func.func @QuantizeUnidirectionalLstm(%arg0: tensor<1x2x3xf32>) -> (tensor<1x2x3xf32>) {
  %1 = "tfl.pseudo_const"() {value = dense<[[0.1]]> : tensor<1x1xf32>} : () -> tensor<1x1xf32>
  %2 = "tfl.pseudo_const"() {value = dense<[[0.2]]> : tensor<1x1xf32>} : () -> tensor<1x1xf32>
  %3 = "tfl.pseudo_const"() {value = dense<[[0.3]]> : tensor<1x1xf32>} : () -> tensor<1x1xf32>
  %4 = "tfl.pseudo_const"() {value = dense<[[0.4]]> : tensor<1x1xf32>} : () -> tensor<1x1xf32>

// CHECK-LABEL: main
func.func @main() -> tensor<3x2xi32> {
  // CHECK: "tfl.pseudo_const"() <{value = dense<0> : tensor<3x2xi32>}> {tfl.is_variable} : () -> tensor<3x2xi32>
  %0 = "tfl.pseudo_const"() {value = dense<0> : tensor<3x2xi32>, tfl.is_variable} : () -> tensor<3x2xi32> loc("variable")
  func.return %0 : tensor<3x2xi32>

  // CHECK-LABEL: testSingleLstm
  // CHECK-DAG:  %[[CST_0:.*]] = "tfl.pseudo_const"() <{value = dense<0.000000e+00> : tensor<4x4xf32>}> : () -> tensor<4x4xf32>
  // CHECK-DAG:  %[[CST_1:.*]] = "tfl.pseudo_const"() <{value = dense<0.000000e+00> : tensor<4x4xf32>}> : () -> tensor<4x4xf32>

  func.return %0 : tensor<1x512xf32>
}

// CHECK:       func @mean_4d_no_keepdim([[VAL_0:%.*]]: tensor<1x48x48x512xf32>) -> tensor<1x512xf32> {
// CHECK:           [[VAL_1:%.*]] = "tfl.pseudo_const"(){{.*}}dense<[1, 512]> : tensor<2xi32>

func.func @main() -> tensor<2x2xf32> {
  // CHECK: %[[cst:.*]] = "tfl.pseudo_const"() <{value = dense<2> : tensor<2xi32>}> : () -> tensor<2xi32>
  // CHECK: %{{.*}} = "tfl.reshape"(%{{.*}}, %[[cst]]) : (tensor<4xf32>, tensor<2xi32>) -> tensor<2x2xf32>
  %cst = arith.constant dense<[2, 2]> : tensor<2xi32>
  %0 = "tfl.pseudo_const" () {value = dense<1.0> : tensor<4xf32>} : () -> tensor<4xf32> loc("Const")

^bb0(%arg0: tensor<4xf32>):
  // CHECK:      [[CONST:%.*]] = "tfl.pseudo_const"() <{value = dense<1.000000e+00> : tensor<4xf32>}> : () -> tensor<4xf32>
  // CHECK-NEXT: [[SQDIFF:%.*]] = tfl.squared_difference %arg0, [[CONST]] : tensor<4xf32>
  // CHECK-NEXT: %{{.*}} = tfl.mul %arg0, [[SQDIFF]] {fused_activation_function = "NONE"} : tensor<4xf32>
  %0 = "tfl.pseudo_const" () {value = dense<1.0> : tensor<4xf32>} : () -> tensor<4xf32> loc("Const")

module {
func.func @add(%arg0: tensor<3x2xf32>) -> tensor<3x2xf32> attributes {tf.entry_function = {inputs = "serving_default_x", outputs = "outputs"}} {
  %0 = "tfl.pseudo_const" () {value = dense<[[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]]> : tensor<3x2xf32>} : () -> tensor<3x2xf32>
  %1 = "tfl.add" (%0, %arg0) {fused_activation_function = "NONE"} : (tensor<3x2xf32>, tensor<3x2xf32>) -> tensor<3x2xf32>

  // CHECK-SAME: tfl.schema_version = 3 : i32

  // CHECK:          %{{.*}} = "tfl.pseudo_const"() <{value = dense<{{\[\[1, 2\], \[3, 4\], \[5, 6\]\]}}> : tensor<3x2xi32>}>
  // CHECK-NEXT:     [[SUB:%.*]] = tfl.sub %{{.*}}, %{{.*}} {fused_activation_function = "RELU6"} : tensor<3x2xi32>
  // CHECK-NEXT:     [[SCALAR:%.*]] = "tfl.pseudo_const"() <{value = dense<10> : tensor<i32>}> : () -> tensor<i32>

  %0 = "tfl.pseudo_const"() {value = dense<["image/encoded", "image/text"]> : tensor<2x!tf_type.string>} : () -> tensor<2x!tf_type.string>
  %1 = "tfl.pseudo_const"() {value = dense<"image/encoded"> : tensor<1x!tf_type.string>} : () -> tensor<1x!tf_type.string>
  %2 = "tfl.pseudo_const"() {value = dense<"image/text"> : tensor<1x!tf_type.string>} : () -> tensor<1x!tf_type.string>

// RUN: json_to_flatbuffer %p/test_schema.fbs %s | flatbuffer_translate --tflite-flatbuffer-to-mlir -o - | FileCheck %s

// CHECK: %0 = "tfl.pseudo_const"() <{value = dense<2> : tensor<2xi32>}> : () -> tensor<2xi32>
// CHECK: %1 = "tfl.reshape"(%arg0, %0) : (tensor<1x4xf32>, tensor<2xi32>) -> tensor<2x2xf32>

{
  "version": 3,
  "operator_codes": [
    {
      "builtin_code": "RESHAPE"
    }
  ],
  "subgraphs": [
    {
      "tensors": [