def test_nasnet_variable_input_channels():
input_shape = (1, None,
None) if K.image_data_format() == 'channels_first' else (
None, None, 1)
model = applications.NASNetMobile(weights=None,
include_top=False,
input_shape=input_shape)
assert model.output_shape == (None, None, None, 1056)
model = applications.NASNetLarge(weights=None,
include_top=False,
input_shape=input_shape)
assert model.output_shape == (None, None, None, 4032)
input_shape = (4, None,
None) if K.image_data_format() == 'channels_first' else (
None, None, 4)
model = applications.NASNetMobile(weights=None,
include_top=False,
input_shape=input_shape)
assert model.output_shape == (None, None, None, 1056)
model = applications.NASNetLarge(weights=None,
include_top=False,
input_shape=input_shape)
assert model.output_shape == (None, None, None, 4032)
def build_fit_save_cnn(input_shape, n_classes, epochs, batch_size, X_train, X_val, y_train, y_val):
base_model = applications.NASNetMobile(weights='imagenet', include_top=False, input_shape=input_shape)
add_model = Sequential()
add_model.add(Flatten(input_shape=base_model.output_shape[1:]))
add_model.add(Dense(512, activation='relu'))
add_model.add(Dense(512, activation='relu'))
add_model.add(Dropout(0.25))
add_model.add(Dense(n_classes, activation='softmax'))
# combine base model and fully connected layers
final_model = Model(inputs=base_model.input, outputs=add_model(base_model.output))
# specify SDG optimizer parameters
sgd = optimizers.SGD(lr=0.001, decay=1e-6, momentum=0.9, nesterov=True)
# compile model
final_model.compile(loss='categorical_crossentropy', optimizer=sgd, metrics=['accuracy'])
history = final_model.fit(X_train, y_train, batch_size=batch_size, epochs=epochs, verbose=1, validation_data=(X_val, y_val))
score = final_model.evaluate(X_val, y_val, verbose=0)
print('Val. score:', score[0])
print('Val. accuracy:', score[1])
plot_model(final_model, to_file='drive/ML-Pandora/CNN-NASNetLarge-Pandora-Model.svg')
show_history(history)
save_model(final_model,history)
return final_model
def test_nasnet_pooling():
model = applications.NASNetMobile(weights=None,
include_top=False,
pooling='avg')
assert model.output_shape == (None, 1056)
model = applications.NASNetLarge(weights=None,
include_top=False,
pooling='avg')
assert model.output_shape == (None, 4032)
def get_imagenet_architecture(architecture, variant, size, alpha, output_layer, include_top=False, weights='imagenet'):
from keras import applications, Model
if include_top:
assert output_layer == 'last'
if size == 'auto':
size = get_image_size(architecture, variant, size)
shape = (size, size, 3)
if architecture == 'densenet':
if variant == 'auto':
variant = 'densenet-121'
if variant == 'densenet-121':
model = applications.DenseNet121(weights=weights, include_top=include_top, input_shape=shape)
elif variant == 'densenet-169':
model = applications.DenseNet169(weights=weights, include_top=include_top, input_shape=shape)
elif variant == 'densenet-201':
model = applications.DenseNet201(weights=weights, include_top=include_top, input_shape=shape)
elif architecture == 'inception-resnet-v2':
model = applications.InceptionResNetV2(weights=weights, include_top=include_top, input_shape=shape)
elif architecture == 'mobilenet':
model = applications.MobileNet(weights=weights, include_top=include_top, input_shape=shape, alpha=alpha)
elif architecture == 'mobilenet-v2':
model = applications.MobileNetV2(weights=weights, include_top=include_top, input_shape=shape, alpha=alpha)
elif architecture == 'nasnet':
if variant == 'auto':
variant = 'large'
if variant == 'large':
model = applications.NASNetLarge(weights=weights, include_top=include_top, input_shape=shape)
else:
model = applications.NASNetMobile(weights=weights, include_top=include_top, input_shape=shape)
elif architecture == 'resnet-50':
model = applications.ResNet50(weights=weights, include_top=include_top, input_shape=shape)
elif architecture == 'vgg-16':
model = applications.VGG16(weights=weights, include_top=include_top, input_shape=shape)
elif architecture == 'vgg-19':
model = applications.VGG19(weights=weights, include_top=include_top, input_shape=shape)
