coremltools convert imageType input shape format [batch_size, height, width, 3]

Question

Created Aug ’23

Replies 1

Boosts 0

Participants 2

I need to convert a Super Resolution model to a mlmodel, but the input shape of the model is designed in the format [batch_size, height, width, 3]. Then I will convert with the following code

 model = hub.load("https://tfhub.dev/captain-pool/esrgan-tf2/1")
 tf.saved_model.save(model, "esrgan_saved_model")

input_type = ct.ImageType(shape=(1 , 192, 192, 3),color_layout=ct.colorlayout.RGB)
output_type = ct.ImageType(color_layout=ct.colorlayout.RGB)
mlmodel = ct.convert(
                  './esrgan_saved_model',     
                  inputs=[input_type],
                  outputs=[output_type],
              source="tensorflow")

mlmodel.save('esrgan.mlmodel')

I got an error

 Shape of the RGB/BGR image output, must be of kind (1, 3, H, W), i.e., first two dimensions must be (1, 3)

ImageType only seems to support input and output from [batch_size, 3, height, width]. What should I do to convert the model of format [batch_size, height, width, 3] to mlmodel？

Boost

Answer 1

Pitetou OP

Aug ’23

There are a lot of model already converted to CoreML thanks to awesome: "John Rocky" MLBoy_DaisukeMajima Yours is already available. https://github.com/john-rocky/CoreML-Models

0