--input_format

Description

Sets the model input format.

See Also

None

Arguments

Arguments:

• If the original framework is Caffe, the supported formats include NCHW (default) and ND (any format with N ≤ 4).
• If the original framework is ONNX, the supported formats include NCHW (default), NCDHW, and ND (any format with N ≤ 4).
• If the original framework is TensorFlow, the supported formats include NCHW, NHWC (default), ND, NCDHW, and NDHWC.
  • For a TensorFlow model converted using the ONNX model conversion tool, this option is required and the value must be NCHW.
  • If the original model contains an operator with the argument data_format, this option is required and ND is recommended. During tuning, the format is inferred based on the operator with data_format. If the input data format cannot be determined, ND is recommended.
• If the original framework is MindSpore, only the NCHW format is allowed.

Default: NCHW for Caffe and ONNX; NHWC for TensorFlow

Restrictions:

• If AIPP is enabled during tuning and the value of --input_format is not NHWC, --input_format does not take effect. Because if AIPP is enabled during tuning, the data format of the input node connected to AIPP must be NHWC during inference.
• If --insert_op_conf is configured at the same time, --input_format can only be set to NCHW or NHWC.

Suggestions and Benefits

None

Examples

--input_format=NCHW

Dependencies and Restrictions

None