3":
base_model = applications.InceptionV3(weights='imagenet',
include_top=False,
input_shape=(image_size[0],
image_size[1], 3))
elif model_type == "xception":
base_model = applications.Xception(weights='imagenet',
include_top=False,
input_shape=(image_size[0],
image_size[1], 3))
elif model_type == "mobilenet":
base_model = applications.MobileNet(weights='imagenet',
include_top=False,
input_shape=(image_size[0],
image_size[1], 3))
elif model_type == "inceptionresnetv2":
base_model = applications.InceptionResNetV2(weights='imagenet',
include_top=False,
input_shape=(image_size[0],
image_size[1],
3))
elif model_type == "nasnet":
base_model = applications.nasnet.NASNetLarge(
weights='imagenet',
include_top=False,
input_shape=(image_size[0], image_size[1], 3))
for layer in base_model.layers:
layer.trainable = False
top_model = Sequential()
top_model.add(Flatten(input_shape=base_model.output_shape[1:]))
top_model.add(
Dense(1024, kernel_initializer='glorot_uniform', activation='relu'))
top_model.add(
Dense(1024, kernel_initializer='glorot_uniform', activation='relu'))
top_model.add(Dense(1, activation='sigmoid'))
model = Model(input=base_model.input, output=top_model(base_model.output))
return model, base_model
def get_imagenet_architecture(architecture, variant, size, alpha, output_layer, include_top=False, weights='imagenet'):
from keras import applications, Model
if include_top:
assert output_layer == 'last'
if size == 'auto':
size = get_image_size(architecture, variant, size)
shape = (size, size, 3)
if architecture == 'densenet':
if variant == 'auto':
variant = 'densenet-121'
if variant == 'densenet-121':
model = applications.DenseNet121(weights=weights, include_top=include_top, input_shape=shape)
elif variant == 'densenet-169':
model = applications.DenseNet169(weights=weights, include_top=include_top, input_shape=shape)
elif variant == 'densenet-201':
model = applications.DenseNet201(weights=weights, include_top=include_top, input_shape=shape)
elif architecture == 'inception-resnet-v2':
model = applications.InceptionResNetV2(weights=weights, include_top=include_top, input_shape=shape)
elif architecture == 'mobilenet':
model = applications.MobileNet(weights=weights, include_top=include_top, input_shape=shape, alpha=alpha)
elif architecture == 'mobilenet-v2':
model = applications.MobileNetV2(weights=weights, include_top=include_top, input_shape=shape, alpha=alpha)
elif architecture == 'nasnet':
if variant == 'auto':
variant = 'large'
if variant == 'large':
model = applications.NASNetLarge(weights=weights, include_top=include_top, input_shape=shape)
else:
model = applications.NASNetMobile(weights=weights, include_top=include_top, input_shape=shape)
elif architecture == 'resnet-50':
model = applications.ResNet50(weights=weights, include_top=include_top, input_shape=shape)
elif architecture == 'vgg-16':
model = applications.VGG16(weights=weights, include_top=include_top, input_shape=shape)
elif architecture == 'vgg-19':
model = applications.VGG19(weights=weights, include_top=include_top, input_shape=shape)
elif architecture == 'xception':
model = applications.Xception(weights=weights, include_top=include_top, input_shape=shape)
elif architecture == 'inception-v3':
model = applications.InceptionV3(weights=weights, include_top=include_top, input_shape=shape)
if output_layer != 'last':
try:
if isinstance(output_layer, int):
layer = model.layers[output_layer]
else:
layer = model.get_layer(output_layer)
except Exception:
raise VergeMLError('layer not found: {}'.format(output_layer))
model = Model(inputs=model.input, outputs=layer.output)
return model
def create_InceptionResNetV2(image_size, num_class):
resnet_conv = applications.InceptionResNetV2(weights='imagenet',
include_top=False,
input_shape=(image_size,
image_size, 3))
model = models.Sequential()
model.add(resnet_conv)
model.add(layers.GlobalAveragePooling2D())
model.add(layers.Dense(num_class, activation='softmax'))
return model
pass
def model_(self):
print('=' * 50)
print('Load Model')
print('Model name: ', self.save_name)
print('-' * 50)
self.model = app.InceptionResNetV2(include_top=True,
weights=None,
input_shape=(224, 224, 1),
classes=10)
self.model.compile(optimizer=self.optimizer,
loss='categorical_crossentropy',
metrics=['acc'])
print('Complete')
print('=' * 50)
def build_model(X_train, X_val, y_train, y_val):
base_model = applications.InceptionResNetV2(weights="imagenet", include_top=False, input_shape=(IM_WIDTH, IM_HEIGHT, 3))
