def vgg_12(pretrained_weights=None, input_size=(256, 256, 1)):
new_input = Input(shape=input_size)
#model = VGG16(include_top=False, input_tensor=new_input, weights=None)
model = VGG16(include_top=False, input_tensor=new_input)
# Say not to train ResNet model layers as they are already trained
#for layer in model.layers:
# layer.trainable = False
# remove last 3 layers of the vgg16 model
x = model.layers[-5].output
pool1 = AveragePooling2D(pool_size=(4, 4))(x)
flat1 = Flatten()(pool1)
dense1 = Dense(1024, activation="relu")(flat1)
drop1 = Dropout(0.5)(dense1)
dense2 = Dense(1, activation="linear")(drop1)
model = Model(inputs=model.inputs, outputs=dense2)
# Compile Our Transfer Learning Model
model.compile(loss='mean_squared_error',
optimizer=Adam(lr=1e-4),
metrics=['mse', 'mae', 'mape'])
print(model.summary())
if (pretrained_weights):
print('Using pretrained weights:', pretrained_weights)
model.load_weights(pretrained_weights)
return model
def get_SV_test_model(embedded_input=True,
pretrained_model=None,
n_mels=hparams.SPK_EMBED_N_MELS,
lstm_units=hparams.SPK_EMBED_LSTM_UNITS,
proj_size=hparams.SPK_EMBED_SIZE,
num_layers=hparams.SPK_EMBED_NUM_LAYERS,
sliding_window_size=hparams.SLIDING_WINDOW_SIZE):
pair1 = Input(
shape=(proj_size, ) if embedded_input else (None, sliding_window_size,
n_mels))
pair2 = Input(
shape=(proj_size, ) if embedded_input else (None, sliding_window_size,
n_mels))
if not embedded_input:
pair1_embed, pair2_embed = TestSpeakerEmbedding(lstm_units,
proj_size,
num_layers,
name='embeddings')(
[pair1, pair2])
else:
pair1_embed, pair2_embed = pair1, pair2
sim = TestSpeakerSimilarity(name='similarity')([pair1_embed, pair2_embed])
model = Model([pair1, pair2], sim)
if not embedded_input:
model.load_weights(pretrained_model, by_name=True)
return model
def finetune_inceptionv3(base_model,
transfer_layer,
x_trainable,
dropout,
fc_layers,
num_classes,
new_weights=""):
# number of freezed layers: 0 (by a default)
freezed_layers = 0
if x_trainable != "all":
if x_trainable == 0:
for layer in base_model.layers:
layer.trainable = False
freezed_layers = freezed_layers + 1
else:
for layer in base_model.layers[:-x_trainable]:
layer.trainable = False
freezed_layers = freezed_layers + 1
all_layers = len(base_model.layers)
print("Number of all layers in a feature-extractor part of model: {}.".
format(all_layers))
print(
"Number of freezed (untrainable) layers in a feature-extractor part of model: {}."
.format(freezed_layers))
# adding custom layers to the classification part of a model
x = transfer_layer.output
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dropout(dropout)(x)
predictions = Dense(num_classes, activation='softmax')(x)
finetune_model = Model(inputs=base_model.input, outputs=predictions)
if new_weights != "":
finetune_model.load_weights(new_weights)
return finetune_model
def vgg_12(pretrained_weights='None', input_size=(256,256,1), initial_weights=True, lr=1e-4):
new_input = Input(shape=input_size)
if initial_weights:
model = VGG16(include_top=False, input_tensor=new_input)
else:
model = VGG16(include_top=False, input_tensor=new_input, weights=None)
# remove last 3 layers of the vgg16 model
x = model.layers[-5].output
pool1 = AveragePooling2D(pool_size=(4, 4))(x)
flat1 = Flatten()(pool1)
dense1 = Dense(1024, activation="relu")(flat1)
drop1 = Dropout(0.5)(dense1)
dense2 = Dense(1, activation="linear")(drop1)
model = Model(inputs=model.inputs, outputs=dense2)
# Compile Our Transfer Learning Model
model.compile(loss='mean_squared_error', optimizer=Adam(lr=lr), metrics=['mse', 'mae', 'mape'])
print(model.summary())
if pretrained_weights!='None':
print('Using pretrained weights:', pretrained_weights)
model.load_weights(pretrained_weights)
return model
def main():
from tensorflow.python.keras.models import Model
from tensorflow.python.keras.layers import Flatten, Dense, Dropout, Conv2D
from tensorflow.python.keras.applications.inception_v3 import InceptionV3, preprocess_input
data_format = 'channels_last'
input_shape = (299, 299, 3) if data_format == 'channels_last' else (3, 299,
299)
#input_shape = (2048, 2048, 3) if data_format == 'channels_last' else (3, 2048, 2048)
K.set_image_data_format(data_format)
net = InceptionV3(include_top=False,
weights=None,
input_tensor=None,
input_shape=input_shape)
x = net.output
x = Conv2D(2, 8, activation='softmax', name='output')(x)
model = Model(inputs=net.input, outputs=x)
model.load_weights(h5_path, by_name=True)
converted_output_node_names = [node.op.name for node in model.outputs]
print(('Converted output node names are: %s',
str(converted_output_node_names)))
sess = K.get_session()
constant_graph = graph_util.convert_variables_to_constants(
sess, sess.graph.as_graph_def(), converted_output_node_names)
graph_io.write_graph(constant_graph, save_path, 'model.pb', as_text=False)
sess.close()
def finetune_inceptionv3(base_model,
transfer_layer,
x_trainable,
dropout,
fc_layers,
num_classes,
new_weights=""):
if x_trainable != 0:
freeze = 0
for layer in base_model.layers[:-x_trainable]:
layer.trainable = False
freeze = freeze + 1
else:
for layer in base_model.layers:
layer.trainable = True
all_lay = 0
for layer in base_model.layers:
all_lay = all_lay + 1
print("Model with {} freezed layers.".format(freeze))
print("All layers {} .".format(all_lay))
x = transfer_layer.output
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dropout(dropout)(x)
predictions = Dense(num_classes, activation='softmax')(x)
finetune_model = Model(inputs=base_model.input, outputs=predictions)
if new_weights != "":
finetune_model.load_weights(new_weights)
return finetune_model
def mlstm_fcn(config: Union[str,
SoccerSageConfig] = SoccerSageConfig()) -> Model:
'''Load and train the MLSTM-FCN model.
Source: https://github.com/titu1994/MLSTM-FCN/blob/master/eeg_model.py
Args:
config: The configuration data.
Returns:
Model: A model in TensorFlow.
'''
if isinstance(config, str):
config = SoccerSageConfig.from_yaml(config)
n_classes = config.num_results
if config.classifier_type == 'total_goals':
n_classes = config.num_goals
ip = Input(shape=(config.time_steps, config.feature_size))
x = Permute((2, 1))(ip)
#x = Masking(mask_value=config.masking_value)(x)
x = LSTM(64)(ip)
x = Dropout(0.8)(x)
y = Conv1D(128, 8, padding='same', kernel_initializer='he_uniform')(ip)
y = BatchNormalization()(y)
y = Activation('relu')(y)
y = squeeze_excite_block(y)
y = Conv1D(256, 5, padding='same', kernel_initializer='he_uniform')(y)
y = BatchNormalization()(y)
y = Activation('relu')(y)
y = squeeze_excite_block(y)
y = Conv1D(128, 3, padding='same', kernel_initializer='he_uniform')(y)
y = BatchNormalization()(y)
y = Activation('relu')(y)
y = GlobalAveragePooling1D()(y)
x = concatenate([x, y])
out = Dense(n_classes, activation='softmax')(x)
classifier = Model(ip, out)
classifier.compile(
loss='categorical_crossentropy',
optimizer=tf.keras.optimizers.Adam(lr=config.learning_rate),
metrics=['accuracy', ranked_probability_score])
if config.pretrained_classifier:
files = SoccerSageFiles(config)
classifier.load_weights(files.model_weights)
return classifier
def SqueezeNet(include_top = True, weights="imagenet", model_input=None, non_top_pooling=None,
num_classes=1000, model_path = ""):
if(weights == "imagenet" and num_classes != 1000):
raise ValueError("You must parse in SqueezeNet model trained on the 1000 class ImageNet")
image_input = model_input
network = Conv2D(64, (3,3), strides=(2,2), padding="valid")(image_input)
network = Activation("relu")(network)
network = MaxPool2D( pool_size=(3,3) , strides=(2,2))(network)
network = squeezenet_fire_module(input=network, input_channel_small=16, input_channel_large=64)
network = squeezenet_fire_module(input=network, input_channel_small=16, input_channel_large=64)
network = MaxPool2D(pool_size=(3,3), strides=(2,2))(network)
network = squeezenet_fire_module(input=network, input_channel_small=32, input_channel_large=128)
network = squeezenet_fire_module(input=network, input_channel_small=32, input_channel_large=128)
network = MaxPool2D(pool_size=(3, 3), strides=(2, 2))(network)
network = squeezenet_fire_module(input=network, input_channel_small=48, input_channel_large=192)
network = squeezenet_fire_module(input=network, input_channel_small=48, input_channel_large=192)
network = squeezenet_fire_module(input=network, input_channel_small=64, input_channel_large=256)
network = squeezenet_fire_module(input=network, input_channel_small=64, input_channel_large=256)
if(include_top):
network = Dropout(0.5)(network)
network = Conv2D(num_classes, kernel_size=(1,1), padding="valid", name="last_conv")(network)
network = Activation("relu")(network)
network = GlobalAvgPool2D()(network)
network = Activation("softmax")(network)
else:
if(non_top_pooling == "Average"):
network = GlobalAvgPool2D()(network)
elif(non_top_pooling == "Maximum"):
network = GlobalMaxPool2D()(network)
elif(non_top_pooling == None):
pass
input_image = image_input
model = Model(inputs=input_image, outputs=network)
if(weights =="imagenet"):
weights_path = model_path
model.load_weights(weights_path)
elif(weights =="trained"):
weights_path = model_path
model.load_weights(weights_path)
return model
def ResNet50(include_top=True,
non_top_pooling=None,
model_input=None,
num_classes=1000,
weights='imagenet',
model_path=""):
layers = [3, 4, 6, 3]
channel_depths = [256, 512, 1024, 2048]
input_object = model_input
output = Conv2D(64, kernel_size=7, strides=2, padding="same")(input_object)
output = BatchNormalization()(output)
output = Activation("relu")(output)
output = MaxPool2D(pool_size=(3, 3), strides=(2, 2))(output)
output = resnet_first_block_first_module(output, channel_depths[0])
for i in range(4):
channel_depth = channel_depths[i]
num_layers = layers[i]
strided_pool_first = True
if (i == 0):
strided_pool_first = False
num_layers = num_layers - 1
output = resnet_block(output,
channel_depth=channel_depth,
num_layers=num_layers,
strided_pool_first=strided_pool_first)
if (include_top):
output = GlobalAvgPool2D(name="global_avg_pooling")(output)
output = Dense(num_classes)(output)
output = Activation("softmax")(output)
else:
if (non_top_pooling == "Average"):
output = GlobalAvgPool2D()(output)
elif (non_top_pooling == "Maximum"):
output = GlobalMaxPool2D()(output)
elif (non_top_pooling == None):
pass
model = Model(inputs=input_object, outputs=output)
if (weights == "imagenet"):
weights_path = model_path
model.load_weights(weights_path)
elif (weights == "trained"):
weights_path = model_path
model.load_weights(weights_path)
return model
def reg_mlstm_fcn(config: Union[
str, SoccerSageConfig] = SoccerSageConfig()) -> Model:
'''Load and train the regression MLSTM-FCN model.
