Rate this Page

extract_results_from_loggers#

class torch.ao.quantization.extract_results_from_loggers(model)[source]#

For a given model, extract the tensors stats and related information for each debug handle. The reason we have a list of object, instead of Tensor is because the output of node may not be a Tensor, it could be (nested) list, tuple or dict as well.

Returns

A dict is keyed by the debug_handle id and the values are a list of object recorded in loggers

Return type

dict[int, tuple[Optional[str], object, list[object]]]