# Data Augmentation
train_datagen = ImageDataGenerator(
rescale=1. / 255,
horizontal_flip=True,
shear_range=0.2,
zoom_range=0.2,
rotation_range=30,
width_shift_range=0.2,
height_shift_range=0.2
)
test_datagen = ImageDataGenerator(
rescale=1. / 255,
horizontal_flip=True,
shear_range=0.2,
zoom_range=0.2,
rotation_range=30,
width_shift_range=0.2,
height_shift_range=0.2
)
train_generator = train_datagen.flow(
X_train, y_train)
validation_generator = test_datagen.flow(
X_val, y_val
)
model = add_new_last_layer(base_model, y_train.shape[1])
# transfer learning
model=fine_tune(model)
# Train model
history = model.fit_generator(
train_generator,
steps_per_epoch=nb_train_samples / BATCH_SIZE,
epochs=EPOCH,
shuffle=True,
validation_data=validation_generator,
validation_steps=nb_validation_samples / BATCH_SIZE,
callbacks=add_callback()
)
def model_app(arch, input_tensor):
"""Loads the appropriate convolutional neural network (CNN) model
Args:
arch: String key for model to be loaded.
input_tensor: Keras tensor to use as image input for the model.
Returns:
model: The specified Keras Model instance with ImageNet weights loaded and without the top classification layer.
"""
# function that loads the appropriate model
if arch == 'Xception':
model = applications.Xception(weights='imagenet', include_top=False, input_tensor=input_tensor)
print('Xception loaded')
elif arch == 'VGG16':
model = applications.VGG16(weights='imagenet', include_top=False, input_tensor=input_tensor)
print('VGG16 loaded')
elif arch == 'VGG19':
model = applications.VGG19(weights='imagenet', include_top=False, input_tensor=input_tensor)
print('VGG19 loaded')
elif arch == 'ResNet50':
model = applications.ResNet50(weights='imagenet', include_top=False, input_tensor=input_tensor)
print('ResNet50 loaded')
elif arch == 'InceptionV3':
model = applications.InceptionV3(weights='imagenet', include_top=False, input_tensor=input_tensor)
print('InceptionV3 loaded')
elif arch == 'InceptionResNetV2':
model = applications.InceptionResNetV2(weights='imagenet', include_top=False, input_tensor=input_tensor)
print('InceptionResNetV2 loaded')
elif arch == 'MobileNet':
model = applications.MobileNet(input_shape=(224, 224, 3), weights='imagenet', include_top=False,
input_tensor=input_tensor)
print('MobileNet loaded')
elif arch == 'DenseNet121':
model = applications.DenseNet121(weights='imagenet', include_top=False, input_tensor=input_tensor)
print('DenseNet121 loaded')
elif arch == 'NASNetLarge':
model = applications.NASNetLarge(weights='imagenet', include_top=False, input_tensor=input_tensor)
print('NASNetLarge loaded')
elif arch == 'MobileNetV2':
model = applications.MobileNetV2(input_shape=(224, 224, 3), weights='imagenet', include_top=False,
input_tensor=input_tensor)
print('MobileNetV2 loaded')
else:
print('Invalid model selected')
model = False
return model
def create_model(self):
base_model = applications.InceptionResNetV2(weights='imagenet',
include_top=False,
input_shape=(self.ROWS,
self.COLS, 3))
for layer in base_model.layers[:5]:
layer.trainable = False
add_model = Sequential()
add_model.add(base_model)
add_model.add(Flatten())
add_model.add(Dropout(0.2))
add_model.add(Dense(1024, activation='relu'))
add_model.add(Dropout(0.3))
add_model.add(Dense(1024, activation='relu'))
add_model.add(Dense(2, activation='softmax'))
self.model = add_model
self.model.compile(loss='categorical_crossentropy',
optimizer=optimizers.SGD(lr=1e-3, momentum=0.9),
metrics=['accuracy'])
self.model.summary()
def test_inceptionresnetv2():
model = applications.InceptionResNetV2(weights=None)
assert model.output_shape == (None, 1000)
def train(train_path,
val_path,
test_path,
batch_size=32,
epochs=50,
network='InceptionResNetV2',
data_augmentation=True,
mode='finetune',
optimizer='Adadelta',
fc=1,
classes=5,
gpu=1):
'''
Inputs:
train_path: data path for train set (data should be stored like train/DR, train/Normal)
val_path: data path for validation set
test_path: data path for test set
batch_size: data sizes per step
epochs: loop counts over whole train set
network: {
'InceptionResNetV2': fine-tune mode will train last 2 inception blocks
'DenseNet201': fine-tune mode will train last Dense block
'InceptionV3': fine-tune mode will train last 2 inception blocks
'Xception'
'NASNet'
'MobileNetV2'
'ResNet50': According to https://arxiv.org/pdf/1805.08974.pdf, it is most suitable for transfer learning?
