EPContext

 Parameters : cluster,

embed_mode : boolean, if true, indicate ep_cache_context is the context content. Else indicate ep_cache_context is the file path to the context content.The path is relative to this Onnx file.
Default value “False”.
ep_cache_context : string, payload of the execution provider context if embed_mode=1, or path to the context file if embed_mode=0.
ep_sdk_version : string, SDK version used to convert the model.
hardware_architecture : string, hardware architecture.
main_context : boolean, usually each single EPContext associate with a graph partition.But for some case like QNN, it has single EPContext contains all partitions. In that case, the node with ep_cache_context should set main_context=true. Other nodes set main_context=false and skip ep_cache_context. The path is relative to this Onnx file.
Default value “False”.
notes : string, some notes for the model.
onnx_model_filename : string, filename of the original ONNX model.
partition_name : string, partitioned graph name.
source : string, the source used to generate the engine/context cache file. Ort EP or native SDK tool chain.
 training? : boolean, whether the layer is in training mode (can store data for backward).
Default value “True”.
 lda coeff : float, defines the coefficient by which the loss derivative will be multiplied before being sent to the previous layer (since during the backward run we go backwards).
Default value “1”.

 name (optional) : string, name of the node.