// CHECK-NEXT:}

  %0 = "tfl.pseudo_qconst"() { qtype = tensor<3x!quant.uniform<i8:f32, 0.1>>, value = dense<2> : tensor<3xi8>} : () -> tensor<3x!quant.uniform<i8:f32, 0.1>>
  %1 = "tfl.mul"(%arg0, %0) {fused_activation_function = "NONE"} : (tensor<3x!quant.uniform<i8:f32, 0.1>>, tensor<3x!quant.uniform<i8:f32, 0.1>>) -> tensor<3x!quant.uniform<i8:f32, 0.1>> loc("mul")
  func.return %1 : tensor<3x!quant.uniform<i8:f32, 0.1>>

  // CHECK-NEXT:}

  %0 = "tfl.pseudo_qconst"() { qtype = tensor<3x!quant.uniform<i8:f32, 1.0>>, value = dense<2> : tensor<3xi8>} : () -> tensor<3x!quant.uniform<i8:f32, 1.0>>
  %1 = "tfl.mul"(%arg0, %0) {fused_activation_function = "NONE"} : (tensor<3x!quant.uniform<i8:f32, 1.0>>, tensor<3x!quant.uniform<i8:f32, 1.0>>) -> tensor<3x!quant.uniform<i8:f32, 1.0>> loc("mul")
  func.return %1 : tensor<3x!quant.uniform<i8:f32, 1.0>>

  int num_retvals = 1;
  return op_ptr->Execute(absl::MakeSpan(output, 1), &num_retvals);
}

// Op: IdentityN()
// Summary: Returns a list of tensors with the same shapes and contents as the
// input
//
// Description:
//   tensors.
//
//   This op can be used to override the gradient for complicated functions. For
//   example, suppose y = f(x) and we wish to apply a custom function g for

  %0 = "tfl.transpose_conv"(%arg0, %arg1, %arg2, %cst) {padding = "SAME", stride_h = 2 : i32, stride_w = 2 : i32, fused_activation_function = "NONE"} : (tensor<4xi32>, tensor<32x4x4x128xf32>, tensor<1x32x42x128xf32>, none) -> tensor<1x64x84x32xf32>
  func.return %0 : tensor<1x64x84x32xf32>

def _contains_tensor(sample: repr_dataset.RepresentativeSample) -> bool:
  """Determines whether `sample` contains any tf.Tensors.

  Args:
    sample: A `RepresentativeSample`.

  Returns:
    True iff `sample` contains at least tf.Tensors.
  """
  return any(map(lambda value: isinstance(value, core.Tensor), sample.values()))


class RepresentativeDatasetTest(test.TestCase):
  """Tests functions for representative datasets."""

class XlaComputationLaunchContext {
 public:
  // Create a new launch context. 'allocate_xla_tensors' is true if allocated
  // output tensors and variables are always XlaTensors. If false they are
  // assumed to be "normal" device pointers.
  // If 'use_multiple_streams' is true, tensors may be defined and used on
  // multiple streams and so se::Events must be defined and waited for. If

  %0 = "tfl.pseudo_const" () {value = dense<1.0> : tensor<4xf32>} : () -> tensor<4xf32> loc("Const")
  %1 = "tfl.mul"(%arg0, %0) {fused_activation_function = "NONE"} : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32> loc("mul")
  // tf.MyCustomOp is the result of conversion to a Custom op
  %2 = "tf.MyCustomOp"(%1, %0) {fused_activation_function = "RELU", int_attr = 2 : i32}  : (tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32> loc("MyCustomOp")

// CHECK-EMPTY:

^bb0(%arg0: tensor<4 x f32>, %arg1: tensor<4 x f32>, %arg2: tensor<4 x f32>, %arg3: tensor<4 x f32>):
  %0 = "tfl.pseudo_const" () {value = dense<0.0> : tensor<4xf32>} : () -> tensor<4xf32> loc("Const")
  %1 = "tfl.svdf"(%arg0, %arg1, %arg2, %arg3, %0) {fused_activation_function = "RELU", rank = 2 : i32} : (tensor<4xf32>, tensor<4xf32>, tensor<4xf32>, tensor<4xf32>, tensor<4xf32>) -> tensor<4xf32>
  func.return %1 : tensor<4xf32>

// CHECK-EMPTY:

^bb0(%arg0: tensor<4 x f32>, %arg1: tensor<4 x f32>, %arg2: tensor<4 x f32>, %arg3: tensor<4 x f32>):
  %0 = "tfl.pseudo_const" () {value = dense<0.0> : tensor<4x4xf32>} : () -> tensor<4x4xf32> loc("Const")
  %1 = "tfl.unidirectional_sequence_rnn"(%arg0, %arg1, %arg2, %arg3, %0) {fused_activation_function = "TANH", time_major = true} : (tensor<4xf32>, tensor<4xf32>, tensor<4xf32>, tensor<4xf32>, tensor<4x4xf32>) -> tensor<4xf32>

SparseTensor is not supported. The return value of the decorated function
must be a Tensor or a list/tuple of Tensors.
  }];

  let arguments = (ins
    Arg<Variadic<TF_Tensor>, [{The tensors to be batched.}]>:$in_tensors,
    Arg<Variadic<TF_Tensor>, [{The tensors which are captured in the function, and don't need
to be batched.}]>:$captured_tensors,

    SymbolRefAttr:$f,
    I64Attr:$num_batch_threads,