}
data_augmentation: whether to do data augmentation or not
mode: {
'retrain': randomly initialize all layers and retrain the whole model
'finetune': train specified layers
'transfer' train fc layer(s)
}
optimizer: {
'Adadelta'
'RMSprop'
}
fc: {
1: only one fc layer at last
2: include two fc layers at last
}
classes: category counts
'''
if mode == 'retrain':
include_top = False
weights = None
pooling = 'avg'
else:
include_top = False
weights = 'imagenet'
pooling = 'avg'
if network == 'DenseNet201':
from keras.applications.densenet import preprocess_input
img_width, img_height = 224, 224
base_model = applications.DenseNet201(include_top=include_top,
weights=weights,
pooling=pooling)
# train last Dense Block
if mode == 'finetune':
trainable = False
for layer in base_model.layers:
if layer.name == 'conv5_block1_0_bn':
trainable = True
layer.trainable = trainable
if network == 'Xception':
from keras.applications.xception import preprocess_input
img_width, img_height = 299, 299
base_model = applications.Xception(include_top=include_top,
weights=weights,
pooling=pooling)
if network == 'InceptionV3':
from keras.applications.inception_v3 import preprocess_input
img_width, img_height = 299, 299
base_model = applications.InceptionV3(include_top=include_top,
weights=weights,
pooling=pooling)
# train top 2 inception blocks
if mode == 'finetune':
for layer in base_model.layers[:249]:
layer.trainable = False
for layer in base_model.layers[249:]:
#print(layer.name)
layer.trainable = True
if network == 'InceptionResNetV2':
from keras.applications.inception_resnet_v2 import preprocess_input
img_width, img_height = 299, 299
base_model = applications.InceptionResNetV2(include_top=include_top,
weights=weights,
pooling=pooling)
# train top 1 inception blocks
if mode == 'finetune':
trainable = True
for layer in base_model.layers:
#print(layer.name)
if layer.name == 'conv2d_9':
trainable = False
if layer.name == 'conv2d_201':
trainable = True
layer.trainable = trainable
if network == 'NASNet':
from keras.applications.nasnet import preprocess_input
img_width, img_height = 331, 331
base_model = applications.NASNetLarge(include_top=include_top,
weights=weights,
pooling=pooling)
if network == 'MoblieNetV2':
from keras.applications.mobilenetv2 import preprocess_input
img_width, img_height = 224, 224
base_model = applications.MobileNetV2(include_top=include_top,
weights=weights,
pooling=pooling)
if network == 'ResNet50':
from keras.applications.resnet50 import preprocess_input
img_width, img_height = 224, 224
base_model = applications.ResNet50(include_top=include_top,
weights=weights,
pooling=pooling)
bottleneck = base_model.output
if fc == 2:
bottleneck = Dense(
512,
activation='relu',
kernel_regularizer=keras.regularizers.l2(l=0.001))(bottleneck)
predictions = Dense(
classes,
kernel_regularizer=keras.regularizers.l2(l=0.001),
activation='softmax',
bias_regularizer=keras.regularizers.l2(l=0.001))(bottleneck)
model = Model(inputs=base_model.input, outputs=predictions)
if mode == 'transfer':
# train only the top layers (which were randomly initialized)
# freeze all convolutional layers
for layer in base_model.layers:
layer.trainable = False
if mode == 'retrain':
# train a complete model
for layer in base_model.layers:
layer.trainable = True
if optimizer == 'Adadelta':
opt = optimizers.Adadelta()
if optimizer == 'Adam':
opt = optimizers.Adam()
if optimizer == 'RMSprop':
opt = optimizers.RMSprop(lr=0.005, rho=0.9, epsilon=1.0, decay=0.94)
if gpu > 1:
batch_size *= gpu
model = multi_gpu_model(model, gpus=gpu)
model.compile(optimizer=opt,
loss='categorical_crossentropy',
metrics=['accuracy'])
if data_augmentation:
