ONNXPredict Example with ModelInputFieldsMap | Vantage BYOM - 3.0 - ONNXPredict Example: With ModelInputFieldsMap Range - Teradata Vantage

Teradata Vantage™ - Bring Your Own Model User Guide

Teradata Vantage
Release Number
May 2022
Last Update
Content Type
User Guide
Publication ID
English (United States)

The following example contains the argument value 'float_input=[1:4]' in ModelInputFieldsMap. In this case, float_input is the ONNX model input name (i.e., tensor name) and it maps to four columns starting at column position 1 and ending with column position 4 in the input table (the first column in table has index 0). The advantage of using the column range is that if you have a lot of columns you don't need to type in each one, you can specify a range. It is still necessary to make sure the order of the columns defined here match with the exact order the model is expecting.

select * from mldb.ONNXPredict(
    on (select * from iris_test)  --- Columns order is important as the base indexes are based off of it
    on (select * from onnx_models where model_id='tf_iris_softmax_onetensor_model') DIMENSION
        OverWriteCachedModel('float_input')  – In this example, a new version of the model is replacing the current version in the cache.
) as td
 *** Query completed. 30 rows found. 2 columns returned.
 *** Total elapsed time was 1 second.
         id  json_report
----------- -----------------------------------------------------------------------
        120       {"probability":[[2.2099151E-8,0.023814192,0.97618586]]}
         85       {"probability":[[1.0646227E-4,0.64747274,0.35242087]]}
        115       {"probability":[[8.84089E-12,1.13627166E-7,0.9999999]]}
         55       {"probability":[[2.3626533E-6,0.9896403,0.010357335]]}
        125       {"probability":[[5.0688627E-9,0.0036252008,0.9963748]]}
         90       {"probability":[[6.0868737E-5,0.9305012,0.06943793]]}
         95       {"probability":[[4.43892E-5,0.98495364,0.015002]]}
        100       {"probability":[[5.467016E-5,0.99671644,0.0032288947]]}
        130       {"probability":[[2.5530914E-8,0.9915139,0.008486167]]}
        135       {"probability":[[1.6936058E-7,0.55152786,0.44847193]]}
        140       {"probability":[[4.6395296E-9,0.004772966,0.995227]]}
         25       {"probability":[[0.99771667,0.0022833364,2.1570362E-11]]}
        110       {"probability":[[5.827173E-11,8.144908E-5,0.9999186]]}
        145       {"probability":[[1.7500341E-11,3.8031712E-6,0.9999962]]}
        150       {"probability":[[2.2181743E-7,0.011317454,0.9886824]]}
         35       {"probability":[[0.999882,1.17950236E-4,2.4415578E-10]]}
         50       {"probability":[[0.99997914,2.0821832E-5,3.7522135E-11]]}
        105       {"probability":[[3.3467944E-11,2.2144119E-5,0.9999778]]}