if I set the args snapshot,the model will load from the path of snapshot, but the training_model = model ,the training_model is not complie, the example is as follow, is this is a bug??
if args.snapshot is not None:
print("Loading model, this may take a second...")
model = models.load_model(args.snapshot, backbone_name=args.backbone)
training_model = model
anchor_params = None
if args.config and "anchor_parameters" in args.config:
anchor_params = parse_anchor_parameters(args.config)
prediction_model = retinanet_bbox(model=model, anchor_params=anchor_params)
This issue has been automatically marked as stale due to the lack of recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
if I set the args snapshot,the model will load from the path of snapshot, but the training_model = model ,the training_model is not complie, the example is as follow, is this is a bug??