Cannot create ConcatV2. Missing or invalid attribute axis

[silppuri]

I get the following error when converting the graph containing a concat node with axis int_value greater than 2.

fatal error: Cannot create ConcatV2. Missing or invalid attribute axis.: file <omited>/Pods/MetalBender/Sources/Adapters/Tensorflow/TFConverter+Mappers.swift, line 162

And the node in question from the .pbtxt:

node {
  name: "fire2/concat/concat/axis"
  op: "Const"
  attr {
    key: "dtype"
    value {
      type: DT_INT32
    }
  }
  attr {
    key: "value"
    value {
      tensor {
        dtype: DT_INT32
        tensor_shape {
        }
        int_val: 3
      }
    }
  }
}

And if I follow correctly the code it executes the LayerConverter+Mappers.swift calls the LayerSize.fromTf with the value 3. which in return is as follow:

    static func fromTF(index: Int) -> LayerSizeAxis? {
        switch index {
        case 0:
            return .w
        case 1:
            return .h
        case 2:
            return .f
        default:
            return nil
        }
    }
}

This evaluates as nil and throws an error.

Is there an error with the graph I'm trying to convert or is a bug in the Bender that it does not support concat indexes beyond axis=2 on a concat layer?

Environment:

• Xcode 8.3.3,
• iOS: 10.3.2,
• SDK version: 10.3

[bryant1410]

Bender, as it's based on MPSImage, doesn't support tensors with more than 3 dimensions. What is the shape of the input tensor of the concat?

[silppuri]

Ah ok good to know! I'm totally new to the iOS development and tipping my toes around to see what fits my project and Bender seems to be a nice API for the iOS ML projects.
Are there any "hacks" to bypass the limitation of three dimensions?

The tensors to be concatenated have shapes like [64,63,128,64] and [128,63,128,64]. This is an inception fire module I'm trying to implement. (An example is of the concat operation )