--is_input_adjust_hw_layout

Description

Sets the network input data type to float16 and data format to NC1HWC0 together with --input_fp16_nodes. Setting this option separately does not take effect, but the model will be successfully converted.

See Also

• Set --is_input_adjust_hw_layout to true and use this option together with --input_fp16_nodes. The node data type of the --input_fp16_nodes inputs is set to float16 and NC1HWC0, respectively.
• When --framework is set to 1, this option is invalid in the MindSpore framework, but the model will be successfully converted.

Argument

Argument: false or true

Default: false

Suggestions and Benefits

None

Example

atc --model=$HOME/module/resnet50_tensorflow*.pb --framework=3 --output=$HOME/module/out/tf_resnet50 --is_input_adjust_hw_layout=true  --input_fp16_nodes="data" --soc_version=<soc_version>

Applicability

Atlas 200/300/500 Inference Product

Atlas Training Series Product

Dependencies and Restrictions

None