%1:2 = "tf.IteratorGetNext"(%arg4) {device = "/job:localhost/replica:0/task:0/device:CPU:0"} : (tensor<*x!tf_type.resource>) -> (tensor<2x224x224x3xf32>, tensor<2x1xf32>)

  // NOFOLD: %[[TRANSPOSE:[0-9]*]] = "tf.Transpose"(%arg0, %[[CST]]) : (tensor<?x224x224x3xf32>, tensor<4xi32>) -> tensor<?x3x224x224xf32>

  // Pad input with new paddings.
  // CHECK: %[[PAD:[0-9]*]] = "tf.Pad"(%arg0, %[[PADDINGS]])
  // CHECK-SAME: (tensor<?x224x224x3xf32>, tensor<4x2xi32>) -> tensor<?x230x230x3xf32>
  // NOFOLD: %[[PAD:[0-9]*]] = "tf.Pad"(%[[TRANSPOSE]], %[[PADDING]])

    ```mlir
    module {
      func @while_body {
        %input = "tf.IteratorGetNext"(...) {device = "/CPU:0"}: -> tensor<2x224x224x3xf32>
        %device_launch = "tf_device.cluster_func"(%input,...) {func = @_func,...)
        return ...
      }
      func @_func(%input: tensor<2x224x224x3xf32>, %filter: tensor<7x7x3x64xf32>) {

```mlir
module {
  func @while_body {
    %input = "tf.IteratorGetNext"(...) {device = "/CPU:0"}: -> tensor<2x224x224x3xf32>
    %device_launch = "tf_device.cluster_func"(%input,...) {func = @_func,...)
    return ...
  }
  func @_func(%input: tensor<2x224x224x3xf32>, %filter: tensor<7x7x3x64xf32>) {