6
C = torch.cat((A,B),1)

shape of tensors: 

A is (1, 128, 128, 256)
B is (1, 1, 128, 256)

Expected C value is (1, 129, 128, 256)

This code is working on pytorch, but while converting to core-ml it gives me below error:

"Error while converting op of type: {}. Error message: {}\n".format(node.op_type, err_message, )
TypeError: Error while converting op of type: Concat. Error message: unable to translate constant array shape to CoreML shape"
mudin
  • 2,672
  • 2
  • 17
  • 45
xfarxod
  • 123
  • 2
  • 6

1 Answers1

0

It was coremltools version related issue. Tried with latest beta coremltools 3.0b2.

Following works without any error with latest beta.

import torch

class cat_model(torch.nn.Module):
    def __init__(self):
        super(cat_model, self).__init__()

    def forward(self, a, b):
        c = torch.cat((a, b), 1)
        # print(c.shape)
        return c

a = torch.randn((1, 128, 128, 256))
b = torch.randn((1, 1, 128, 256))

model = cat_model()
torch.onnx.export(model, (a, b), 'cat_model.onnx')

import onnx
model = onnx.load('cat_model.onnx')
onnx.checker.check_model(model)
print(onnx.helper.printable_graph(model.graph))

from onnx_coreml import convert
mlmodel = convert(model)
xfarxod
  • 123
  • 2
  • 6