Changing Input Shapes

OpenVINO™ enables you to change model input shape during the application runtime. It may be useful when you want to feed the model an input that has different size than the model input shape. The following instructions are for cases where you need to change the model input shape repeatedly.

Note

If you need to do this only once, prepare a model with updated shapes via Model Optimizer. For more information, refer to the Specifying –input_shape Command-line Parameter article.

The reshape method

The reshape method is used as ov::Model::reshape in C++ and Model.reshape in Python. The method updates input shapes and propagates them down to the outputs of the model through all intermediate layers. The code below is an example of how to set a new batch size with the reshape method:

model->reshape({8, 3, 448, 448});
model.reshape([8, 3, 448, 448])

The diagram below presents the results of using the method, where the size of model input is changed with an image input:

shape_inference_explained

When using the reshape method, you may take one of the approaches:

  1. You can pass a new shape to the method in order to change the input shape of the model with a single input. See the example of adjusting spatial dimensions to the input image:

        // Read an image and adjust models single input for image to fit
        cv::Mat image = cv::imread("path/to/image");
        model->reshape({1, 3, image.rows, image.cols});
    
    from cv2 import imread
    image = imread("path/to/image")
    model.reshape({1, 3, image.shape[0], image.shape[1]})
    

    To do the opposite - to resize input image to match the input shapes of the model, use the pre-processing API.

  2. You can express a reshape plan, specifying the input by the port, the index, and the tensor name:

    map<ov::Output<ov::Node>, ov::PartialShape specifies input by passing actual input port:

        std::map<ov::Output<ov::Node>, ov::PartialShape> port_to_shape;
        for (const ov::Output<ov::Node>& input : model->inputs()) {
            ov::PartialShape shape = input.get_partial_shape();
            // Modify shape to fit your needs
            // ...
            port_to_shape[input] = shape;
        }
        model->reshape(port_to_shape);
    

    openvino.runtime.Output dictionary key specifies input by passing actual input object. Dictionary values representing new shapes could be PartialShape:

    port_to_shape = dict()
    for input_obj in model.inputs:
        shape = input_obj.get_partial_shape()
        # modify shape to fit your needs
        # ...
        port_to_shape[input_obj] = shape
    model.reshape(port_to_shape)
    

    map<size_t, ov::PartialShape> specifies input by its index:

        size_t i = 0;
        std::map<size_t, ov::PartialShape> idx_to_shape;
        for (const ov::Output<ov::Node>& input : model->inputs()) {
            ov::PartialShape shape = input.get_partial_shape();
            // Modify shape to fit your needs
            // ...
            idx_to_shape[i++] = shape;
        }
        model->reshape(idx_to_shape);
    

    int dictionary key specifies input by its index. Dictionary values representing new shapes could be tuple:

    idx_to_shape = dict()
    i = 0
    for input_obj in model.inputs:
        shape = input_obj.get_partial_shape()
        # modify shape to fit your needs
        # ...
        idx_to_shape[i] = shape
        i += 1
    model.reshape(idx_to_shape)
    

    map<string, ov::PartialShape> specifies input by its name:

        std::map<std::string, ov::PartialShape> name_to_shape;
        for (const ov::Output<ov::Node>& input : model->inputs()) {
            ov::PartialShape shape = input.get_partial_shape();
            // input may have no name, in such case use map based on input index or port instead
            if (!input.get_names().empty()) {
            // Modify shape to fit your needs
            // ...
                name_to_shape[input.get_any_name()] = shape;
            }
        }
        model->reshape(name_to_shape);
    

    str dictionary key specifies input by its name. Dictionary values representing new shapes could be str:

    name_to_shape = dict()
    for input_obj in model.inputs:
        shape = input_obj.get_partial_shape()
        # input may have no name, in such case use map based on input index or port instead
        if len(input_obj.get_names()) != 0:
            # modify shape to fit your needs
            # ...
            name_to_shape[input_obj.get_any_name()] = shape
    model.reshape(name_to_shape)
    

You can find the usage scenarios of the reshape method in Hello Reshape SSD Samples.

Note

In some cases, models may not be ready to be reshaped. Therefore, a new input shape cannot be set neither with Model Optimizer nor the reshape method.

The set_batch method

The meaning of the model batch may vary depending on the model design. To change the batch dimension of the model, set the layout and call the set_batch method.

// Mark up batch in the layout of the input(s) and reset batch to the new value
model->get_parameters()[0]->set_layout("N...");
ov::set_batch(model, new_batch);
model.get_parameters()[0].set_layout(Layout("N..."))
set_batch(model, 5)

The set_batch method is a high-level API of the reshape functionality, so all information about the reshape method implications are applicable for set_batch too, including the troubleshooting section.

Once you set the input shape of the model, call the compile_model method to get a CompiledModel object for inference with updated shapes.

There are other approaches to change model input shapes during the stage of IR generation or model representation in OpenVINO Runtime.

Important

Shape-changing functionality could be used to turn dynamic model input into a static one and vice versa. Always set static shapes when the shape of data is NOT going to change from one inference to another. Setting static shapes can avoid memory and runtime overheads for dynamic shapes which may vary depending on hardware plugin and model used. For more information, refer to the Dynamic Shapes.

Additional Resources