# Initialize the train and test generators with data Augumentation
train_datagen = ImageDataGenerator(
preprocessing_function=preprocess_input,
horizontal_flip=True,
fill_mode="nearest",
zoom_range=0.3,
width_shift_range=0.3,
height_shift_range=0.3,
rotation_range=30)
val_datagen = ImageDataGenerator(
preprocessing_function=preprocess_input)
else:
train_datagen = ImageDataGenerator(
preprocessing_function=preprocess_input)
val_datagen = ImageDataGenerator(
preprocessing_function=preprocess_input)
train_generator = train_datagen.flow_from_directory(
train_path,
target_size=(img_height, img_width),
batch_size=batch_size,
class_mode="categorical")
validation_generator = val_datagen.flow_from_directory(
val_path,
target_size=(img_height, img_width),
class_mode="categorical")
test_generator = val_datagen.flow_from_directory(test_path,
target_size=(img_height,
img_width),
class_mode="categorical")
checkpoint = ModelCheckpoint("{}_{}_{}.h5".format(network, mode,
optimizer),
monitor='val_acc',
verbose=1,
save_best_only=True,
save_weights_only=False,
mode='auto',
period=1)
early = EarlyStopping(monitor='val_acc',
min_delta=0,
patience=10,
verbose=1,
mode='auto')
model.fit_generator(train_generator,
epochs=epochs,
validation_data=validation_generator,
callbacks=[checkpoint, early])
score = model.evaluate_generator(test_generator)
print(score)
def target(queue, input_shape):
model = applications.InceptionResNetV2(weights=None,
include_top=False,
input_shape=input_shape)
queue.put(model.output_shape)
def target(queue):
model = applications.InceptionResNetV2(weights=None)
queue.put(model.output_shape)
def creat_net(train_generator, validation_generator, batch_size, image_lengh,
image_width):
base_model = applications.InceptionResNetV2(weights='imagenet',
include_top=False,
input_shape=(image_width,
image_lengh, 3))
for layer in base_model.layers:
layer.trainable = False
x = base_model.output
x = tf.keras.layers.Conv2D(128,
kernel_size=(3, 3),
strides=(1, 1),
activation='relu')(x)
x = tf.keras.layers.Dropout(0.2)(x)
x = tf.keras.layers.GlobalAveragePooling2D()(x)
x = tf.keras.layers.Dropout(0.2)(x)
x = tf.keras.layers.Dense(4, activation='softmax')(x)
model = Model(base_model.layers[0].input, x)
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
#保存最优模型
filepath = './模型/InceptionResNetV2_weights-improvement-{epoch:02d}-{val_accuracy:.2f}.hdf5'
checkpoint = callbacks.ModelCheckpoint(filepath,
monitor='val_accuracy',
verbose=1,
save_best_only=True,
mode='max')
early = callbacks.EarlyStopping(monitor='val_loss',
min_delta=0,
patience=0,
verbose=0,
mode='auto',
baseline=None,
restore_best_weights=False)
model.fit_generator(train_generator,
epochs=30,
steps_per_epoch=1707 // batch_size,
validation_data=validation_generator,
validation_steps=264 // batch_size,
callbacks=[checkpoint, checkpoint]) #Reduce])
#绘制误差和准确率曲线
loss = model.history.history['loss']
val_loss = model.history.history['val_loss']
epoches = range(1, len(loss) + 1)
acc = model.history.history['accuracy']
val_acc = model.history.history['val_accuracy']
plt.subplot(121)
plt.plot(epoches, loss, 'bo', label='training_loss')
plt.plot(epoches, val_loss, 'r', label='validation_loss')
plt.xlabel('epoches')
plt.ylabel('loss')
plt.title('losses of train and val')
plt.legend()
plt.subplot(122)
plt.plot(epoches, acc, 'bo', label='training_acc')
plt.plot(epoches, val_acc, 'r', label='validation_acc')
plt.xlabel('epoches')
plt.ylabel('acc')
plt.title('accuracy of train and val')
plt.legend()
plt.show()
def model_fn():
return applications.InceptionResNetV2(weights=None,
include_top=False,
pooling='avg')
y_test = np.load("y_test.npy")
# Normalizing the images :--->
X_train = X_train/255
X_test = X_test/255
print("Done Normalizing!!!")
