Constricted model types and software specifications

Constricted software specifications are only supported in an upgraded instance. They are not supported in new installations, imported space assets, and patch operations.

Support for the following software specifications is constricted:

List of constricted software specifications and model types
Framework Versions Model Type Default software specification Supported platforms
AutoAI 0.1 NA autoai-kb_rt22.1-py3.9
autoai-ts_rt22.1-py3.9
x86
AutoAI 0.1 NA autoai-kb_rt22.2-py3.10 (F)(deprecated)
autoai-ts_rt22.2-py3.10 (F)
x86. PPC, s390x
PyTorch 1.10 pytorch-onnx_1.10
pytorch-onnx_rt22.1
runtime-22.1-py3.9
pytorch-onnx_rt22.1-py3.9
pytorch-onnx_rt22.1-py3.9-edt
x86
PyTorch 1.12 pytorch-onnx_1.12
pytorch-onnx_rt22.2
runtime-22.2-py3.10 (F)pytorch-onnx_rt22.2-py3.10 (F)pytorch-onnx_rt22.2-py3.10-edt (F) x86. PPC, s390x
PyTorch 1.12 pytorch-onnx_1.12
pytorch-onnx_rt22.2(deprecated)
pytorch-onnx_rt22.2-py3.10-dist(x86) (F) x86(deprecated)
Python functions NA NA runtime-22.1-py3.9 x86
Python functions NA NA runtime-22.2-py3.10 (F) x86, PPC, s390x
Python Scripts NA NA runtime-22.1-py3.9 x86
Python scripts NA NA runtime-22.2-py3.10 (F) x86, PPC, s390x
R Scripts NA NA default_r3.6
runtime-22.1-r3.6
runtime-22.2-r4.2 (F)
x86
R Shiny applications NA NA shiny-r3.6 x86, PPC
R Shiny applications NA NA rstudio_r4.2 (deprecated) x86
Scikit-learn 1.0 scikit-learn_1.0 runtime-22.1-py3.9 x86
Scikit-learn 1.1 scikit-learn_1.1 runtime-22.2-py3.10 (F) x86, PPC, s390x
Tensorflow 2.7 tensorflow_2.7
tensorflow_rt22.1
runtime-22.1-py3.9
tensorflow_rt22.1-py3.9
x86
Tensorflow 2.9 tensorflow_2.9
tensorflow_rt22.2
runtime-22.2-py3.10 (F)
tensorflow_rt22.2-py3.10 (F)
x86, PPC, s390x
Tensorflow 2.9 tensorflow_2.9
4.8.4tensorflow_rt22.2
tensorflow_rt22.2-py3.10-dist(x86) (F)
tensorflow_rt22.2-py3.10-edt(x86) (F)(deprecated)
x86, s390x, PPC
XGBoost 1.5 xgboost_1.5 or scikit-learn_1.0 (see notes) runtime-22.1-py3.9 x86
XGBoost 1.6 xgboost_1.6 or scikit-learn_1.1 runtime-22.2-py3.10 (F) x86, s390x, PPC
Important:

For XGBoost, if model is trained with sklearn wrapper (XGBClassifier or XGBRegressor), use the scikit-learn_1.1 model type in Python 3.10.

Parent topic: Frameworks and software specifications in Watson Machine Learning