def initialize_network(self):
self.local_model = load_model(
self.model_path,
custom_objects={
"annealed_loss": lc.loss_selector("annealed_loss")
},
)
def __load_local_model(self, path: str):
self.model = load_model(
path,
custom_objects={
"annealed_loss": lc.loss_selector("annealed_loss")
},
)
def __init__(self, inferrence_json_path, generator_obj):
self.inferrence_json_path = inferrence_json_path
self.generator_obj = generator_obj
local_json_loader = JsonLoader(inferrence_json_path)
local_json_loader.load_json()
self.json_data = local_json_loader.json_data
self.output_file = self.json_data["output_file"]
self.model_path = self.json_data["model_path"]
if "save_raw" in self.json_data.keys():
self.save_raw = self.json_data["save_raw"]
else:
self.save_raw = False
if "rescale" in self.json_data.keys():
self.rescale = self.json_data["rescale"]
else:
self.rescale = True
self.batch_size = self.generator_obj.batch_size
self.nb_datasets = len(self.generator_obj)
self.indiv_shape = self.generator_obj.get_output_size()
self.model = load_model(
self.model_path,
custom_objects={"annealed_loss": lc.loss_selector("annealed_loss")},
)
def initialize_loss(self):
self.loss = lc.loss_selector(self.loss_type)
# For transfer learning, knowing the baseline validation loss is important
baseline_val_loss = self.local_model.evaluate(self.local_test_generator)
# save init losses
save_loss_path = os.path.join(
self.output_dir, self.run_uid + "_" + self.model_string + "init_val_loss.npy"
)
np.save(save_loss_path, baseline_val_loss)
def initialize_loss(self):
self.loss = lc.loss_selector(self.loss_type)