Source: https://github.com/titu1994/MLSTM-FCN/blob/master/eeg_model.py
Args:
config: The configuration data.
Returns:
Model: A model in TensorFlow.
'''
if isinstance(config, str):
config = SoccerSageConfig.from_yaml(config)
ip = Input(shape=(config.time_steps, config.feature_size))
x = Permute((2, 1))(ip)
# x = Masking(mask_value=config.masking_value)(x)
x = LSTM(8)(x)
x = Dropout(0.8)(x)
y = Conv1D(128, 8, padding='same', kernel_initializer='he_uniform')(ip)
y = BatchNormalization()(y)
y = Activation('relu')(y)
y = squeeze_excite_block(y)
y = Conv1D(256, 5, padding='same', kernel_initializer='he_uniform')(y)
y = BatchNormalization()(y)
y = Activation('relu')(y)
y = squeeze_excite_block(y)
y = Conv1D(128, 3, padding='same', kernel_initializer='he_uniform')(y)
y = BatchNormalization()(y)
y = Activation('relu')(y)
y = GlobalAveragePooling1D()(y)
x = concatenate([x, y])
out = Dense(1, activation='linear')(x)
classifier = Model(ip, out)
classifier.compile(
loss='mse',
optimizer=tf.keras.optimizers.Adam(lr=config.learning_rate),
metrics=['mse', 'mae'])
if config.pretrained_classifier:
files = SoccerSageFiles(config)
classifier.load_weights(files.regressor_weights)
return classifier
def textgenrnn_model(num_classes,
cfg,
context_size=None,
weights_path=None,
dropout=0.0,
optimizer=RMSprop(lr=4e-3, rho=0.99)):
'''
Builds the model architecture for textgenrnn_tf and
loads the specified weights for the model.
'''
input = Input(shape=(cfg['max_length'], ), name='input')
embedded = Embedding(num_classes,
cfg['dim_embeddings'],
input_length=cfg['max_length'],
name='embedding')(input)
if dropout > 0.0:
embedded = SpatialDropout1D(dropout, name='dropout')(embedded)
rnn_layer_list = []
for i in range(cfg['rnn_layers']):
prev_layer = embedded if i is 0 else rnn_layer_list[-1]
rnn_layer_list.append(new_rnn(cfg, i + 1)(prev_layer))
seq_concat = concatenate([embedded] + rnn_layer_list, name='rnn_concat')
attention = AttentionWeightedAverage(name='attention')(seq_concat)
output = Dense(num_classes, name='output', activation='softmax')(attention)
if context_size is None:
model = Model(inputs=[input], outputs=[output])
if weights_path is not None:
model.load_weights(weights_path, by_name=True)
model.compile(loss='categorical_crossentropy', optimizer=optimizer)
else:
context_input = Input(shape=(context_size, ), name='context_input')
context_reshape = Reshape((context_size, ),
name='context_reshape')(context_input)
merged = concatenate([attention, context_reshape], name='concat')
main_output = Dense(num_classes,
name='context_output',
activation='softmax')(merged)
model = Model(inputs=[input, context_input],
outputs=[main_output, output])
if weights_path is not None:
model.load_weights(weights_path, by_name=True)
model.compile(loss='categorical_crossentropy',
optimizer=optimizer,
loss_weights=[0.8, 0.2])
return model
def get_model(weights=None, **kwargs):
for k, v in kwargs.items():
assert k in PARAMS
PARAMS[k] = v
print("Model hyper-parameters:", PARAMS)
dhw = PARAMS['dhw']
first_scale = PARAMS['first_scale']
first_layer = PARAMS['first_layer']
kernel_initializer = PARAMS['kernel_initializer']
weight_decay = PARAMS['weight_decay']
down_structure = PARAMS['down_structure']
output_size = PARAMS['output_size']
bottleneck = PARAMS['bottleneck']
shape = dhw + [1]
inputs = Input(shape=shape)
if first_scale is not None:
scaled = Lambda(first_scale)(inputs)
else:
scaled = inputs
conv = Conv3D(first_layer,
kernel_size=(3, 3, 3),
padding='same',
use_bias=True,
kernel_initializer=kernel_initializer,
kernel_regularizer=l2_penalty(weight_decay))(scaled)
downsample_times = len(down_structure)
for l, n in enumerate(down_structure):
db = _dense_block(conv, n, bottleneck[l])
conv = _transmit_block(db, l == downsample_times - 1)
if output_size == 1:
last_activation = 'sigmoid'
else:
last_activation = 'softmax'
outputs = Dense(output_size,
activation=last_activation,
kernel_regularizer=l2_penalty(weight_decay),
kernel_initializer=kernel_initializer)(conv)
model = Model(inputs, outputs)
model.summary()
if weights is not None:
model.load_weights(weights)
print('load weights:', weights)
return model
def load_mobilenetv2_224_075_detector(path):
input_tensor = Input(shape=(224, 224, 3))
output_tensor = MobileNetV2(weights=None,
include_top=False,
input_tensor=input_tensor,
alpha=0.75).output
output_tensor = ZeroPadding2D()(output_tensor)
output_tensor = Conv2D(kernel_size=(3, 3), filters=5)(output_tensor)
model = Model(inputs=input_tensor, outputs=output_tensor)
model.load_weights(path)
return model
def unet(inputSize=INPUTSIZE,
batchSize=None,
name=None,
dtype=None,
sparse=False,
tensor=None,
pretrainedWeights=None):
inp = Input(shape=inputSize,
batch_size=batchSize,
name=name,
dtype=dtype,
sparse=sparse,
tensor=tensor)
down1, toConc1 = blockDown(inp=inp,
filters=8)
down2, toConc2 = blockDown(inp=down1,
filters=16)
down3, toConc3 = blockDown(inp=down2,
filters=32)
down4, toConc4 = blockDown(inp=down3,
filters=64,
dropRate=0.5)
down5, toConc5 = blockDown(inp=down4,
filters=128,
dropRate=0.5)
up6 = blockUp(inp=down5,
toConc=toConc5,
filters=64)
up7 = blockUp(inp=up6,
toConc=toConc4,
filters=32)
up8 = blockUp(inp=up7,
toConc=toConc3,
filters=16)
up9 = blockUp(inp=up8,
toConc=toConc2,
filters=8)
finish = Conv2D(filters=10,
kernel_size=(3, 3),
padding='same',
activation='relu',
kernel_initializer='he_normal')(up9)
model = Model(inp, finish)
model.compile(optimizer=Adam(lr=1e-4), loss='categorical_crossentropy', metrics=['accuracy'])
if pretrainedWeights != None:
model.load_weights(pretrainedWeights)
return model
def create_network(cls, config, logger):
conv_initialization = config['conv_init']
dense_initialization = config['dense_init']
network_type = config['network_type']
num_actions = config['num_actions']
buffer_size = config['buffer_size']
resize_dim = config['resize_dim']
input_shape = Input(shape=(resize_dim, resize_dim, buffer_size))
base_network = getattr(tRexNetwork, 'base_network')(input_shape, conv_initialization)
end_network = getattr(tRexNetwork, network_type)(base_network, dense_initialization, num_actions)
network = Model(inputs=input_shape, outputs=end_network)
path_to_weights_to_load = config['path_to_weights_to_load'] if 'path_to_weights_to_load' in config else None
if(path_to_weights_to_load is not None):
network.load_weights(path_to_weights_to_load)
print("Loading weights from {}".format(path_to_weights_to_load))
return cls(config, network=network, logger=logger)
def ResNet50(include_top=True, non_top_pooling=None, model_input=None, num_classes=1000, weights='imagenet', model_path=""):
layers = [3,4,6,3]
channel_depths = [256, 512, 1024, 2048]
input_object = model_input
output = Conv2D(64, kernel_size=7, strides=2, padding="same")(input_object)
output = BatchNormalization()(output)
output = Activation("relu")(output)
output = MaxPool2D(pool_size=(3,3), strides=(2,2))(output)
output = resnet_first_block_first_module(output, channel_depths[0])
for i in range(4):
channel_depth = channel_depths[i]
num_layers = layers[i]
strided_pool_first = True
if(i == 0):
strided_pool_first = False
num_layers = num_layers - 1
output = resnet_block(output, channel_depth=channel_depth, num_layers=num_layers, strided_pool_first=strided_pool_first)
if(include_top):
output = GlobalAvgPool2D(name="global_avg_pooling")(output)
output = Dense(num_classes)(output)
output = Activation("softmax")(output)
else:
if (non_top_pooling == "Average"):
output = GlobalAvgPool2D()(output)
elif (non_top_pooling == "Maximum"):
output = GlobalMaxPool2D()(output)
elif (non_top_pooling == None):
pass
model = Model(inputs=input_object, outputs=output)
if(weights == "imagenet"):
weights_path = model_path
model.load_weights(weights_path)
elif (weights == "trained"):
weights_path = model_path
model.load_weights(weights_path)
return model
def img_cate(filename):
img_width, img_height = 224, 224
# build the network
base_model = applications.resnet50.ResNet50(include_top=False,
weights='imagenet',
input_shape=(224, 224, 3))
# build a classifier model to put on top of the convolutional model
top_model = Sequential()
top_model.add(Flatten(input_shape=base_model.output_shape[1:]))
top_model.add(Dense(1000, activation='relu'))
top_model.add(Dropout(0.5))
top_model.add(Dense(1000, activation='relu'))
top_model.add(Dropout(0.5))
top_model.add(Dense(4, activation='softmax'))
model = Model(inputs=base_model.input,
outputs=top_model(base_model.output))
model.load_weights('./ResNet_trainAll_May.h5')
print('Model loaded.')
