-1

I am using the Intel OpenVINO 2022.1 on Windows OS for my project. I am trying to convert the input data shape of the vgg16 CNN model from [1,3,224,224] to [2,3,300,300]. I tried to use the following command:

mo --input_model <path_to_model_directory>\vgg16.caffemodel --input data --input_shape [2,3,300,300] -o <path_to_vgg16_fp32_optimized_model_directory>

I went through the online documentation and followed every step. However, it showed me errors. I don't know what's happening. The first error is 'Cannot infer shapes or values for node "fc6/WithoutBiases". What does it mean? OpenVINO supports Fully Connected layers, doesn't it? Can you guys please help me out? Thanks!

Md Maksud-Ul-Kabir Rico
  • 1
  • 1

1 Answers1

0

The vgg16 model is trained with a specific size and it is unable to reshape with Model Optimizer operation. For a custom input shape, you have to preprocess the image before running inference. Refer to Resizing Image for the preprocessing API details.

Aznie_Intel
  • 101
  • 3