Overflow/Underflow Operator Data Collection and Analysis

Prerequisites

To use the ATC tool to convert a model, ensure that the --status_check parameter has been added to the conversion command and set to 1, indicating that the overflow/underflow detection logic is added during operator compilation.

For details about the ATC tool and its parameters, see ATC Instructions.

Collecting Overflow/Underflow Operator Information

When the acl.init API is called for initialization, the dump configuration of an overflow/underflow operator is added to the JSON configuration file.

The following is an example of the content in the JSON configuration file. In the example, dump_path is a relative path.

{
    "dump":{
        "dump_path":"output",
        "dump_debug":"on"
    }
}

If dump_path is set to a relative path, you can view the exported data files in {app_executable_files}/{dump_path} directory. For each overflow/underflow operator, two data files are exported:

The dump file of an overflow/underflow operator is named as: {op_type}.{op_name}.{taskid}.{stream_id}.{timestamp}. Any period (.), slash (/), backslash (\), or space in the op_type or op_name field is replaced by an underscore (_).
The data file of an overflow/underflow operator is named as: OpDebug.Node_Opdebug.{taskid}.{stream_id}.{timestamp}, where taskid is not the task ID of an overflow/underflow operator and can be ignored.

For details about how to parse the preceding two files, see ""Overflow/Underflow Operator Data Collection and Analysis" " in Accuracy Debugging Tool Guide.

Parent topic: Additional Features