# test on validation
img_path = str('./uploadFile/') + str(filename)
# print(img_path)
Pic = cv2.imread(img_path)
Pic_regu = scipy.misc.imresize(Pic, [img_width, img_height, 3]) / 255
FC_predict = model.predict(np.array([Pic_regu]))
print('\n')
print('Prediction:')
print(FC_predict)
# RC_predict = zeros(4)
# RC_predict[0] = '%.2f%%' % (FC_predict[0][0] * 100)
# RC_predict[1] = '%.2f%%' % (FC_predict[0][1] * 100)
# RC_predict[2] = '%.2f%%' % (FC_predict[0][2] * 100)
# RC_predict[3] = '%.2f%%' % (FC_predict[0][3] * 100)
# print(RC_predict)
Category = 'No Data'
if np.argmax(FC_predict) == 0:
Category = 'Bare Pavement'
if np.argmax(FC_predict) == 1:
Category = 'Partly Coverage'
if np.argmax(FC_predict) == 2:
Category = 'Fully Coverage.'
if np.argmax(FC_predict) == 3:
Category = 'Not Recognizable'
return Category, FC_predict
def get_model(self,
class_names,
model_name="DenseNet121",
use_base_weights=True,
weights_path=None,
input_shape=None,
pop_last_layer=False):
if use_base_weights is True:
base_weights = "imagenet"
else:
base_weights = None
base_model_class = getattr(
importlib.import_module(
f"tensorflow.python.keras.applications.{self.models_[model_name]['module_name']}"
), model_name)
if input_shape is None:
input_shape = self.models_[model_name]["input_shape"]
img_input = Input(shape=input_shape)
base_model = base_model_class(include_top=False,
input_tensor=img_input,
input_shape=input_shape,
weights=base_weights,
pooling="avg")
x = base_model.output
predictions = Dense(len(class_names),
activation="sigmoid",
name="predictions")(x)
loaded_model = Model(inputs=img_input, outputs=predictions)
if weights_path == "":
weights_path = None
if weights_path is not None:
print(f"load model weights_path: {weights_path}")
loaded_model.load_weights(weights_path)
if pop_last_layer:
for _ in range(1):
# loaded_model.layers.pop()
loaded_model.outputs = [loaded_model.layers[-3].output]
# loaded_model.layers[-1].outbound_nodes = []
return loaded_model
def finetune(train_path, test_path):
train_datagen = ImageDataGenerator()
test_datagen = ImageDataGenerator()
print("获取测试数据... ...")
test_generator = test_datagen.flow_from_directory(test_path,
target_size=(224, 224),
batch_size=4)
print("获取训练数据... ...")
train_generator = train_datagen.flow_from_directory(train_path,
target_size=(224, 224),
batch_size=4)
print("开始训练... ...")
logging = TensorBoard(log_dir='/home/app/program/micro_emotion/log')
early_stopping = EarlyStopping(monitor='val_loss',
min_delta=0,
patience=5,
verbose=1)
model_check = ModelCheckpoint(filepath=model_path,
monitor='val_loss',
save_best_only=True)
lr_decay = ReduceLROnPlateau(monitor='val_loss',
factor=0.1,
patience=3,
min_delta=0.001)
model = RN.resnet10(include_top=False,
pooling='avg',
input_shape=(224, 224, 3),
classes=5)
x = model.output
x = Dense(5, activation='softmax', name='fc8_micro')(x)
model = Model(inputs=model.input, outputs=x)
model.load_weights(pre_model, by_name=True)
#model = frozen(model)
model.compile(loss="categorical_crossentropy",
optimizer=SGD(lr=0.01, momentum=0.9, decay=0.1 / 10),
metrics=['accuracy'])
history = model.fit_generator(
train_generator,
steps_per_epoch=62,
epochs=30,
validation_data=test_generator,
validation_steps=30,
callbacks=[logging, early_stopping, model_check, lr_decay])
def _restore_inference_model(self, input_image_pairs, ckpt_dir):
"""
Restores an pre-trained inference model from a given checkpoint.
"""
c = input_image_pairs.get_shape()[-1]
w = input_image_pairs.get_shape()[-2]
h = input_image_pairs.get_shape()[-3]
seq_len = input_image_pairs.get_shape()[-4]
weight_path = os.path.join(ckpt_dir, 'model_weights.h5')
model_input = Input(shape=(seq_len, h, w, c))
inferred_actions = action_inference_model(model_input)
model = Model(inputs=model_input, outputs=inferred_actions)
model.load_weights(weight_path)
return model
def network(self, weights=None):
num_inp = Input(shape=[self.state_length])
num_feats = Dense(70, activation='relu')(num_inp)
num_feats = Dense(40, activation='relu')(num_feats)
board_inp = Input(shape=[10, 10, 10])
board_feats = Dropout(rate=0.05)(
BatchNormalization()(Conv2D(30,
kernel_size=(3, 3),
strides=(1, 1),
activation='relu')(board_inp)))
board_feats = Dropout(rate=0.05)(
BatchNormalization()(Conv2D(30,
kernel_size=(3, 3),
strides=(1, 1),
activation='relu')(board_feats)))
board_feats = (Conv2D(30,
kernel_size=(3, 3),
strides=(1, 1),
activation='relu')(board_feats))
board_feats = Flatten()(board_feats)
board_feats = Dropout(rate=0.05)(Dense(150,
activation='relu')(board_feats))
#board_feats = Dense(50, activation='relu')(board_feats)
feats = Dropout(rate=0.05)(Concatenate()([num_feats, board_feats]))
feats = Dropout(rate=0.02)(Dense(150, activation='relu')(feats))
feats = Dense(60, activation='relu')(feats)
output = Dense(4)(feats)
model = Model([num_inp, board_inp], output)
model.summary()
opt = Adam(lr=self.learning_rate, )
model.compile(loss='mse', optimizer=opt)
if weights:
model.load_weights(weights)
return model
def vgg_12_bn(pretrained_weights=None, input_size=(256, 256, 1)):
new_input = Input(shape=input_size)
model = VGG16(include_top=False, input_tensor=new_input, weights=None)
# Say not to train ResNet model layers as they are already trained
#for layer in model.layers:
# layer.trainable = False
# extract first convolutional layer of vgg & apply BN to first two conv layers
conv1 = model.layers[1].output
bn1 = BatchNormalization()(conv1)
conv2 = model.layers[2](bn1)
bn2 = BatchNormalization()(conv2)
x = model.layers[3](bn2)
# append other layers of vgg network
for layer in model.layers[4:15]:
x = layer(x)
# append final dense layers to model
pool1 = AveragePooling2D(pool_size=(4, 4))(x)
flat1 = Flatten()(pool1)
dense1 = Dense(1024, activation="relu")(flat1)
drop1 = Dropout(0.5)(dense1)
dense2 = Dense(1, activation="linear")(drop1)
model = Model(inputs=model.inputs, outputs=dense2)
# Compile Our Transfer Learning Model
model.compile(loss='mean_squared_error',
optimizer=Adam(lr=1e-4),
metrics=['mse', 'mae', 'mape'])
print(model.summary())
if (pretrained_weights):
print('Using pretrained weights:', pretrained_weights)
model.load_weights(pretrained_weights)
return model
def temporal_module_with_attention(data_dim,
timesteps_TIM=10,
classes=5,
weights_path=None):
inputs = Input(shape=(
timesteps_TIM,
data_dim,
))
attention_mul = attention_3d_block(inputs)
attention_mul = LSTM(3000,
return_sequences=False,
input_shape=(timesteps_TIM, data_dim))(attention_mul)
output = Dense(128, activation='relu')(attention_mul)
output = Dense(classes, activation='sigmoid')(output)
model = Model(inputs=[inputs], outputs=output)
if weights_path:
model.load_weights(weights_path)
return model
def confusionmatrix(img_path, dim):
labels = os.listdir(img_path)
labels.sort()
files = []
for label in labels:
imgpath = os.path.join(img_path, label)
imgnames = os.listdir(imgpath)
for imgname in imgnames:
s = '{0}/{1} {0}'.format(label, imgname)
files.append(s)
np.random.shuffle(files)
confusion_matrix = np.zeros((dim, dim), np.int)
confusion_matrix_float = np.zeros((dim, dim), np.float)
#构建模型
model = RN.resnet10(include_top=False,
pooling='avg',
input_tensor=None,
input_shape=(224, 224, 3),
classes=5)
x = model.output
x = Dense(5, activation='softmax', name='fc8_micro')(x)
model = Model(inputs=model.input, outputs=x)
model.load_weights(model_path, by_name=True)
#获取混淆矩阵
for file in files:
path = file.split()[0]
sign = eval(file.split()[1])
img = cv2.imread(os.path.join(img_path, path))
face = cv2.resize(img, (224, 224))
face = img_to_array(face)
face = face.reshape((-1, 224, 224, 3))
predict_value = int(model.predict(face).argmax())
confusion_matrix[sign, predict_value] += 1
print(confusion_matrix)
c_sum = confusion_matrix.sum(axis=1)
confusion_matrix_float = confusion_matrix / c_sum
print(confusion_matrix_float)
def create_model(input_shape, n_classes, weights_path, freeze_convnet):
convnet = ResNet50(
include_top=False, weights='imagenet', input_shape=input_shape)
x = convnet.output
x = Flatten()(x)
x = Dense(n_classes, activation='softmax', name='out')(x)
model = Model(inputs=convnet.input, outputs=x)
# load weights
if type(weights_path) is str:
model.load_weights(weights_path, by_name=True)
elif type(weights_path) is list:
for p in weights_path:
model.load_weights(p, by_name=True)
if freeze_convnet:
print('Freeze convolutional layers')
for layer in convnet.layers:
layer.trainable = False
return model
def _construct_model(self, is_training, feature_extractor, detector):
yolov2 = YOLOv2MetaArch(feature_extractor=feature_extractor,
detector=detector,
anchors=self.anchors,
num_classes=self.num_classes)
inputs = Input(shape=(None, None, 3), name='input_images')
outputs = yolov2.predict(inputs)
if is_training:
model = Model(inputs=inputs, outputs=outputs)
else:
deploy_params = self.config['deploy_params']
outputs = yolov2.post_process(outputs,
deploy_params['iou_threshold'],
deploy_params['score_threshold'],
deploy_params['maximum_boxes'])
model = Model(inputs=inputs, outputs=outputs)
model.load_weights(self.config['model']['weight_file'])
print("Weight file has been loaded in to model")
return model
def finetune_vgg16_model(base_model,
transfer_layer,
x_trainable,
dropout,
fc_layers,
num_classes,
new_weights=""):
# number of freezed layers: 0 (by a default)
freezed_layers = 0
if x_trainable != "all":
if x_trainable == 0:
for layer in base_model.layers:
layer.trainable = False
freezed_layers = freezed_layers + 1
else:
for layer in base_model.layers[:-x_trainable]:
layer.trainable = False
freezed_layers = freezed_layers + 1
all_layers = len(base_model.layers)
print("Number of all layers in a feature-extractor part of model: {}.".
format(all_layers))
print(
"Number of freezed (untrainable) layers in a feature-extractor part of model: {}."
