mindspore_lite.FmkType
- class mindspore_lite.FmkType[source]
When Converter, the FmkType is used to define Input model framework type.
Currently, the following model framework types are supported:
Definition
Description
FmkType.TF
TensorFlow model’s framework type, and the model uses .pb as suffix.
FmkType.CAFFE
Caffe model’s framework type, and the model uses .prototxt as suffix.
FmkType.ONNX
ONNX model’s framework type, and the model uses .onnx as suffix.
FmkType.MINDIR
MindSpore model’s framework type, and the model uses .mindir as suffix.
FmkType.TFLITE
TensorFlow Lite model’s framework type, and the model uses .tflite as suffix.
FmkType.PYTORCH
PyTorch model’s framework type, and the model uses .pt or .pth as suffix.
Examples
>>> # Method 1: Import mindspore_lite package >>> import mindspore_lite as mslite >>> print(mslite.FmkType.TF) FmkType.TF >>> # Method 2: from mindspore_lite package import FmkType >>> from mindspore_lite import FmkType >>> print(FmkType.TF) FmkType.TF