Extracting a feature map of Convolution layer by inputing differebt image size

[timosy]

I'd like to extract feature map from Convolution layer by inputting
larg

[IntelSupport · Accepted solution]

Hi hep77to,

Thanks for reaching out.

OpenVINO™ provides capabilities to change model input shape during the runtime. You can set a new input shape with the reshape method. Refer to Changing input shapes for the details. The reshape method is useful in case you would like to feed model an input that has different size than model input shape.

Apart from that, the Hello Reshape SSD C++ Sample demonstrates how to do synchronous inference of object detection models using input reshape feature. Below is the reshape method used in the sample:

/ Step 5. Reshape model to image size and batch size

       // assume model layout NCHW

       const ov::Layout model_layout{"NCHW"};

       ov::Shape tensor_shape = model->input().get_shape();

       size_t batch_size = 1;

       tensor_shape[ov::layout::batch_idx(model_layout)] = batch_size;

       tensor_shape[ov::layout::channels_idx(model_layout)] = image_channels;

       tensor_shape[ov::layout::height_idx(model_layout)] = image_height;

       tensor_shape[ov::layout::width_idx(model_layout)] = image_width;

       std::cout << "Reshape network to the image size = [" << image_height << "x" << image_width << "] " << std::endl;

       model->reshape({{model->input().get_any_name(), tensor_shape}});

       printInputAndOutputsInfo(*model);

Hope this helps.

Regards,

Aznie

[timosy]

Dear

IntelSupport

Community Manager

Nice infoamtion!

Thanks a lot.

[IntelSupport]

Hi hep77to,

This thread will no longer be monitored since this we have provided the information. If you need any additional information from Intel, please submit a new question.

Regards,

Aznie