.format(freeze))
# adding custom layers to the classification part of a model
x = transfer_layer.output
#x = Dense(num_classes, activation='softmax')
x = Flatten()(x)
for fc in fc_layers:
# New FC layer, random init
x = Dense(fc, activation='relu')(x)
x = Dropout(dropout)(x)
# New softmax layer
predictions = Dense(num_classes, activation='softmax')(x)
finetune_model = Model(inputs=base_model.input, outputs=predictions)
if new_weights != "":
finetune_model.load_weights(new_weights)
return finetune_model
def finetune_vgg16_model(base_model,
transfer_layer,
x_trainable,
dropout,
fc_layers,
num_classes,
new_weights=""):
for layer in base_model.layers[:-x_trainable]:
layer.trainable = False
x = transfer_layer.output
#x = Dense(num_classes, activation='softmax')
x = Flatten()(x)
for fc in fc_layers:
# New FC layer, random init
x = Dense(fc, activation='relu')(x)
x = Dropout(dropout)(x)
# New softmax layer
predictions = Dense(num_classes, activation='softmax')(x)
finetune_model = Model(inputs=base_model.input, outputs=predictions)
if new_weights != "":
finetune_model.load_weights(new_weights)
return finetune_model
def _get_model(model_weight_file):
img_tensor = Input(shape=(64, 64, 3))
content_code = get_content_code(img_tensor)
style_code = get_style_code(img_tensor)
adain_parameters = Lambda(get_adain_parameters)(style_code)
x = Lambda(adain, arguments={'epsilon':
1e-5})((content_code, adain_parameters))
x = get_decoding_residual_blocks_signal(x)
x = get_upsampled_signal(x)
# reconstruction = Conv2DTranspose(filters=3, kernel_size=(3, 3), strides=1, padding='same', activation='sigmoid', name='reconstruction')(x) # v1, v2
reconstruction = Conv2DTranspose(filters=3,
kernel_size=(3, 3),
strides=1,
padding='same',
activation='relu',
name='reconstruction')(x) # v3, v4
prediction_code = get_encoded_predictions(style_code)
predictions = Dense(units=num_classes,
activation='softmax',
name='predictions')(style_code)
model = Model(inputs=img_tensor, outputs=[reconstruction, predictions])
print(model.summary())
loss = {
'reconstruction': mean_squared_error,
'predictions': categorical_crossentropy
}
optimizer = SGD(lr=0.005, momentum=0.9, decay=1e-6, nesterov=True)
metrics = {'predictions': [categorical_accuracy]}
# class_weight = { 'reconstruction': 1., 'predictions': 1. } # v1, v2
class_weight = {'reconstruction': 0.05, 'predictions': 1.} # v3, v4
model.compile(optimizer=optimizer, loss=loss, metrics=metrics)
model.load_weights(model_weight_file)
return model
def init_resnet(stack_fn, preact, use_bias, model_name, input_shape,
block_name_to_hyperparameters_dict, preprocess_input_mode):
# Downloads the weights
file_name = model_name + "_weights_tf_dim_ordering_tf_kernels_notop.h5"
file_hash = WEIGHTS_HASHES[model_name][1]
weights_path = data_utils.get_file(file_name,
BASE_WEIGHTS_PATH + file_name,
cache_subdir="models",
file_hash=file_hash)
# Define and initialize the first block
first_block = ResNet(stack_fn=lambda x: x,
preact=preact,
use_bias=use_bias,
include_top=False,
weights=None,
input_shape=input_shape)
first_block.load_weights(weights_path, by_name=True)
submodel_list = [first_block]
# Define and initialize each block
for block_name, (filters, blocks,
stride1) in block_name_to_hyperparameters_dict.items():
input_tensor = Input(shape=K.int_shape(submodel_list[-1].output)[1:])
output_tensor = stack_fn(input_tensor,
filters=filters,
blocks=blocks,
stride1=stride1,
name=block_name)
submodel = Model(inputs=input_tensor,
outputs=output_tensor,
name="{}_block".format(block_name))
submodel.load_weights(weights_path, by_name=True)
submodel_list.append(submodel)
return submodel_list, lambda x: preprocess_input(x,
mode=preprocess_input_mode)
def resnet50(pretrained_weights=None, input_size=(1024, 150, 3)):
new_input = Input(shape=input_size)
model = ResNet50(include_top=False, input_tensor=new_input)
'''
Say not to train ResNet model layers as they are already trained otherwise skip
this step to train from scratch
'''
#for layer in model.layers:
# layer.trainable = False
# add custom model layers as per requirments
x = model.output
x = AveragePooling2D(pool_size=(4, 4))(x)
x = Flatten()(x)
x = Dense(1024, activation="relu")(x)
x = Dropout(0.5)(x)
x = Dense(1024, activation="relu")(x)
# final output layer for prediction regression variable
predictions = Dense(1, activation='linear')(x)
model = Model(inputs=model.inputs, outputs=predictions)
# Compile Our Transfer Learning Model
model.compile(loss='mean_squared_error',
optimizer=Adam(lr=1e-4),
metrics=['mse', 'mae', 'mape'])
print(model.summary())
if (pretrained_weights):
print('Using pretrained weights:', pretrained_weights)
model.load_weights(pretrained_weights)
return model
def create_network_given_future(
state_input,
predictor_type="cnn",
use_batch_norm=False,
weight_path='weights/root_model/optimal_stocks.h5',
load_weights=False):
root_network = RootNetwork(inputs=state_input,
predictor_type=predictor_type,
use_batch_norm=use_batch_norm).net
root_model = Model(state_input, root_network)
if load_weights:
try:
root_model.load_weights(weight_path)
for layer in root_model.layers:
layer.trainable = False
print('Model load successfully')
except:
print('Build model from scratch')
else:
print('Build model from scratch')
net = Dense(300, activation="relu")(root_network)
net = Flatten()(net)
net = Dense(300, activation="relu")(net)
nb_assets = state_input.shape[1]
output = Dense(nb_assets, activation='softmax')(net)
imitation_model = Model(state_input, output)
imitation_model.compile(loss='categorical_crossentropy',
optimizer=Adam(lr=1e-3),
metrics=['accuracy'])
return root_model, imitation_model
def Xception(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Xception architecture.
Optionally loads weights pre-trained
on ImageNet. This model is available for TensorFlow only,
and can only be used with inputs following the TensorFlow
data format `(width, height, channels)`.
You should set `image_data_format='channels_last'` in your Keras config
located at ~/.keras/keras.json.
Note that the default input image size for this model is 299x299.
Arguments:
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(299, 299, 3)`.
It should have exactly 3 inputs channels,
and width and height should be no smaller than 71.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
RuntimeError: If attempting to run this model with a
backend that does not support separable convolutions.
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
if K.image_data_format() != 'channels_last':
logging.warning(
'The Xception model is only available for the '
'input data format "channels_last" '
'(width, height, channels). '
'However your settings specify the default '
'data format "channels_first" (channels, width, height). '
'You should set `image_data_format="channels_last"` in your Keras '
'config located at ~/.keras/keras.json. '
'The model being returned right now will expect inputs '
'to follow the "channels_last" data format.')
