dcase_util.keras.data_collector
- dcase_util.keras.data_collector(item_list=None, data_processing_chain=None, meta_processing_chain=None, target_format='single_target_per_sequence', channel_dimension='channels_last', verbose=True, print_indent=2)[source]
Data collector
Collects data and meta into matrices while processing them through processing chains.
- Parameters
- item_listlist or dict
Items in the data sequence. List containing multi-level dictionary with first level key ‘data’ and ‘meta’. Second level should contain parameters for process method in the processing chain. Default value None
- data_processing_chainProcessingChain
Data processing chain. Default value None
- meta_processing_chainProcessingChain
Meta processing chain. Default value None
- channel_dimensionstr
Controls where channel dimension should be added. Similar to Keras data format parameter. If None given, no channel dimension is added. Possible values [None, ‘channels_first’, ‘channels_last’] Default value None
- target_formatstr
Meta data interpretation in the relation to the data items. Possible values [‘same’, ‘single_target_per_segment’] Default value ‘single_target_per_segment’
- verbosebool
Print information about the data Default value True
- print_indentint
Default value 2
- Returns
- numpy.ndarray
data
- numpy.ndarray
meta
- dict
data size information