Shortcuts

mmcls.utils.load_json_log

mmcls.utils.load_json_log(json_log)[source]

load and convert json_logs to log_dicts.

Parameters

json_log (str) – The path of the json log file.

Returns

Key is the epoch, value is a sub dict. The keys in each sub dict are different metrics, e.g. memory, bbox_mAP, and the value is a list of corresponding values in all iterations in this epoch.

# An example output
{
    1: {'iter': [100, 200, 300], 'loss': [6.94, 6.73, 6.53]},
    2: {'iter': [100, 200, 300], 'loss': [6.33, 6.20, 6.07]},
    ...
}

Return type

dict[int, dict[str, list]]