K.set_image_data_format('channels_last')
old_data_format = 'channels_first'
else:
old_data_format = None
# Determine proper input shape
input_shape = _obtain_input_shape(
input_shape,
default_size=299,
min_size=71,
data_format=K.image_data_format(),
require_flatten=False,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = Conv2D(
32, (3, 3), strides=(2, 2), use_bias=False, name='block1_conv1')(
img_input)
x = BatchNormalization(name='block1_conv1_bn')(x)
x = Activation('relu', name='block1_conv1_act')(x)
x = Conv2D(64, (3, 3), use_bias=False, name='block1_conv2')(x)
x = BatchNormalization(name='block1_conv2_bn')(x)
x = Activation('relu', name='block1_conv2_act')(x)
residual = Conv2D(
128, (1, 1), strides=(2, 2), padding='same', use_bias=False)(
x)
residual = BatchNormalization()(residual)
x = SeparableConv2D(
128, (3, 3), padding='same', use_bias=False, name='block2_sepconv1')(
x)
x = BatchNormalization(name='block2_sepconv1_bn')(x)
x = Activation('relu', name='block2_sepconv2_act')(x)
x = SeparableConv2D(
128, (3, 3), padding='same', use_bias=False, name='block2_sepconv2')(
x)
x = BatchNormalization(name='block2_sepconv2_bn')(x)
x = MaxPooling2D(
(3, 3), strides=(2, 2), padding='same', name='block2_pool')(
x)
x = layers.add([x, residual])
residual = Conv2D(
256, (1, 1), strides=(2, 2), padding='same', use_bias=False)(
x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block3_sepconv1_act')(x)
x = SeparableConv2D(
256, (3, 3), padding='same', use_bias=False, name='block3_sepconv1')(
x)
x = BatchNormalization(name='block3_sepconv1_bn')(x)
x = Activation('relu', name='block3_sepconv2_act')(x)
x = SeparableConv2D(
256, (3, 3), padding='same', use_bias=False, name='block3_sepconv2')(
x)
x = BatchNormalization(name='block3_sepconv2_bn')(x)
x = MaxPooling2D(
(3, 3), strides=(2, 2), padding='same', name='block3_pool')(
x)
x = layers.add([x, residual])
residual = Conv2D(
728, (1, 1), strides=(2, 2), padding='same', use_bias=False)(
x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block4_sepconv1_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False, name='block4_sepconv1')(
x)
x = BatchNormalization(name='block4_sepconv1_bn')(x)
x = Activation('relu', name='block4_sepconv2_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False, name='block4_sepconv2')(
x)
x = BatchNormalization(name='block4_sepconv2_bn')(x)
x = MaxPooling2D(
(3, 3), strides=(2, 2), padding='same', name='block4_pool')(
x)
x = layers.add([x, residual])
for i in range(8):
residual = x
prefix = 'block' + str(i + 5)
x = Activation('relu', name=prefix + '_sepconv1_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv1')(
x)
x = BatchNormalization(name=prefix + '_sepconv1_bn')(x)
x = Activation('relu', name=prefix + '_sepconv2_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv2')(
x)
x = BatchNormalization(name=prefix + '_sepconv2_bn')(x)
x = Activation('relu', name=prefix + '_sepconv3_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False, name=prefix + '_sepconv3')(
x)
x = BatchNormalization(name=prefix + '_sepconv3_bn')(x)
x = layers.add([x, residual])
residual = Conv2D(
1024, (1, 1), strides=(2, 2), padding='same', use_bias=False)(
x)
residual = BatchNormalization()(residual)
x = Activation('relu', name='block13_sepconv1_act')(x)
x = SeparableConv2D(
728, (3, 3), padding='same', use_bias=False, name='block13_sepconv1')(
x)
x = BatchNormalization(name='block13_sepconv1_bn')(x)
x = Activation('relu', name='block13_sepconv2_act')(x)
x = SeparableConv2D(
1024, (3, 3), padding='same', use_bias=False, name='block13_sepconv2')(
x)
x = BatchNormalization(name='block13_sepconv2_bn')(x)
x = MaxPooling2D(
(3, 3), strides=(2, 2), padding='same', name='block13_pool')(
x)
x = layers.add([x, residual])
x = SeparableConv2D(
1536, (3, 3), padding='same', use_bias=False, name='block14_sepconv1')(
x)
x = BatchNormalization(name='block14_sepconv1_bn')(x)
x = Activation('relu', name='block14_sepconv1_act')(x)
x = SeparableConv2D(
2048, (3, 3), padding='same', use_bias=False, name='block14_sepconv2')(
x)
x = BatchNormalization(name='block14_sepconv2_bn')(x)
x = Activation('relu', name='block14_sepconv2_act')(x)
if include_top:
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='xception')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'xception_weights_tf_dim_ordering_tf_kernels.h5',
TF_WEIGHTS_PATH,
cache_subdir='models',
file_hash='0a58e3b7378bc2990ea3b43d5981f1f6')
else:
weights_path = get_file(
'xception_weights_tf_dim_ordering_tf_kernels_notop.h5',
TF_WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
file_hash='b0042744bf5b25fce3cb969f33bebb97')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
if old_data_format:
K.set_image_data_format(old_data_format)
return model
def MobileNet(input_shape=None,
alpha=1.0,
depth_multiplier=1,
dropout=1e-3,
include_top=True,
weights='imagenet',
input_tensor=None,
pooling=None,
classes=1000):
"""Instantiates the MobileNet architecture.
To load a MobileNet model via `load_model`, import the custom
objects `relu6` and pass them to the `custom_objects` parameter.
E.g.
model = load_model('mobilenet.h5', custom_objects={
'relu6': mobilenet.relu6})
Arguments:
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or (3, 224, 224) (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 32.
E.g. `(200, 200, 3)` would be one valid value.
alpha: controls the width of the network.
- If `alpha` < 1.0, proportionally decreases the number
of filters in each layer.
- If `alpha` > 1.0, proportionally increases the number
of filters in each layer.
- If `alpha` = 1, default number of filters from the paper
are used at each layer.
depth_multiplier: depth multiplier for depthwise convolution
(also called the resolution multiplier)
dropout: dropout rate
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of
`layers.Input()`)
to use as image input for the model.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model
will be the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a
2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
RuntimeError: If attempting to run this model with a
backend that does not support separable convolutions.
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as ImageNet with `include_top` '
'as true, `classes` should be 1000')
# Determine proper input shape and default size.
if input_shape is None:
default_size = 224
else:
if K.image_data_format() == 'channels_first':
rows = input_shape[1]
cols = input_shape[2]
else:
rows = input_shape[0]
cols = input_shape[1]
if rows == cols and rows in [128, 160, 192, 224]:
default_size = rows
else:
default_size = 224
input_shape = _obtain_input_shape(
input_shape,
default_size=default_size,
min_size=32,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
if K.image_data_format() == 'channels_last':
row_axis, col_axis = (0, 1)
else:
row_axis, col_axis = (1, 2)
rows = input_shape[row_axis]
cols = input_shape[col_axis]
if weights == 'imagenet':
if depth_multiplier != 1:
raise ValueError('If imagenet weights are being loaded, '
'depth multiplier must be 1')
if alpha not in [0.25, 0.50, 0.75, 1.0]:
raise ValueError('If imagenet weights are being loaded, '
'alpha can be one of'
'`0.25`, `0.50`, `0.75` or `1.0` only.')
if rows != cols or rows not in [128, 160, 192, 224]:
if rows is None:
rows = 224
logging.warning('MobileNet shape is undefined.'
' Weights for input shape (224, 224) will be loaded.')
else:
raise ValueError('If imagenet weights are being loaded, '
'input must have a static square shape (one of '
'(128, 128), (160, 160), (192, 192), or (224, 224)).'
' Input shape provided = %s' % (input_shape,))
if K.image_data_format() != 'channels_last':
logging.warning('The MobileNet family of models is only available '
'for the input data format "channels_last" '
'(width, height, channels). '
'However your settings specify the default '
'data format "channels_first" (channels, width, height).'
' You should set `image_data_format="channels_last"` '
'in your Keras config located at ~/.keras/keras.json. '
'The model being returned right now will expect inputs '
'to follow the "channels_last" data format.')
K.set_image_data_format('channels_last')
old_data_format = 'channels_first'
else:
old_data_format = None
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
x = _conv_block(img_input, 32, alpha, strides=(2, 2))
x = _depthwise_conv_block(x, 64, alpha, depth_multiplier, block_id=1)
x = _depthwise_conv_block(
x, 128, alpha, depth_multiplier, strides=(2, 2), block_id=2)
x = _depthwise_conv_block(x, 128, alpha, depth_multiplier, block_id=3)
x = _depthwise_conv_block(
x, 256, alpha, depth_multiplier, strides=(2, 2), block_id=4)
x = _depthwise_conv_block(x, 256, alpha, depth_multiplier, block_id=5)
x = _depthwise_conv_block(
x, 512, alpha, depth_multiplier, strides=(2, 2), block_id=6)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=7)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=8)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=9)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=10)
x = _depthwise_conv_block(x, 512, alpha, depth_multiplier, block_id=11)
x = _depthwise_conv_block(
x, 1024, alpha, depth_multiplier, strides=(2, 2), block_id=12)
x = _depthwise_conv_block(x, 1024, alpha, depth_multiplier, block_id=13)
if include_top:
if K.image_data_format() == 'channels_first':
shape = (int(1024 * alpha), 1, 1)
else:
shape = (1, 1, int(1024 * alpha))
x = GlobalAveragePooling2D()(x)
x = Reshape(shape, name='reshape_1')(x)
x = Dropout(dropout, name='dropout')(x)
x = Conv2D(classes, (1, 1), padding='same', name='conv_preds')(x)
x = Activation('softmax', name='act_softmax')(x)
x = Reshape((classes,), name='reshape_2')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='mobilenet_%0.2f_%s' % (alpha, rows))
# load weights
if weights == 'imagenet':
if K.image_data_format() == 'channels_first':
raise ValueError('Weights for "channels_first" format '
'are not available.')
if alpha == 1.0:
alpha_text = '1_0'
elif alpha == 0.75:
alpha_text = '7_5'
elif alpha == 0.50:
alpha_text = '5_0'
else:
alpha_text = '2_5'
if include_top:
model_name = 'mobilenet_%s_%d_tf.h5' % (alpha_text, rows)
weigh_path = BASE_WEIGHT_PATH + model_name
weights_path = get_file(model_name, weigh_path, cache_subdir='models')
else:
model_name = 'mobilenet_%s_%d_tf_no_top.h5' % (alpha_text, rows)
weigh_path = BASE_WEIGHT_PATH + model_name
weights_path = get_file(model_name, weigh_path, cache_subdir='models')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
if old_data_format:
K.set_image_data_format(old_data_format)
return model
def InceptionV3(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Inception v3 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format='channels_last'` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
Note that the default input image size for this model is 299x299.
Arguments:
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(299, 299, 3)` (with `channels_last` data format)
or `(3, 299, 299)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 139.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(
input_shape,
default_size=299,
min_size=139,
data_format=K.image_data_format(),
require_flatten=False,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == 'channels_first':
channel_axis = 1
else:
channel_axis = 3
x = conv2d_bn(img_input, 32, 3, 3, strides=(2, 2), padding='valid')
x = conv2d_bn(x, 32, 3, 3, padding='valid')
x = conv2d_bn(x, 64, 3, 3)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv2d_bn(x, 80, 1, 1, padding='valid')
x = conv2d_bn(x, 192, 3, 3, padding='valid')
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
# mixed 0, 1, 2: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 32, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed0')
# mixed 1: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed1')
# mixed 2: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed2')
# mixed 3: 17 x 17 x 768
branch3x3 = conv2d_bn(x, 384, 3, 3, strides=(2, 2), padding='valid')
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(
branch3x3dbl, 96, 3, 3, strides=(2, 2), padding='valid')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = layers.concatenate(
[branch3x3, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed3')
# mixed 4: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 128, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 128, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 128, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed4')
# mixed 5, 6: 17 x 17 x 768
for i in range(2):
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 160, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 160, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 160, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(5 + i))
# mixed 7: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 192, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 192, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed7')
# mixed 8: 8 x 8 x 1280
branch3x3 = conv2d_bn(x, 192, 1, 1)
branch3x3 = conv2d_bn(branch3x3, 320, 3, 3, strides=(2, 2), padding='valid')
branch7x7x3 = conv2d_bn(x, 192, 1, 1)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 1, 7)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 7, 1)
branch7x7x3 = conv2d_bn(
branch7x7x3, 192, 3, 3, strides=(2, 2), padding='valid')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = layers.concatenate(
[branch3x3, branch7x7x3, branch_pool], axis=channel_axis, name='mixed8')
# mixed 9: 8 x 8 x 2048
for i in range(2):
branch1x1 = conv2d_bn(x, 320, 1, 1)
branch3x3 = conv2d_bn(x, 384, 1, 1)
branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3)
branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1)
branch3x3 = layers.concatenate(
[branch3x3_1, branch3x3_2], axis=channel_axis, name='mixed9_' + str(i))
branch3x3dbl = conv2d_bn(x, 448, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3)
branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3)
branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1)
branch3x3dbl = layers.concatenate(
[branch3x3dbl_1, branch3x3dbl_2], axis=channel_axis)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch3x3, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(9 + i))
if include_top:
# Classification block
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='inception_v3')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'inception_v3_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
file_hash='9a0d58056eeedaa3f26cb7ebd46da564')
else:
weights_path = get_file(
'inception_v3_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
file_hash='bcbd6486424b2319ff4ef7d526e38f63')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def InceptionV3(include_top=True,
weights='imagenet',
input_tensor=None,
model_input=None,
pooling=None,
classes=1000, model_path=""):
"""Instantiates the Inception v3 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format='channels_last'` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
Note that the default input image size for this model is 299x299.
