// CHECK-SAME: batch_group_count = 1
  // CHECK-SAME: feature_group_count = 2

  %0 = "tf.Conv2D"(%arg0, %arg1) {data_format = "NHWC", dilations = [1, 2, 3, 1], padding = "SAME", strides = [1, 4, 5, 1]} : (tensor<256x32x32x6xf32>, tensor<3x3x3x16xf32>) -> tensor<256x8x7x16xf32>
  func.return %0 : tensor<256x8x7x16xf32>
}

// -----

     IsIntList1XY1:$strides,
     BoolAttr:$use_cudnn_on_gpu,
     IsSameOrValid:$padding,
     I64ArrayAttr:$explicit_paddings,
     IsDataFormatNHWC:$data_format,
     IsAllOnes:$dilations),
  (TFL_TransposeConvOp $input_sizes,
     (TFL_TransposeOp $filter,
       (Arith_ConstantOp ConstantAttr<I32VectorElementsAttr<4>, "{2, 0, 1, 3}">)),
     $out_backprop,
     /*bias=*/ (CreateNoneValue $input_sizes),

        verify_size(window_strides.size(), "window strides") &&
        verify_size(padding.size(), "padding entries") &&
        verify_size(lhs_dilation.size(), "lhs dilation factors") &&
        verify_size(rhs_dilation.size(), "rhs dilation factors")))
    return std::nullopt;

  xla::Window window;
  for (size_t i = 0; i < window_dimensions.size(); i++) {
    auto dim = window.add_dimensions();

  %1 = "tf.Const"() {value = dense<1.000000e+00> : tensor<1x520x520x1xf32>} : () -> tensor<1x520x520x1xf32>
  %2 = "tf.DepthwiseConv2dNative"(%1, %0) {data_format = "NHWC", device = "", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "SAME", strides = [1, 1, 1, 1]} : (tensor<1x520x520x1xf32>, tensor<3x3x1x1xf32>) -> tensor<1x520x520x1xf32>
  func.return %2 : tensor<1x520x520x1xf32>

  // CHECK: tf.Const

    Arg<TF_I32OrI64Tensor, [{the padding to apply at the start and end of each input dimensions}]>:$padding,
    Arg<TF_I32OrI64Tensor, [{dilation to apply between input elements}]>:$lhs_dilation,
    Arg<TF_I32OrI64Tensor, [{dilation to apply between kernel elements}]>:$rhs_dilation,
    Arg<TF_I32OrI64Tensor, [{number of feature groups for grouped convolution.}]>:$feature_group_count,

      TCresVTEtIsSameAsOpBase<0, 2>>,
    Pure]> {
  let summary = "Dilation operator";

  let description = "Extends a tensor by adding new elements between the existing ones.";

  let arguments = (ins
     TFL_TensorOf<[I8, I16, I32, I64, UI8, UI16, UI32, UI64, F32, F64]>:$input,
     TFL_TensorOf<[I32]>:$dilations,
     TFL_0DTensorOf<[I8, I16, I32, I64, UI8, UI16, UI32, UI64, F32, F64]>:$padding_value
  );

    // CHECK: tf.Conv2DBackpropInput
    // CHECK-SAME: (tensor<4xi32>, tensor<3x3x32x64xf32>, tensor<200x24x24x64xf32>) -> tensor<200x26x26x32xf32>
    %1 = "tf.Conv2DBackpropInput"(%0, %arg0, %arg1) {data_format = "NHWC", dilations = [1, 1, 1, 1], explicit_paddings = [], padding = "VALID", strides = [1, 1, 1, 1], use_cudnn_on_gpu = true} : (tensor<4xi32>, tensor<3x3x32x64xf32>, tensor<200x24x24x64xf32>) -> tensor<?x?x?x?xf32>
    func.return %1 : tensor<?x?x?x?xf32>

        *   (since v2.7) `tf.math.bincount`
        *   (since v2.7) `tf.nn.depthwise_conv2d` backprop to `filter` when not
            using cuDNN convolution
        *   (since v2.7) `tf.nn.dilation2d` gradient
        *   (since v2.7) `tf.nn.max_pool_with_argmax` gradient
        *   (since v2.7) `tf.raw_ops.DebugNumericSummary` and
            `tf.raw_ops.DebugNumericSummaryV2`