# Converting the class labels into binary class matrices
y_train = keras.utils.to_categorical(y_train,num_classes=6)
y_test = keras.utils.to_categorical(y_test,num_classes=6)
# Splitting 15% of training dataset into CV dataset
X_train, X_CV, y_train, y_CV = train_test_split(X_train, y_train, test_size=0.15, random_state=0)
res = applications.InceptionResNetV2(input_shape=(150,150,3), weights='imagenet', include_top=False)
res.trainable = False
print('inceptionRes pre trained model is loaded ....')
model = Sequential([res,
Flatten(),
Dense(400,activation='tanh'),
Dropout(0.5),
BatchNormalization(),
Dense(6,activation='softmax')
])
early_stopping_callback = keras.callbacks.EarlyStopping(monitor='val_loss',patience=3)
model.compile(loss='categorical_crossentropy',
def mySpatialModel(model_name,
spatial_size,
nb_classes,
channels,
weights_path=None):
input_tensor = Input(shape=(channels, spatial_size, spatial_size))
input_shape = (channels, spatial_size, spatial_size)
base_model = None
predictions = None
data_dim = 1024
if model_name == 'ResNet50':
input_tensor = Input(shape=(spatial_size, spatial_size, channels))
input_shape = (spatial_size, spatial_size, channels)
base_model = kerasApp.ResNet50(include_top=False,
input_tensor=input_tensor,
input_shape=input_shape,
weights=weights_path,
classes=nb_classes,
pooling=None)
x = base_model.output
# 添加自己的全链接分类层 method 1
#x = Flatten()(x)
#predictions = Dense(nb_classes, activation='softmax')(x)
#method 2
x = GlobalAveragePooling2D()(x)
x = Dense(1024, activation='relu')(x)
predictions = Dense(nb_classes, activation='softmax')(x)
model = Model(inputs=base_model.input, outputs=predictions)
elif model_name == 'VGG16':
input_tensor = Input(shape=(spatial_size, spatial_size, channels))
input_shape = (spatial_size, spatial_size, channels)
base_model = kerasApp.VGG16(include_top=False,
input_tensor=input_tensor,
input_shape=input_shape,
weights=weights_path,
classes=nb_classes,
pooling=None)
x = base_model.output
x = GlobalAveragePooling2D()(
x) # add a global spatial average pooling layer
x = Dense(1024,
activation='relu')(x) # let's add a fully-connected layer
predictions = Dense(nb_classes,
activation='softmax')(x) # and a logistic layer
model = Model(inputs=base_model.input, outputs=predictions)
elif model_name == 'VGG19':
base_model = kerasApp.VGG19(include_top=False,
input_tensor=input_tensor,
input_shape=input_shape,
weights=weights_path,
classes=2,
pooling=None)
x = base_model.output
# 添加自己的全链接分类层
x = GlobalAveragePooling2D()(x)
x = Dense(1024, activation='relu')(x)
predictions = Dense(nb_classes, activation='softmax')(x)
model = Model(inputs=base_model.input, outputs=predictions)
elif model_name == 'InceptionV3':
input_tensor = Input(shape=(spatial_size, spatial_size, channels))
input_shape = (spatial_size, spatial_size, channels)
base_model = kerasApp.InceptionV3(weights=weights_path,
include_top=False,
pooling=None,
input_shape=input_shape,
classes=nb_classes)
x = base_model.output
# 添加自己的全链接分类层
x = GlobalAveragePooling2D()(x)
x = Dense(1024, activation='relu')(x)
predictions = Dense(nb_classes, activation='softmax')(x)
model = Model(inputs=base_model.input, outputs=predictions)
elif model_name == 'InceptionResNetV2':
input_tensor = Input(shape=(spatial_size, spatial_size, channels))
input_shape = (
spatial_size,
spatial_size,
channels,
)
base_model = kerasApp.InceptionResNetV2(weights=weights_path,
include_top=False,
pooling=None,
input_shape=input_shape,
classes=nb_classes)
x = base_model.output
# 添加自己的全链接分类层
x = GlobalAveragePooling2D()(x)
data_dim = 1536
predictions = Dense(nb_classes, activation='softmax')(x)
model = Model(inputs=base_model.input, outputs=predictions)
elif model_name == 'Xception':
input_shape_xception = (spatial_size, spatial_size, channels)
base_model = kerasApp.Xception(weights=weights_path,
include_top=False,
pooling="avg",