# Arguments
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization)
or 'imagenet' (pre-training on ImageNet).
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(299, 299, 3)` (with `channels_last` data format)
or `(3, 299, 299)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 139.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
# Returns
A Keras model instance.
# Raises
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
img_input = model_input
channel_axis = 3
x = conv2d_bn(img_input, 32, 3, 3, strides=(2, 2), padding='valid')
x = conv2d_bn(x, 32, 3, 3, padding='valid')
x = conv2d_bn(x, 64, 3, 3)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv2d_bn(x, 80, 1, 1, padding='valid')
x = conv2d_bn(x, 192, 3, 3, padding='valid')
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
# mixed 0, 1, 2: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 32, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed0')
# mixed 1: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed1')
# mixed 2: 35 x 35 x 256
branch1x1 = conv2d_bn(x, 64, 1, 1)
branch5x5 = conv2d_bn(x, 48, 1, 1)
branch5x5 = conv2d_bn(branch5x5, 64, 5, 5)
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1, 1)
x = layers.concatenate(
[branch1x1, branch5x5, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed2')
# mixed 3: 17 x 17 x 768
branch3x3 = conv2d_bn(x, 384, 3, 3, strides=(2, 2), padding='valid')
branch3x3dbl = conv2d_bn(x, 64, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 96, 3, 3)
branch3x3dbl = conv2d_bn(
branch3x3dbl, 96, 3, 3, strides=(2, 2), padding='valid')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = layers.concatenate(
[branch3x3, branch3x3dbl, branch_pool], axis=channel_axis, name='mixed3')
# mixed 4: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 128, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 128, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 128, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 128, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed4')
# mixed 5, 6: 17 x 17 x 768
for i in range(2):
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 160, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 160, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 160, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 160, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D(
(3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(5 + i))
# mixed 7: 17 x 17 x 768
branch1x1 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(x, 192, 1, 1)
branch7x7 = conv2d_bn(branch7x7, 192, 1, 7)
branch7x7 = conv2d_bn(branch7x7, 192, 7, 1)
branch7x7dbl = conv2d_bn(x, 192, 1, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 7, 1)
branch7x7dbl = conv2d_bn(branch7x7dbl, 192, 1, 7)
branch_pool = AveragePooling2D((3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch7x7, branch7x7dbl, branch_pool],
axis=channel_axis,
name='mixed7')
# mixed 8: 8 x 8 x 1280
branch3x3 = conv2d_bn(x, 192, 1, 1)
branch3x3 = conv2d_bn(branch3x3, 320, 3, 3,
strides=(2, 2), padding='valid')
branch7x7x3 = conv2d_bn(x, 192, 1, 1)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 1, 7)
branch7x7x3 = conv2d_bn(branch7x7x3, 192, 7, 1)
branch7x7x3 = conv2d_bn(
branch7x7x3, 192, 3, 3, strides=(2, 2), padding='valid')
branch_pool = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = layers.concatenate(
[branch3x3, branch7x7x3, branch_pool], axis=channel_axis, name='mixed8')
# mixed 9: 8 x 8 x 2048
for i in range(2):
branch1x1 = conv2d_bn(x, 320, 1, 1)
branch3x3 = conv2d_bn(x, 384, 1, 1)
branch3x3_1 = conv2d_bn(branch3x3, 384, 1, 3)
branch3x3_2 = conv2d_bn(branch3x3, 384, 3, 1)
branch3x3 = layers.concatenate(
[branch3x3_1, branch3x3_2], axis=channel_axis, name='mixed9_' + str(i))
branch3x3dbl = conv2d_bn(x, 448, 1, 1)
branch3x3dbl = conv2d_bn(branch3x3dbl, 384, 3, 3)
branch3x3dbl_1 = conv2d_bn(branch3x3dbl, 384, 1, 3)
branch3x3dbl_2 = conv2d_bn(branch3x3dbl, 384, 3, 1)
branch3x3dbl = layers.concatenate(
[branch3x3dbl_1, branch3x3dbl_2], axis=channel_axis)
branch_pool = AveragePooling2D(
(3, 3), strides=(1, 1), padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 192, 1, 1)
x = layers.concatenate(
[branch1x1, branch3x3, branch3x3dbl, branch_pool],
axis=channel_axis,
name='mixed' + str(9 + i))
if include_top:
# Classification block
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
inputs = img_input
# Create model.
model = Model(inputs, x, name='inception_v3')
# load weights
if weights == 'imagenet':
if K.image_data_format() == 'channels_first':
if K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
if include_top:
weights_path = model_path
model.load_weights(weights_path)
else:
weights_path = ""
elif (weights == "trained"):
weights_path = model_path
model.load_weights(weights_path)
return model
def VGG19(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the VGG19 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format='channels_last'` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
Arguments:
include_top: whether to include the 3 fully-connected
layers at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 48.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(
input_shape,
default_size=224,
min_size=48,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Block 1
x = Conv2D(
64, (3, 3), activation='relu', padding='same', name='block1_conv1')(
img_input)
x = Conv2D(
64, (3, 3), activation='relu', padding='same', name='block1_conv2')(
x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool')(x)
# Block 2
x = Conv2D(
128, (3, 3), activation='relu', padding='same', name='block2_conv1')(
x)
x = Conv2D(
128, (3, 3), activation='relu', padding='same', name='block2_conv2')(
x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool')(x)
# Block 3
x = Conv2D(
256, (3, 3), activation='relu', padding='same', name='block3_conv1')(
x)
x = Conv2D(
256, (3, 3), activation='relu', padding='same', name='block3_conv2')(
x)
x = Conv2D(
256, (3, 3), activation='relu', padding='same', name='block3_conv3')(
x)
x = Conv2D(
256, (3, 3), activation='relu', padding='same', name='block3_conv4')(
x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool')(x)
# Block 4
x = Conv2D(
512, (3, 3), activation='relu', padding='same', name='block4_conv1')(
x)
x = Conv2D(
512, (3, 3), activation='relu', padding='same', name='block4_conv2')(
x)
x = Conv2D(
512, (3, 3), activation='relu', padding='same', name='block4_conv3')(
x)
x = Conv2D(
512, (3, 3), activation='relu', padding='same', name='block4_conv4')(
x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool')(x)
# Block 5
x = Conv2D(
512, (3, 3), activation='relu', padding='same', name='block5_conv1')(
x)
x = Conv2D(
512, (3, 3), activation='relu', padding='same', name='block5_conv2')(
x)
x = Conv2D(
512, (3, 3), activation='relu', padding='same', name='block5_conv3')(
x)
x = Conv2D(
512, (3, 3), activation='relu', padding='same', name='block5_conv4')(
x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool')(x)
if include_top:
# Classification block
x = Flatten(name='flatten')(x)
x = Dense(4096, activation='relu', name='fc1')(x)
x = Dense(4096, activation='relu', name='fc2')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='vgg19')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'vgg19_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
file_hash='cbe5617147190e668d6c5d5026f83318')
else:
weights_path = get_file(
'vgg19_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
file_hash='253f8cb515780f3b799900260a226db6')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def NASNet(input_shape=None,
penultimate_filters=4032,
num_blocks=6,
stem_block_filters=96,
skip_reduction=True,
filter_multiplier=2,
include_top=True,
weights=None,
input_tensor=None,
pooling=None,
classes=1000,
default_size=None):
"""Instantiates a NASNet model.
Note that only TensorFlow is supported for now,
therefore it only works with the data format
`image_data_format='channels_last'` in your Keras config
at `~/.keras/keras.json`.
Arguments:
input_shape: Optional shape tuple, the input shape
is by default `(331, 331, 3)` for NASNetLarge and
`(224, 224, 3)` for NASNetMobile.
It should have exactly 3 inputs channels,
and width and height should be no smaller than 32.
E.g. `(224, 224, 3)` would be one valid value.
penultimate_filters: Number of filters in the penultimate layer.
NASNet models use the notation `NASNet (N @ P)`, where:
- N is the number of blocks
- P is the number of penultimate filters
num_blocks: Number of repeated blocks of the NASNet model.
NASNet models use the notation `NASNet (N @ P)`, where:
- N is the number of blocks
- P is the number of penultimate filters
stem_block_filters: Number of filters in the initial stem block
skip_reduction: Whether to skip the reduction step at the tail
end of the network. Set to `False` for CIFAR models.
filter_multiplier: Controls the width of the network.
- If `filter_multiplier` < 1.0, proportionally decreases the number
of filters in each layer.
- If `filter_multiplier` > 1.0, proportionally increases the number
of filters in each layer.
- If `filter_multiplier` = 1, default number of filters from the
paper are used at each layer.
include_top: Whether to include the fully-connected
layer at the top of the network.
weights: `None` (random initialization) or
`imagenet` (ImageNet weights)
input_tensor: Optional Keras tensor (i.e. output of
`layers.Input()`)
to use as image input for the model.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model
will be the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a
2D tensor.
- `max` means that global max pooling will
be applied.
classes: Optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
default_size: Specifies the default image size of the model
Returns:
A Keras model instance.
Raises:
ValueError: In case of invalid argument for `weights`,
invalid input shape or invalid `penultimate_filters` value.
RuntimeError: If attempting to run this model with a
backend that does not support separable convolutions.
