Closed taraspiotr closed 6 years ago
Right now target_sizes are definded in pipeline_manager.py:
target_sizes
data = {'input': {'meta': meta_train, 'target_sizes': [(300, 300)] * len(meta_train)}, 'specs': {'train_mode': True}, 'callback_input': {'meta_valid': meta_valid} }
It can be problematic when images are all the same. I was thinking about storing target_sizes, which are also source sizes, in metadata.
@taraspiotr that is how we usually do it. but this time, since it was all one size we left it like that. Feel free to refactor/add to meta when using other data sources.
Right now
target_sizes
are definded in pipeline_manager.py:It can be problematic when images are all the same. I was thinking about storing target_sizes, which are also source sizes, in metadata.