elif architecture == 'xception':
model = applications.Xception(weights=weights, include_top=include_top, input_shape=shape)
elif architecture == 'inception-v3':
model = applications.InceptionV3(weights=weights, include_top=include_top, input_shape=shape)
if output_layer != 'last':
try:
if isinstance(output_layer, int):
layer = model.layers[output_layer]
else:
layer = model.get_layer(output_layer)
except Exception:
raise VergeMLError('layer not found: {}'.format(output_layer))
model = Model(inputs=model.input, outputs=layer.output)
return model
def test_nasnet():
model = applications.NASNetMobile(weights=None)
assert model.output_shape == (None, 1000)
model = applications.NASNetLarge(weights=None)
assert model.output_shape == (None, 1000)
input_shape=(256, 256, 3))
elif args.base_model == 'densenet121':
base_model = applications.DenseNet121(weights='imagenet',
include_top=False,
input_shape=(256, 256, 3))
elif args.base_model == 'densenet169':
base_model = applications.DenseNet169(weights='imagenet',
include_top=False,
input_shape=(256, 256, 3))
elif args.base_model == 'densenet201':
base_model = applications.DenseNet201(weights='imagenet',
include_top=False,
input_shape=(256, 256, 3))
elif args.base_model == 'nasnetmobile':
base_model = applications.NASNetMobile(weights='imagenet',
include_top=False,
input_shape=(256, 256, 3))
elif args.base_model == 'nasnetlarge':
base_model = applications.NASNetLarge(weights='imagenet',
include_top=False,
input_shape=(256, 256, 3))
else:
raise ValueError(
"Model you entered is not present in the model zoo thats offered")
if args.bottleneck_tensorname is None:
# Taking the last tensor (Just before the softmax layer)
BOTTLENECK_TENSOR_NAME = base_model.layers[-1].name
else:
BOTTLENECK_TENSOR_NAME = args.bottleneck_tensorname
def _nasnetmobile(image_shape):
return applications.NASNetMobile(include_top=False,
input_shape=image_shape)
def bulid_keras_pretrained_net(net_name, width, height, RGB, ouput_classes, load_epoch = 0):
'''
Build NASNET which is able to save weights in one file
'''
MODEL_W_PATH = SAVE_FOLDER + '/mobilenetv2_weights_'
channel = 3 if RGB == True else 1
dev = "/cpu:0" if N_GPU != 1 else "/gpu:0"
with tf.device(dev):
if load_epoch != 0:
model = load_model(MODEL_W_PATH + str(load_epoch) + '.h5')
else:
# this could also be the output a different Keras model or layer
input_tensor = Input(shape=(width, height, channel)) # this assumes K.image_data_format() == 'channels_last'
if net_name == 'Xception':
MODEL_W_PATH = SAVE_FOLDER + '/xception_weights_'
base_model = applications.xception.Xception(input_tensor=input_tensor,weights='imagenet', include_top=False)
elif net_name == 'MobileNet':
MODEL_W_PATH = SAVE_FOLDER + '/mobilenetv2_weights_'
base_model = applications.mobilenet_v2.MobileNetV2(input_tensor=input_tensor, weights='imagenet', include_top=False)
elif net_name == 'NasnetMoblie':
MODEL_W_PATH = SAVE_FOLDER + '/nasnetmobile_weights_'
base_model = applications.NASNetMobile(input_tensor=input_tensor,weights='imagenet', include_top=False)
else:
raise ValueError(net_name, ' is not supported!')
x = base_model.output
## add a global spatial average pooling layer
x = GlobalAveragePooling2D()(x)
x = Dropout(0.5)(x)
#x = Flatten()(x)
x = Dense(TOP_HIDDEN_L
,name='hidden_l')(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Dropout(0.5)(x)
# and a logistic layer -- let's say we have 200 classes
predictions = Dense(ouput_classes
, kernel_regularizer=regularizers.l2(1e-4)
, activation='softmax'
, name = 'predictions')(x)
# this is the model we will train
model = Model(inputs=base_model.input, outputs=predictions)
# set if some weights are trainable or not
for layer in model.layers[:len(base_model.layers)]:
layer.trainable = TRANSFERED_MODEL_UPDATE
#model = multi_gpu_model(model, gpus=N_GPU)
if N_GPU > 1: model = ModelMGPU(model, N_GPU)
# compile the model with a Adam optimizer and dynamic learning rate.
model.compile(loss='categorical_crossentropy', \
optimizer=Adam(lr=lr_schedule(load_epoch)), \
#optimizer=SGD(lr=1e-4, momentum=0.9), \
metrics=['accuracy'])
model.summary()
return model, MODEL_W_PATH
