--out_nodes

Description

Specifies output nodes (operators) of a network model or specifies the names of the outputs of a network model.

If the output nodes are not specified, the output layer of the model is used by default. If they are specified, information of the specified operators is output. To check the parameters of a specific operator layer, mark the operator layer so that this operator layer is specified as the output nodes. After the model is converted, you can view the parameter settings of the specified operator at the end of the .om model file or the .json file converted from the .om model file.

See Also

When --framework is set to 1, this option is invalid in the MindSpore framework, but the model will be successfully converted.

Argument

Argument:

• Node names (node_name) in the network model.

  Enclose all output nodes in double quotation marks ("") and separate the nodes with semicolons (;). node_name must be the node name in the original model. The number after the colon indicates the output index. For example, node_name1:0 indicates output 0 of the node named node_name1.

• Top names (topname) of a layer (Caffe network only).

  Enclose all output nodes in double quotation marks ("") and separate the nodes with semicolons (;). The argument must be top names of a layer on the Caffe network before model build. If multiple layers have the same topname, the topname of the output layer is used.

• Names of network model outputs. (Applicable only for ONNX network models.)

  Enclose names of network model outputs in double quotation marks (""), and separate output names with semicolons (;). output must be the output of the network model.

Restrictions:

1. The passed argument is one of the preceding arguments.
2. Only Caffe networks support top names argument.
3. Only ONNX networks support output names argument.

Suggestions and Benefits

None

Example

• Node names (node_name) in the network model.

  --out_nodes="node_name1:0;node_name1:1;node_name2:0"

• Top names (topname) of a layer

  --out_nodes="topname0;topname1;topname2"

• Names of network model outputs.

  --out_nodes="output1;output2;output3"

Applicability

Atlas 200/300/500 Inference Product

Atlas Training Series Product

Dependencies and Restrictions

None