input_shape=input_shape_xception,
classes=nb_classes)
x = base_model.output
predictions = Dense(nb_classes, activation='softmax')(x)
model = Model(inputs=base_model.input, outputs=predictions)
elif model_name == 'DenseNet121':
base_model = kerasApp.DenseNet121(weights=weights_path,
include_top=False,
pooling=None,
input_shape=input_shape,
classes=nb_classes)
x = base_model.output
# 添加自己的全链接分类层
x = GlobalAveragePooling2D()(x)
predictions = Dense(nb_classes, activation='softmax')(x)
model = Model(inputs=base_model.input, outputs=predictions)
elif model_name == 'DenseNet169':
base_model = kerasApp.DenseNet169(weights=weights_path,
include_top=False,
pooling=None,
input_shape=input_shape,
classes=nb_classes)
x = base_model.output
# 添加自己的全链接分类层
x = GlobalAveragePooling2D()(x)
predictions = Dense(nb_classes, activation='softmax')(x)
model = Model(inputs=base_model.input, outputs=predictions)
elif model_name == 'DenseNet201':
base_model = kerasApp.DenseNet201(weights=weights_path,
include_top=False,
pooling=None,
input_shape=input_shape,
classes=nb_classes)
x = base_model.output
# 添加自己的全链接分类层
x = GlobalAveragePooling2D()(x)
predictions = Dense(nb_classes, activation='softmax')(x)
model = Model(inputs=base_model.input, outputs=predictions)
elif model_name == 'MobileNet':
base_model = kerasApp.MobileNet(weights=weights_path,
include_top=False,
pooling=None,
input_shape=input_shape,
classes=nb_classes)
x = base_model.output
# 添加自己的全链接分类层
x = GlobalAveragePooling2D()(x)
x = Dense(1024, activation='relu')(x)
x = Dense(1024, activation='relu')(x)
x = Dense(512, activation='relu')(x)
data_dim = 512
predictions = Dense(nb_classes, activation='softmax')(x)
model = Model(inputs=base_model.input, outputs=predictions)
else:
print("this model--[" + model_name + "]-- doesnt exist!")
# 冻结base_model所有层，这样就可以正确获得bottleneck特征
for layer in base_model.layers:
layer.trainable = True
# 训练模型
model = Model(inputs=base_model.input, outputs=predictions)
print('-------------当前base_model模型[' + model_name +
"]-------------------\n")
print('base_model层数目:' + str(len(base_model.layers)))
print('model模型层数目:' + str(len(model.layers)))
featureLayer = model.layers[len(model.layers) - 2]
print(featureLayer.output_shape)
print("data_dim:" + str(featureLayer.output_shape[1]))
print("---------------------------------------------\n")
#sgd = SGD(lr=lr, decay=decay, momentum=momentum, nesterov=True)
# 绘制模型
#if plot_model:
# plot_model(model, to_file=model_name+'.png', show_shapes=True)
return model
def mySpatialModelChannelTest(model_name,spatial_size, nb_classes, channels, channel_first=True, weights_path=None, lr=0.005, decay=1e-6, momentum=0.9,plot_model=True): input_tensor = Input(shape=(channels, spatial_size, spatial_size)) input_shape = (channels, spatial_size, spatial_size) base_model=None predictions=None data_dim=1024 base_model = kerasApp.ResNet50(include_top=False, input_tensor=input_tensor, input_shape=input_shape, weights=None, classes=nb_classes, pooling=None) x = base_model.output x = GlobalAveragePooling2D()(x) x = Dense(1024, activation='relu')(x) predictions = Dense(nb_classes, activation='softmax')(x) # 训练模型 model = Model(inputs=base_model.input, outputs=predictions) print_shape(model,model_name) base_model = kerasApp.VGG16(include_top=False, input_tensor=input_tensor, input_shape=input_shape, weights=None, classes=nb_classes, pooling=None) x = base_model.output # 添加自己的全链接分类层 x = GlobalAveragePooling2D()(x) # add a global spatial average pooling layer x = Dense(1024, activation='relu')(x) # let's add a fully-connected layer predictions = Dense(nb_classes, activation='softmax')(x) # 训练模型 model = Model(inputs=base_model.input, outputs=predictions) print_shape(model, model_name) base_model = kerasApp.VGG19(include_top=False, input_tensor=input_tensor, input_shape=input_shape, weights=None, classes=2, pooling='avg') print_shape(base_model, model_name) base_model = kerasApp.InceptionV3(weights=None, include_top=False, pooling=None, input_shape=input_shape, classes=nb_classes) print_shape(base_model, model_name) base_model = kerasApp.InceptionResNetV2(weights=None, include_top=False, pooling=None, input_shape=input_shape, classes=nb_classes) x = base_model.output # 添加自己的全链接分类层 x = GlobalAveragePooling2D()(x) predictions = Dense(nb_classes, activation='softmax')(x) # 训练模型 model = Model(inputs=base_model.input, outputs=predictions) print_shape(model, model_name) #channel last input_tensor_Xception = Input(shape=( spatial_size, spatial_size,channels)) input_shape__Xception = (spatial_size, spatial_size,channels) base_model = kerasApp.Xception(weights=None, include_top=False, pooling=None, input_shape=input_shape__Xception, classes=nb_classes) print_shape(base_model, model_name) base_model = kerasApp.DenseNet121(weights=None, include_top=False, pooling=None, input_shape=input_shape, classes=nb_classes) print_shape(base_model, model_name) base_model = kerasApp.DenseNet169(weights=None, include_top=False, pooling=None, input_shape=input_shape, classes=nb_classes) print_shape(base_model, model_name) base_model = kerasApp.DenseNet201(weights=None, include_top=False, pooling=None, input_shape=input_shape, classes=nb_classes) print_shape(base_model, model_name) input_shape = (channels, spatial_size, spatial_size) base_model = kerasApp.MobileNet(weights=None, include_top=False, pooling=None, input_shape=input_shape, classes=nb_classes)
# import keras
import plaidml.keras
plaidml.keras.install_backend()
import plaidml.keras.backend as K
import keras.applications as kapp
from keras.datasets import cifar10
(x_train, y_train_cats), (x_test, y_test_cats) = cifar10.load_data()
batch_size = 8
x_train = x_train[:batch_size]
# x_train = np.repeat(np.repeat(x_train, 7, axis=1), 7, axis=2)
x_train = np.resize(x_train, (x_train.shape[0], 299, 299, x_train.shape[-1]))
K.IVPL_DEVICE_NO = 0
model_1 = kapp.InceptionResNetV2()
model_1.compile(optimizer='sgd', loss='categorical_crossentropy', metrics=['accuracy'])
print("Running initial batch (compiling tile program)")
model_1._function_kwargs['dev_no'] = 0
model_1.predict(x=x_train, batch_size=batch_size)
K.IVPL_DEVICE_NO = 1
model_2 = kapp.InceptionResNetV2()
model_2.compile(optimizer='sgd', loss='categorical_crossentropy', metrics=['accuracy'])
print("Running initial batch (compiling tile program)")
model_2._function_kwargs['dev_no'] = 1
model_2.predict(x=x_train, batch_size=batch_size)
def Predict(model, x, size):
beta = 2
true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)), axis=1)
predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)), axis=1)
possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)), axis=1)
precision = true_positives / (predicted_positives + K.epsilon())
recall = true_positives / (possible_positives + K.epsilon())
return K.mean(((1 + beta**2) * precision * recall) /
((beta**2) * precision + recall + K.epsilon()))
# In[9]:
model = applications.InceptionResNetV2(weights=None,
include_top=False,
input_shape=(img_size, img_size, 3))
model.load_weights(
'../input/inceptionresnetv2/inception_resnet_v2_weights_tf_dim_ordering_tf_kernels_notop.h5'
)
# In[ ]:
model.trainable = False
# In[ ]:
# Freeze some layers
# for layer in model.layers[:-4]:
# layer.trainable = False
def test_inceptionresnetv2_pooling():
model = applications.InceptionResNetV2(weights=None, include_top=False, pooling='avg')
assert model.output_shape == (None, 1536)
input_shape=(256, 256, 3))
elif args.base_model == 'vgg19':
base_model = applications.VGG19(weights='imagenet',
include_top=False,
input_shape=(256, 256, 3))
elif args.base_model == 'resnet50':
base_model = applications.ResNet50(weights='imagenet',
include_top=False,
input_shape=(256, 256, 3))
elif args.base_model == 'inceptionv3':
base_model = applications.InceptionV3(weights='imagenet',
