Step Parameter missing from Audio Representation
Hi again folks, I'm back into the Ketos saddle and running into a problem when I go to export my model to the ketos protobuf format. It seems to be related to teh step parameters, but I have this set in my json file. Here's the error I am getting:
Traceback (most recent call last): File "C:\Users\eferg.conda\envs\ketos_env\lib\site-packages\IPython\core\interactiveshell.py", line 3444, in run_code exec(code_obj, self.user_global_ns, self.user_ns) File "", line 2, in tmp_folder="tmp_export_folder", input_shape=(1,110,129,1), overwrite=False, input_duration=None) File "C:\Users\eferg.conda\envs\ketos_env\lib\site-packages\ketos\neural_networks\dev_utils\export.py", line 116, in export_to_ketos_protobuf assert 'step' in ar.keys(), 'step parameter is missing from audio representation' AttributeError: 'float' object has no attribute 'keys'
The 'step parameter is missing' element is leading me to think the issue is with that part of the attached json file. spec_config_BOEM.json
Thanks for any thoughts!