I am using a model in which one of the arguments is the following file, which is passed with the name checkpoint (without extension):
model_checkpoint_path: "epoch-29"
all_model_checkpoint_paths: "epoch-29"
It is used in the following piece of code:
parser = argparse.ArgumentParser()
parser.add_argument('--checkpoint', help='path to checkpoint to restore',default='epoch')
args = parser.parse_args()
# load config
config = generate_config()
# build model and restore from checkpoint
model = build_model(num_output_neurons=config.n_output_neurons, y_input=config.n_mels, num_units=config.n_dense_units, num_filts=config.n_filters)
checkpoint = tf.train.Checkpoint(model=model)
checkpoint.restore(args.checkpoint)
I obtain the following error:
tensorflow.python.framework.errors_impl.DataLossError: Unable to open table file ...: Data loss: not an sstable (bad magic number): perhaps your file is in a different file format and you need to use a different restore operator?
Which is the correct format for the method restore?