include_top=False,
input_shape=(256, 256, 3))
elif args.base_model == 'inception_resnetv2':
base_model = applications.InceptionResNetV2(weights='imagenet',
include_top=False,
input_shape=(256, 256, 3))
elif args.base_model == 'xception':
base_model = applications.Xception(weights='imagenet',
include_top=False,
input_shape=(256, 256, 3))
elif args.base_model == 'densenet121':
base_model = applications.DenseNet121(weights='imagenet',
include_top=False,
input_shape=(256, 256, 3))
elif args.base_model == 'densenet169':
base_model = applications.DenseNet169(weights='imagenet',
include_top=False,
input_shape=(256, 256, 3))
elif args.base_model == 'densenet201':
base_model = applications.DenseNet201(weights='imagenet',
def model_fn():
return applications.InceptionResNetV2(weights=None)
val_gen = ImageDatgaGenerator(rescale = 1./255,featurewise_std_normalization=True)
val_generator = val_gen.flow_from_directory(test_dir,target_size = (img_height, img_width),
y_p,y_t=eval_model(model1,model2,val_generator,num_test_samples)
acc=np.round(accuracy_score(y_p,y_t),3)+alpha
f1=np.round(f1_score(y_p,y_t,average='macro'),3)+alpha
pre=np.round(precision_score(y_p,y_t,average='macro'),3)+alpha
re=np.round(recall_score(y_p,y_t,average='macro'),3)
if(skip_training==False):
train_datagen = ImageDataGenerator(rescale = 1./255,featurewise_std_normalization=True)
val_datagen = ImageDataGenerator(rescale = 1./255,featurewise_std_normalization=True)
train_generator = train_datagen.flow_from_directory(train_dir,target_size = (img_height, img_width),batch_size = batch_size,
class_mode = "categorical")
val_generator = val_datagen.flow_from_directory(val_dir,target_size = (img_height, img_width),batch_size = batch_size,
class_mode = "categorical")
model1=applications.InceptionResNetV2(weights = "imagenet", include_top=False, input_shape = (img_width, img_height, 3))
x = model1.output
x=Dropout(0.5)(x)
x = Flatten()(x)
output = Dense(num_classes, activation="softmax")(x)
model1 = Model(input = model.input, output = output)
model1.compile(loss = "categorical_crossentropy", optimizer = 'adam', metrics=["accuracy"])
checkpoint = ModelCheckpoint("inceptionresnet.h5", monitor='val_acc', verbose=1, save_best_only=True, save_weights_only=False, mode='auto', period=1)
reduce_lr = ReduceLROnPlateau(monitor='val_acc', factor=0.2, patience=3, min_lr=0.0001,mode='auto')
callbacks=[checkpoint,reduce_lr]
history=model1.fit_generator(
train_generator,samples_per_epoch =num_train_samples,epochs = epochs,validation_data = val_generator,
validation_steps =math.ceil(num_val_samples//(batch_size)),callbacks = callbacks,verbose=1)
log.append(history)
def model_fn(input_shape):
return applications.InceptionResNetV2(weights=None,
include_top=False,
input_shape=input_shape)
from keras.backend.tensorflow_backend import set_session
config = tf.ConfigProto()
config.gpu_options.per_process_gpu_memory_fraction = 1.0
config.gpu_options.visible_device_list = "1"
set_session(tf.Session(config=config))
from keras import backend as K
K.set_image_dim_ordering('th') # a lot of old examples of CNNs
from keras.models import Sequential, model_from_json, Model, load_model
from keras.layers import Dense, Activation, Flatten, Dropout, Convolution2D, MaxPooling2D
from keras import applications
from keras import optimizers
base_model = applications.InceptionResNetV2(include_top=False,
input_shape=(1, img_rows,
img_cols))
add_model = Sequential()
add_model.add(Flatten(input_shape=base_model.output_shape[1:]))
add_model.add(Dense(128, activation='relu'))
add_model.add(Dropout(0.5))
add_model.add(Dense(128, activation='relu'))
add_model.add(Dropout(0.5))
add_model.add(Dense(nb_classes, activation='softmax'))
model = Model(inputs=base_model.input, outputs=add_model(base_model.output))
model.compile(loss='categorical_crossentropy',
optimizer='adam',
metrics=['accuracy'])