TfLiteArmnnDelegate: Exception (FullyConnectedLayer: TensorShape set on OutputSlot[0] does not match the infer

[luchangli03]

terminating with uncaught exception of type armnn::Exception: TfLiteArmnnDelegate: Exception (FullyConnectedLayer: TensorShape set on OutputSlot[0] does not match the infer red shape. : [1,512,768] != [512,768]) caught from optimize. Aborted

model: FullyConnected with input shapes of [1,512,768] x [768,768]

[ArmRyan]

Hi @luchangli03 ,

What version of ArmNN/Compute Library are you using?

If you are using v22.05 or v22.08,

Could try this option:

     *    Option key: "allow-expanded-dims" \n
     *    Possible values: ["true"/"false"] \n
     *    Description: If true will disregard dimensions with a size of 1 when validating tensor shapes but tensor
     *                 sizes must still match. \n
     *                 This is an Experimental parameter that is incompatible with "infer-output-shape". \n
     *                 This parameter may be removed in a later update.

[luchangli03]

Hi @luchangli03 ,

What version of ArmNN/Compute Library are you using?

If you are using v22.05 or v22.08,

Could try this option:

     *    Option key: "allow-expanded-dims" \n
     *    Possible values: ["true"/"false"] \n
     *    Description: If true will disregard dimensions with a size of 1 when validating tensor shapes but tensor
     *                 sizes must still match. \n
     *                 This is an Experimental parameter that is incompatible with "infer-output-shape". \n
     *                 This parameter may be removed in a later update.

armnn-22.05.01

[ArmRyan]

Does the option mentioned in the comment above help fix the issue?

[FrancisMurtagh-arm]

Closing due to lack of activity, please reopen if you are still having the issue.

Thanks, Francis.