Proto and Serialization¶
Proto¶
AttributeProto¶
FunctionProto¶
GraphProto¶
MapProto¶
ModelProto¶
NodeProto¶
OperatorProto¶
OperatorSetIdProto¶
OperatorSetProto¶
OptionalProto¶
SequenceProto¶
SparseTensorProto¶
- class onnx.SparseTensorProto¶
- DESCRIPTOR = <google._upb._message.Descriptor object>¶
The
google.protobuf.descriptor.Descriptor
for this message type.
StringStringEntryProto
TensorProto¶
TensorShapeProto¶
TrainingInfoProto¶
TypeProto¶
- class onnx.TypeProto¶
- DESCRIPTOR = <google._upb._message.Descriptor object>¶
The
google.protobuf.descriptor.Descriptor
for this message type.
- class Map¶
- DESCRIPTOR = <google._upb._message.Descriptor object>¶
The
google.protobuf.descriptor.Descriptor
for this message type.
- class Opaque¶
- DESCRIPTOR = <google._upb._message.Descriptor object>¶
The
google.protobuf.descriptor.Descriptor
for this message type.
- class Optional¶
- DESCRIPTOR = <google._upb._message.Descriptor object>¶
The
google.protobuf.descriptor.Descriptor
for this message type.
- class Sequence¶
- DESCRIPTOR = <google._upb._message.Descriptor object>¶
The
google.protobuf.descriptor.Descriptor
for this message type.
ValueInfoProto¶
Serialization¶
Load a model¶
- onnx.load(f: Union[IO[bytes], str], format: Optional[Any] = None, load_external_data: bool = True) ModelProto ¶
Loads a serialized ModelProto into memory load_external_data is true if the external data under the same directory of the model and load the external data If not, users need to call load_external_data_for_model with directory to load
- Parameters:
f – can be a file-like object (has “read” function) or a string containing a file name
format – for future use
- Returns:
Loaded in-memory ModelProto
from onnx import load
onnx_model = load("model.onnx")
Or:
from onnx import load
with open("model.onnx", "rb") as f:
onnx_model = load(f)
Save a model¶
This ONNX graph needs to be serialized into one contiguous memory buffer. Method SerializeToString is available in every ONNX objects.
with open("model.onnx", "wb") as f:
f.write(onnx_model.SerializeToString())
This method has the following signature.
Load data¶
Data means here any type containing data including a model, a tensor, a sparse tensor…
- onnx.load_model_from_string(s: bytes, format: Optional[Any] = None) ModelProto [source]¶
Loads a binary string (bytes) that contains serialized ModelProto
- Parameters:
s – a string, which contains serialized ModelProto
format – for future use
- Returns:
Loaded in-memory ModelProto
- onnx.load_tensor_from_string(s: bytes, format: Optional[Any] = None) TensorProto [source]¶
Loads a binary string (bytes) that contains serialized TensorProto
- Parameters:
s – a string, which contains serialized TensorProto
format – for future use
- Returns:
Loaded in-memory TensorProto
protobuf does not store any information about the class of the saved data. Therefore, this class must be known before restoring an object.
Save data¶
Any Proto class includes a method called SerializeToString. It must be called to serialize any proto object into an array of bytes.