Error: Cannot retrieve vector from IRValue format int32

[anhnd101]

🐞Describing the bug

I convert model to Coreml, model use this method:

def create_2d_sin_embedding(d_model, height, width, device="cpu", max_period=10000):
    """
    :param d_model: dimension of the model
    :param height: height of the positions
    :param width: width of the positions
    :return: d_model*height*width position matrix
    """
    if d_model % 4 != 0:
        raise ValueError("Cannot use sin/cos positional encoding with " "odd dimension (got dim={:d})".format(d_model))
    pe = torch.zeros(d_model, height, width)
    # Each dimension use half of d_model
    d_model = int(d_model / 2)
    div_term = torch.exp(torch.arange(0.0, d_model, 2) * -(math.log(max_period) / d_model))
    pos_w = torch.arange(0.0, width).unsqueeze(1)
    pos_h = torch.arange(0.0, height).unsqueeze(1)
    pe[0:d_model:2, :, :] = torch.sin(pos_w * div_term).transpose(0, 1).unsqueeze(1).repeat(1, height, 1)
    pe[1:d_model:2, :, :] = torch.cos(pos_w * div_term).transpose(0, 1).unsqueeze(1).repeat(1, height, 1)
    pe[d_model::2, :, :] = torch.sin(pos_h * div_term).transpose(0, 1).unsqueeze(2).repeat(1, 1, width)
    pe[d_model + 1 :: 2, :, :] = torch.cos(pos_h * div_term).transpose(0, 1).unsqueeze(2).repeat(1, 1, width)
    return pe[None, :].to(device)

It converted successful, but then I do the Init the model in XCode, it printed this error: Error: Cannot retrieve vector from IRValue format int32
I think it because this slice: [0:d_model:2, :, :],
Can someone help fix this ?

Paste Python code snippet here, complete with any required import statements.

- If the model conversion succeeds, but there is a numerical mismatch in predictions, please include the code used for comparisons.

## System environment (please complete the following information):
 - coremltools version: 8.1
 - MacOS

[YifanShenSZ]

Hi @anhnd101 could you please make your reproduce more complete?

Concretely, what you shared in PR description seems to be only a function coded in torch. Could you please share the entire export -> convert script, i.e. something like

import torch

import coremltools as ct


class Model(torch.nn.Module):
    def forward(self, ...):
        ...

model = Model()
model.eval()

example_inputs = ...
exported_program = torch.export.export(model, example_inputs)

mlmodel = ct.convert(exported_program)