"""
if K.backend() != 'tensorflow':
raise RuntimeError('Only Tensorflow backend is currently supported, '
'as other backends do not support '
'separable convolution.')
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as ImageNet with `include_top` '
'as true, `classes` should be 1000')
if (isinstance(input_shape, tuple) and None in input_shape and
weights == 'imagenet'):
raise ValueError('When specifying the input shape of a NASNet'
' and loading `ImageNet` weights, '
'the input_shape argument must be static '
'(no None entries). Got: `input_shape=' +
str(input_shape) + '`.')
if default_size is None:
default_size = 331
# Determine proper input shape and default size.
input_shape = _obtain_input_shape(
input_shape,
default_size=default_size,
min_size=32,
data_format=K.image_data_format(),
require_flatten=False,
weights=weights)
if K.image_data_format() != 'channels_last':
logging.warning('The NASNet family of models is only available '
'for the input data format "channels_last" '
'(width, height, channels). '
'However your settings specify the default '
'data format "channels_first" (channels, width, height).'
' You should set `image_data_format="channels_last"` '
'in your Keras config located at ~/.keras/keras.json. '
'The model being returned right now will expect inputs '
'to follow the "channels_last" data format.')
K.set_image_data_format('channels_last')
old_data_format = 'channels_first'
else:
old_data_format = None
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if penultimate_filters % 24 != 0:
raise ValueError(
'For NASNet-A models, the value of `penultimate_filters` '
'needs to be divisible by 24. Current value: %d' % penultimate_filters)
channel_dim = 1 if K.image_data_format() == 'channels_first' else -1
filters = penultimate_filters // 24
if not skip_reduction:
x = Conv2D(
stem_block_filters, (3, 3),
strides=(2, 2),
padding='valid',
use_bias=False,
name='stem_conv1',
kernel_initializer='he_normal')(
img_input)
else:
x = Conv2D(
stem_block_filters, (3, 3),
strides=(1, 1),
padding='same',
use_bias=False,
name='stem_conv1',
kernel_initializer='he_normal')(
img_input)
x = BatchNormalization(
axis=channel_dim, momentum=0.9997, epsilon=1e-3, name='stem_bn1')(
x)
p = None
if not skip_reduction: # imagenet / mobile mode
x, p = _reduction_a_cell(
x, p, filters // (filter_multiplier**2), block_id='stem_1')
x, p = _reduction_a_cell(
x, p, filters // filter_multiplier, block_id='stem_2')
for i in range(num_blocks):
x, p = _normal_a_cell(x, p, filters, block_id='%d' % (i))
x, p0 = _reduction_a_cell(
x, p, filters * filter_multiplier, block_id='reduce_%d' % (num_blocks))
p = p0 if not skip_reduction else p
for i in range(num_blocks):
x, p = _normal_a_cell(
x, p, filters * filter_multiplier, block_id='%d' % (num_blocks + i + 1))
x, p0 = _reduction_a_cell(
x,
p,
filters * filter_multiplier**2,
block_id='reduce_%d' % (2 * num_blocks))
p = p0 if not skip_reduction else p
for i in range(num_blocks):
x, p = _normal_a_cell(
x,
p,
filters * filter_multiplier**2,
block_id='%d' % (2 * num_blocks + i + 1))
x = Activation('relu')(x)
if include_top:
x = GlobalAveragePooling2D()(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
model = Model(inputs, x, name='NASNet')
# load weights
if weights == 'imagenet':
if default_size == 224: # mobile version
if include_top:
weight_path = NASNET_MOBILE_WEIGHT_PATH
model_name = 'nasnet_mobile.h5'
else:
weight_path = NASNET_MOBILE_WEIGHT_PATH_NO_TOP
model_name = 'nasnet_mobile_no_top.h5'
weights_file = get_file(model_name, weight_path, cache_subdir='models')
model.load_weights(weights_file)
elif default_size == 331: # large version
if include_top:
weight_path = NASNET_LARGE_WEIGHT_PATH
model_name = 'nasnet_large.h5'
else:
weight_path = NASNET_LARGE_WEIGHT_PATH_NO_TOP
model_name = 'nasnet_large_no_top.h5'
weights_file = get_file(model_name, weight_path, cache_subdir='models')
model.load_weights(weights_file)
else:
raise ValueError('ImageNet weights can only be loaded with NASNetLarge'
' or NASNetMobile')
elif weights is not None:
model.load_weights(weights)
if old_data_format:
K.set_image_data_format(old_data_format)
return model
def ResNet50(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the ResNet50 architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format='channels_last'` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The data format
convention used by the model is the one
specified in your Keras config file.
Arguments:
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 197.
E.g. `(200, 200, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(
input_shape,
default_size=224,
min_size=197,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
if K.image_data_format() == 'channels_last':
bn_axis = 3
else:
bn_axis = 1
x = Conv2D(
64, (7, 7), strides=(2, 2), padding='same', name='conv1')(img_input)
x = BatchNormalization(axis=bn_axis, name='bn_conv1')(x)
x = Activation('relu')(x)
x = MaxPooling2D((3, 3), strides=(2, 2))(x)
x = conv_block(x, 3, [64, 64, 256], stage=2, block='a', strides=(1, 1))
x = identity_block(x, 3, [64, 64, 256], stage=2, block='b')
x = identity_block(x, 3, [64, 64, 256], stage=2, block='c')
x = conv_block(x, 3, [128, 128, 512], stage=3, block='a')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='b')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='c')
x = identity_block(x, 3, [128, 128, 512], stage=3, block='d')
x = conv_block(x, 3, [256, 256, 1024], stage=4, block='a')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='b')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='c')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='d')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='e')
x = identity_block(x, 3, [256, 256, 1024], stage=4, block='f')
x = conv_block(x, 3, [512, 512, 2048], stage=5, block='a')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='b')
x = identity_block(x, 3, [512, 512, 2048], stage=5, block='c')
x = AveragePooling2D((7, 7), name='avg_pool')(x)
if include_top:
x = Flatten()(x)
x = Dense(classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
model = Model(inputs, x, name='resnet50')
# load weights
if weights == 'imagenet':
if include_top:
weights_path = get_file(
'resnet50_weights_tf_dim_ordering_tf_kernels.h5',
WEIGHTS_PATH,
cache_subdir='models',
md5_hash='a7b3fe01876f51b976af0dea6bc144eb')
else:
weights_path = get_file(
'resnet50_weights_tf_dim_ordering_tf_kernels_notop.h5',
WEIGHTS_PATH_NO_TOP,
cache_subdir='models',
md5_hash='a268eb855778b3df3c7506639542a6af')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def DenseNet(model_input, depth=40, nb_dense_block=3, growth_rate=12, nb_filter=-1, nb_layers_per_block=-1,
bottleneck=False, reduction=0.0, dropout_rate=0.0, weight_decay=1e-4, subsample_initial_block=False,
include_top=True, weights=None, input_tensor=None,
classes=10, activation='softmax', model_path = ''):
'''Instantiate the DenseNet architecture,
optionally loading weights pre-trained
on CIFAR-10. Note that when using TensorFlow,
for best performance you should set
`image_data_format='channels_last'` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with both
TensorFlow and Theano. The dimension ordering
convention used by the model is the one
specified in your Keras config file.
# Arguments
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(32, 32, 3)` (with `channels_last` dim ordering)
or `(3, 32, 32)` (with `channels_first` dim ordering).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 8.
E.g. `(200, 200, 3)` would be one valid value.
depth: number or layers in the DenseNet
nb_dense_block: number of dense blocks to add to end (generally = 3)
growth_rate: number of filters to add per dense block
nb_filter: initial number of filters. -1 indicates initial
number of filters is 2 * growth_rate
nb_layers_per_block: number of layers in each dense block.
Can be a -1, positive integer or a list.
If -1, calculates nb_layer_per_block from the network depth.
If positive integer, a set number of layers per dense block.
If list, nb_layer is used as provided. Note that list size must
be (nb_dense_block + 1)
bottleneck: flag to add bottleneck blocks in between dense blocks
reduction: reduction factor of transition blocks.
Note : reduction value is inverted to compute compression.
dropout_rate: dropout rate
weight_decay: weight decay rate
subsample_initial_block: Set to True to subsample the initial convolution and
add a MaxPool2D before the dense blocks are added.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization) or
'imagenet' (pre-training on ImageNet)..
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
activation: Type of activation at the top layer. Can be one of 'softmax' or 'sigmoid'.
Note that if sigmoid is used, classes must be 1.
# Returns
A Keras model instance.
'''
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as ImageNet with `include_top`'
' as true, `classes` should be 1000')
if activation not in ['softmax', 'sigmoid']:
raise ValueError('activation must be one of "softmax" or "sigmoid"')
if activation == 'sigmoid' and classes != 1:
raise ValueError('sigmoid activation can only be used when classes = 1')
# Determine proper input shape
img_input = model_input
x = __create_dense_net(classes, img_input, include_top, depth, nb_dense_block,
growth_rate, nb_filter, nb_layers_per_block, bottleneck, reduction,
dropout_rate, weight_decay, subsample_initial_block, activation)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
inputs = img_input
# Create model.
model = Model(inputs, x, name='densenet')
# load weights
if weights == 'imagenet':
weights_loaded = False
if (depth == 121) and (nb_dense_block == 4) and (growth_rate == 32) and (nb_filter == 64) and \
(bottleneck is True) and (reduction == 0.5) and (dropout_rate == 0.0) and (subsample_initial_block):
weights_path = model_path
model.load_weights(weights_path)
weights_loaded = True
if weights_loaded:
if K.backend() == 'theano':
convert_all_kernels_in_model(model)
if K.image_data_format() == 'channels_first' and K.backend() == 'tensorflow':
warnings.warn('You are using the TensorFlow backend, yet you '
'are using the Theano '
'image data format convention '
'(`image_data_format="channels_first"`). '
'For best performance, set '
'`image_data_format="channels_last"` in '
'your Keras config '
'at ~/.keras/keras.json.')
elif (weights == "trained"):
weights_path = model_path
model.load_weights(weights_path)
return model
def InceptionResNetV2(include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the Inception-ResNet v2 architecture.
Optionally loads weights pre-trained on ImageNet.
Note that when using TensorFlow, for best performance you should
set `"image_data_format": "channels_last"` in your Keras config
at `~/.keras/keras.json`.
The model and the weights are compatible with TensorFlow, Theano and
CNTK backends. The data format convention used by the model is
the one specified in your Keras config file.
