def reset_layer_names(args):
'''In case of transfer learning, it's important that the names of the weights match
between the different networks (e.g. 2X and 4X). This function loads the lower-lever
SR network from a reset keras session (thus forcing names to start from naming index 0),
loads the weights onto that network, and saves the weights again with proper names'''
# Find lower-upscaling model results
BASE_G = os.path.join(
args.weight_path, 'VSRGANplus' + args.modelname + '_generator_' +
str(args.scaleFrom) + 'X.h5')
BASE_D = os.path.join(
args.weight_path, 'VSRGANplus' + args.modelname + '_discriminator_' +
str(args.scaleFrom) + 'X.h5')
assert os.path.isfile(BASE_G), 'Could not find ' + BASE_G
assert os.path.isfile(BASE_D), 'Could not find ' + BASE_D
# Load previous model with weights, and re-save weights so that name ordering will match new model
prev_gan = VSRGANplus(upscaling_factor=args.scaleFrom)
prev_gan.load_weights(BASE_G, BASE_D)
prev_gan.save_weights(args.weight_path +
'VSRGANplus{}'.format(args.modelname))
del prev_gan
K.reset_uids()
gc.collect()
return BASE_G, BASE_D
def predict_koa(self):
K.reset_uids()
model = "models\model.json"
weights = "models/model_weight.h5"
classes = {
'TRAIN': ['GRADE 0', 'GRADE 1', 'GRADE 2', 'GRADE 3', 'GRADE 4'],
'VALIDATION': ['GRADE 0', 'GRADE 1', 'GRADE 2', 'GRADE 3', 'GRADE 4'],
'TEST': ['GRADE 0', 'GRADE 1', 'GRADE 2', 'GRADE 3', 'GRADE 4'],
}
with CustomObjectScope({'GlorotUniform': glorot_uniform()}):
with open(model, 'r') as f:
model = model_from_json(f.read())
model.load_weights(weights)
img = image.load_img(self.img, target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)
model.compile(loss="categorical_crossentropy", metrics=[
"accuracy"], optimizer="adam")
result = model.predict(x)
pred_name = classes['TRAIN'][np.argmax(result)]
print("The osteoarthritis is classified to be {}.".format(pred_name))
return pred_name
def cargar_rnn(nombreArchivoModelo, nombreArchivoPesos):
k.reset_uids()
# Cargar la Arquitectura desde el archivo JSON
with open(nombreArchivoModelo + '.json', 'r') as f:
model = model_from_json(f.read())
# Cargar Pesos (weights) en el nuevo modelo
model.load_weights(nombreArchivoPesos + '.h5')
return model
def __init__(self, image_size, is_learning_phase=False):
K.set_learning_phase(int(is_learning_phase))
K.reset_uids()
self.image_size = image_size
self.n_cells = self.image_size // 32
self.m = self.buildModel()
self.model_compile()
def trainModels(nameList, shutDown):
for modelSet in modelSets:
print("Training {0}".format(modelSet.name))
model = modelsDict[modelSet.name]
trainModel(model.structure, model.generator, modelClass = modelSet.modelClass, epochs = model.epochs, losses = model.losses, modelName = modelSet.name, outClasses = model.outClasses, outVectors = model.outVectors, learning_rate = model.lr, metrics = model.metrics, altLabels = model.altLabels, augmentation = model.augmentation)
K.clear_session()
K.reset_uids()
if shutDown:
os.system('shutdown -s')
def __init__(self,encoder, image_size, n_classes):
self.encoder_output = encoder.model.output
self.anchors = np.array([
1.08, 1.19, 3.42, 4.41, 6.63, 11.38, 9.42, 5.11, 16.62, 10.52
]).reshape(5, 2)
K.reset_uids()
self.image_size = image_size
self.n_cells = self.image_size // 32
self.B = self.anchors.shape[0]
self.n_classes = n_classes
self.model = self.make_model()
self.num_layers = ModelBlock.get_head_num_layers(encoder, self.model)
def cargar_rnn(nombreArchivoModelo, nombreArchivoPesos):
k.reset_uids()
with open(nombreArchivoModelo + '.json', 'r') as f:
model = model_from_json(f.read())
model.load_weights(nombreArchivoPesos + '.h5')
return model
def wrapped(*args, **kwargs):
K.clear_session()
K.reset_uids()
return func(*args, **kwargs)
