%cst = arith.constant dense<[-1, -1, 4]> : tensor<3xi32>
  // expected-error @+1 {{tfl.reshape' op requires 'shape' to have at most one dynamic dimension, but got multiple dynamic dimensions at indices 0 and 1. You need to set up the unspecified size(s) to avoid this problem, for example,setting batch size in keras model or setting unspecified input size(s) with fixed ones.}}