Note that the default input image size for this model is 299x299, instead
of 224x224 as in the VGG16 and ResNet models. Also, the input preprocessing
function is different (i.e., do not use `imagenet_utils.preprocess_input()`
with this model. Use `preprocess_input()` defined in this module instead).
Arguments:
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is `False` (otherwise the input shape
has to be `(299, 299, 3)` (with `'channels_last'` data format)
or `(3, 299, 299)` (with `'channels_first'` data format).
It should have exactly 3 inputs channels,
and width and height should be no smaller than 139.
E.g. `(150, 150, 3)` would be one valid value.
pooling: Optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the last convolutional layer.
- `'avg'` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `'max'` means that global max pooling will be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is `True`, and
if no `weights` argument is specified.
Returns:
A Keras `Model` instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(
input_shape,
default_size=299,
min_size=139,
data_format=K.image_data_format(),
require_flatten=False,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
# Stem block: 35 x 35 x 192
x = conv2d_bn(img_input, 32, 3, strides=2, padding='valid')
x = conv2d_bn(x, 32, 3, padding='valid')
x = conv2d_bn(x, 64, 3)
x = MaxPooling2D(3, strides=2)(x)
x = conv2d_bn(x, 80, 1, padding='valid')
x = conv2d_bn(x, 192, 3, padding='valid')
x = MaxPooling2D(3, strides=2)(x)
# Mixed 5b (Inception-A block): 35 x 35 x 320
branch_0 = conv2d_bn(x, 96, 1)
branch_1 = conv2d_bn(x, 48, 1)
branch_1 = conv2d_bn(branch_1, 64, 5)
branch_2 = conv2d_bn(x, 64, 1)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_pool = AveragePooling2D(3, strides=1, padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1)
branches = [branch_0, branch_1, branch_2, branch_pool]
channel_axis = 1 if K.image_data_format() == 'channels_first' else 3
x = Concatenate(axis=channel_axis, name='mixed_5b')(branches)
# 10x block35 (Inception-ResNet-A block): 35 x 35 x 320
for block_idx in range(1, 11):
x = inception_resnet_block(
x, scale=0.17, block_type='block35', block_idx=block_idx)
# Mixed 6a (Reduction-A block): 17 x 17 x 1088
branch_0 = conv2d_bn(x, 384, 3, strides=2, padding='valid')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 256, 3)
branch_1 = conv2d_bn(branch_1, 384, 3, strides=2, padding='valid')
branch_pool = MaxPooling2D(3, strides=2, padding='valid')(x)
branches = [branch_0, branch_1, branch_pool]
x = Concatenate(axis=channel_axis, name='mixed_6a')(branches)
# 20x block17 (Inception-ResNet-B block): 17 x 17 x 1088
for block_idx in range(1, 21):
x = inception_resnet_block(
x, scale=0.1, block_type='block17', block_idx=block_idx)
# Mixed 7a (Reduction-B block): 8 x 8 x 2080
branch_0 = conv2d_bn(x, 256, 1)
branch_0 = conv2d_bn(branch_0, 384, 3, strides=2, padding='valid')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 288, 3, strides=2, padding='valid')
branch_2 = conv2d_bn(x, 256, 1)
branch_2 = conv2d_bn(branch_2, 288, 3)
branch_2 = conv2d_bn(branch_2, 320, 3, strides=2, padding='valid')
branch_pool = MaxPooling2D(3, strides=2, padding='valid')(x)
branches = [branch_0, branch_1, branch_2, branch_pool]
x = Concatenate(axis=channel_axis, name='mixed_7a')(branches)
# 10x block8 (Inception-ResNet-C block): 8 x 8 x 2080
for block_idx in range(1, 10):
x = inception_resnet_block(
x, scale=0.2, block_type='block8', block_idx=block_idx)
x = inception_resnet_block(
x, scale=1., activation=None, block_type='block8', block_idx=10)
# Final convolution block: 8 x 8 x 1536
x = conv2d_bn(x, 1536, 1, name='conv_7b')
if include_top:
# Classification block
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='predictions')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D()(x)
elif pooling == 'max':
x = GlobalMaxPooling2D()(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`
if input_tensor is not None:
inputs = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model
model = Model(inputs, x, name='inception_resnet_v2')
# Load weights
if weights == 'imagenet':
if include_top:
fname = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels.h5'
weights_path = get_file(
fname,
BASE_WEIGHT_URL + fname,
cache_subdir='models',
file_hash='e693bd0210a403b3192acc6073ad2e96')
else:
fname = 'inception_resnet_v2_weights_tf_dim_ordering_tf_kernels_notop.h5'
weights_path = get_file(
fname,
BASE_WEIGHT_URL + fname,
cache_subdir='models',
file_hash='d19885ff4a710c122648d3b5c3b684e4')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
def DenseNet(blocks,
include_top=True,
weights='imagenet',
input_tensor=None,
input_shape=None,
pooling=None,
classes=1000):
"""Instantiates the DenseNet architecture.
Optionally loads weights pre-trained
on ImageNet. Note that when using TensorFlow,
for best performance you should set
`image_data_format='channels_last'` in your Keras config
at ~/.keras/keras.json.
The model and the weights are compatible with
TensorFlow, Theano, and CNTK. The data format
convention used by the model is the one
specified in your Keras config file.
Arguments:
blocks: numbers of building blocks for the four dense layers.
include_top: whether to include the fully-connected
layer at the top of the network.
weights: one of `None` (random initialization),
'imagenet' (pre-training on ImageNet),
or the path to the weights file to be loaded.
input_tensor: optional Keras tensor (i.e. output of `layers.Input()`)
to use as image input for the model.
input_shape: optional shape tuple, only to be specified
if `include_top` is False (otherwise the input shape
has to be `(224, 224, 3)` (with `channels_last` data format)
or `(3, 224, 224)` (with `channels_first` data format).
It should have exactly 3 inputs channels.
pooling: optional pooling mode for feature extraction
when `include_top` is `False`.
- `None` means that the output of the model will be
the 4D tensor output of the
last convolutional layer.
- `avg` means that global average pooling
will be applied to the output of the
last convolutional layer, and thus
the output of the model will be a 2D tensor.
- `max` means that global max pooling will
be applied.
classes: optional number of classes to classify images
into, only to be specified if `include_top` is True, and
if no `weights` argument is specified.
Returns:
A Keras model instance.
Raises:
ValueError: in case of invalid argument for `weights`,
or invalid input shape.
"""
if not (weights in {'imagenet', None} or os.path.exists(weights)):
raise ValueError('The `weights` argument should be either '
'`None` (random initialization), `imagenet` '
'(pre-training on ImageNet), '
'or the path to the weights file to be loaded.')
if weights == 'imagenet' and include_top and classes != 1000:
raise ValueError('If using `weights` as imagenet with `include_top`'
' as true, `classes` should be 1000')
# Determine proper input shape
input_shape = _obtain_input_shape(
input_shape,
default_size=224,
min_size=221,
data_format=K.image_data_format(),
require_flatten=include_top,
weights=weights)
if input_tensor is None:
img_input = Input(shape=input_shape)
else:
if not K.is_keras_tensor(input_tensor):
img_input = Input(tensor=input_tensor, shape=input_shape)
else:
img_input = input_tensor
bn_axis = 3 if K.image_data_format() == 'channels_last' else 1
x = ZeroPadding2D(padding=((3, 3), (3, 3)))(img_input)
x = Conv2D(64, 7, strides=2, use_bias=False, name='conv1/conv')(x)
x = BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='conv1/bn')(x)
x = Activation('relu', name='conv1/relu')(x)
x = ZeroPadding2D(padding=((1, 1), (1, 1)))(x)
x = MaxPooling2D(3, strides=2, name='pool1')(x)
x = dense_block(x, blocks[0], name='conv2')
x = transition_block(x, 0.5, name='pool2')
x = dense_block(x, blocks[1], name='conv3')
x = transition_block(x, 0.5, name='pool3')
x = dense_block(x, blocks[2], name='conv4')
x = transition_block(x, 0.5, name='pool4')
x = dense_block(x, blocks[3], name='conv5')
x = BatchNormalization(axis=bn_axis, epsilon=1.001e-5, name='bn')(x)
if include_top:
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(classes, activation='softmax', name='fc1000')(x)
else:
if pooling == 'avg':
x = GlobalAveragePooling2D(name='avg_pool')(x)
elif pooling == 'max':
x = GlobalMaxPooling2D(name='max_pool')(x)
# Ensure that the model takes into account
# any potential predecessors of `input_tensor`.
if input_tensor is not None:
inputs = layer_utils.get_source_inputs(input_tensor)
else:
inputs = img_input
# Create model.
if blocks == [6, 12, 24, 16]:
model = Model(inputs, x, name='densenet121')
elif blocks == [6, 12, 32, 32]:
model = Model(inputs, x, name='densenet169')
elif blocks == [6, 12, 48, 32]:
model = Model(inputs, x, name='densenet201')
else:
model = Model(inputs, x, name='densenet')
# Load weights.
if weights == 'imagenet':
if include_top:
if blocks == [6, 12, 24, 16]:
weights_path = get_file(
'densenet121_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET121_WEIGHT_PATH,
cache_subdir='models',
file_hash='0962ca643bae20f9b6771cb844dca3b0')
elif blocks == [6, 12, 32, 32]:
weights_path = get_file(
'densenet169_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET169_WEIGHT_PATH,
cache_subdir='models',
file_hash='bcf9965cf5064a5f9eb6d7dc69386f43')
elif blocks == [6, 12, 48, 32]:
weights_path = get_file(
'densenet201_weights_tf_dim_ordering_tf_kernels.h5',
DENSENET201_WEIGHT_PATH,
cache_subdir='models',
file_hash='7bb75edd58cb43163be7e0005fbe95ef')
else:
if blocks == [6, 12, 24, 16]:
weights_path = get_file(
'densenet121_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET121_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='4912a53fbd2a69346e7f2c0b5ec8c6d3')
elif blocks == [6, 12, 32, 32]:
weights_path = get_file(
'densenet169_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET169_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='50662582284e4cf834ce40ab4dfa58c6')
elif blocks == [6, 12, 48, 32]:
weights_path = get_file(
'densenet201_weights_tf_dim_ordering_tf_kernels_notop.h5',
DENSENET201_WEIGHT_PATH_NO_TOP,
cache_subdir='models',
file_hash='1c2de60ee40562448dbac34a0737e798')
model.load_weights(weights_path)
elif weights is not None:
model.load_weights(weights)
return model
