--input_shape

Function Usage

Sets the shape of the model input. The shape must be the same as that of the input data after dataset processing.

See Also

Required if --evaluator is not included.

Argument

Argument: shape of each input.

Format: "input_name1:n1,c1,h1,w1;input_name2:n2,c2,h2,w2".

Remarks: If a model has multiple inputs, the specified nodes must be enclosed in double quotation marks ("") and separated by semicolons (;). input_name must be the node name in the network model before model conversion.

Suggestions and Benefits

None

Examples

--input_shape="input_name1:n1,c1,h1,w1;input_name2:n2,c2,h2,w2"

Constraints

• If the model input has a dynamic shape, for example, "input_name1:?,h,w,c" (where ? indicates the number of images per batch), the image number must be equal to that of the .bin dataset.
• This option is used only in PTQ scenarios.