--out_nodes

Applicable Products

All processors

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 outputs of intermediate-layer operators, use this option to specify the operators of a specific layer to be output during model conversion. After model conversion, information of the specified output operators is available at the end of the offline model file (.om). If such information cannot be retrieved from the offline model file (.om), convert the file into JSON format for inspection.

See Also

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

Arguments

Argument:

• Node names (node_name) in the network model

  If multiple output nodes are specified, their names must be enclosed in double quotation marks ("") and separated by 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 1 of the node named node_name1.

• Top names (topname) of specified output nodes (Caffe network models only)

  If multiple output nodes are specified, their top names must be enclosed in double quotation marks ("") and separated by semicolons (;). topname must be the top name of a layer in the Caffe network model before model build. If multiple layers have the same topname, topname of the last layer is used.

• Names (name) of network model outputs (ONNX network models only)

  If multiple outputs are specified, their names must be enclosed in double quotation marks ("") and separated by 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"

Dependencies and Restrictions

None