def load_model(filesystem: S3FS, config: PredictionConfig) -> ResUnetA:
""" Copy the model locally if not existing and load it """
if not os.path.exists(f'{config.temp_model_path}/{config.model_name}'):
if not filesystem.exists(
f'{config.model_path}/{config.model_name}/checkpoints/'):
filesystem.makedirs(
f'{config.model_path}/{config.model_name}/checkpoints/')
copy_dir(filesystem,
f'{config.model_path}/{config.model_name}/checkpoints/',
f'{config.temp_model_path}/{config.model_name}',
'checkpoints')
copy_file(filesystem,
f'{config.model_path}/{config.model_name}/model_cfg.json',
f'{config.temp_model_path}/{config.model_name}',
'model_cfg.json')
input_shape = dict(
features=[None, config.height, config.width, config.n_channels])
with open(f'{config.temp_model_path}/{config.model_name}/model_cfg.json',
'r') as jfile:
model_cfg = json.load(jfile)
# initialise model from config, build, compile and load trained weights
model = ResUnetA(model_cfg)
model.build(input_shape)
model.net.compile()
model.net.load_weights(
f'{config.temp_model_path}/{config.model_name}/checkpoints/model.ckpt')
return model
def load_metadata(filesystem: S3FS, config: PredictionConfig) -> pd.DataFrame:
""" Load DataFrame with info about normalisation factors """
metadata_dir = os.path.dirname(config.metadata_path)
if not filesystem.exists(metadata_dir):
filesystem.makedirs(metadata_dir)
df = pd.read_csv(filesystem.open(f'{config.metadata_path}'))
normalisation_factors = df.groupby(
pd.to_datetime(df.timestamp).dt.to_period("M")).max()
normalisation_factors['month'] = pd.to_datetime(
normalisation_factors.timestamp).dt.month
return normalisation_factors
