Help Center/ Huawei HiLens/ FAQs/ FAQs/ Skill Development/ How Do I Determine the Input Tensor Shape During Model Conversion?
Updated on 2022-08-18 GMT+08:00

How Do I Determine the Input Tensor Shape During Model Conversion?

Mandatory. The shape of the input data, in the format of NHWC, for example, input_name:1,224,224,3. input_name must be a node name in the network model before model conversion, which must be configured when the model has dynamic shape input. For example, in input_name1:?,h,w,c, the question mark (?) indicates the batch size, that is, the number of images processed at a time. It is used to convert the original model with a dynamic shape into an offline model with a fixed shape.

Use commas to separate multiple inputs.

When a pb model is converted to an om model, the input tensor shape is the input node and shape of the pb model, for example, images:1,224,224,3.