}

// CHECK-LABEL: conv2d_backprop_input_with_add
func.func @conv2d_backprop_input_with_add(%arg0: tensor<4xi32>, %arg1: tensor<3x3x1x32xf32>, %arg2: tensor<15x14x14x32xf32>) -> tensor<15x28x28x1xf32> {
  %0 = "tf.Conv2DBackpropInput"(%arg0, %arg1, %arg2) {strides = [1, 2, 2, 1], padding="SAME", dilations=[1, 1, 1, 1]}: (tensor<4xi32>, tensor<3x3x1x32xf32>, tensor<15x14x14x32xf32>) -> tensor<15x28x28x1xf32>

}

// CHECK-LABEL: conv2d_backprop_input_with_add
func.func @conv2d_backprop_input_with_add(%arg0: tensor<4xi32>, %arg1: tensor<3x3x1x32xf32>, %arg2: tensor<15x14x14x32xf32>) -> tensor<15x28x28x1xf32> {
  %0 = "tf.Conv2DBackpropInput"(%arg0, %arg1, %arg2) {strides = [1, 2, 2, 1], padding="SAME", dilations=[1, 1, 1, 1]}: (tensor<4xi32>, tensor<3x3x1x32xf32>, tensor<15x14x14x32xf32>) -> tensor<15x28x28x1xf32>

  TF_RETURN_IF_ERROR(GetNodeAttr(attrs, "use_cudnn_on_gpu", &use_cudnn_on_gpu));
  auto dx_1 = Conv2DBackpropInput(scope, Shape(scope, op.input(0)), op.input(1),
                                  grad_inputs[0], strides, padding,
                                  Conv2DBackpropInput::DataFormat(data_format)
                                      .UseCudnnOnGpu(use_cudnn_on_gpu));
  grad_outputs->push_back(dx_1);

  %input_size:   tensor<4xi32>,
  %filter:       tensor<1x28x28x64xf32>,
  %out_backprop: tensor<1x28x28x64xf32>
) -> tensor<1x28x28x64xf32> {

  // CHECK: "tf.Conv2DBackpropInput"
  // CHECK-SAME: data_format = "NCHW"
  %0 = "tf.Conv2DBackpropInput"(%input_size, %filter, %out_backprop)
       {
         data_format = "NHWC",
         padding = "VALID",
         strides = [1, 1, 1, 1]

  %input_size:   tensor<4xi32>,
  %filter:       tensor<1x28x28x64xf16>,
  %out_backprop: tensor<1x28x28x64xf16>
) -> tensor<1x28x28x64xf16> {

  // CHECK: "tf.Conv2DBackpropInput"
  // CHECK-SAME: data_format = "NCHW"
  %0 = "tf.Conv2DBackpropInput"(%input_size, %filter, %out_backprop)
       {
         data_format = "NHWC",
         padding = "VALID",
         strides = [1, 1, 1, 1]

 _Retval 2
cluster 0 size 2178
 Add 17
 AddN 72
 ArgMax 1
 AssignAddVariableOp 1
 AssignSubVariableOp 106
 BiasAdd 1
 BiasAddGrad 1
 Cast 3
 Const 357
 Conv2D 53
 Conv2DBackpropFilter 53
 Conv2DBackpropInput 52
 DivNoNan 1
 Equal 1
 FusedBatchNorm 53
 FusedBatchNormGrad 53
 Identity 2
 MatMul 3
 MaxPool 1
 MaxPoolGrad 1
 Mean 1
 Mul 164
 Pad 1
 ReadVariableOp 646
 Relu 49
 ReluGrad 49

 _Arg 435
 _Retval 2
cluster 0 size 1910
 Add 16
 AddN 71
 ArgMax 1
 AssignAddVariableOp 1
 BiasAdd 1
 BiasAddGrad 1
 Cast 115
 Const 407
 Conv2D 53
 Conv2DBackpropFilter 53
 Conv2DBackpropInput 52
 Equal 1
 FusedBatchNormGradV2 53
 FusedBatchNormV2 53
 MatMul 3
 MaxPool 1
 MaxPoolGrad 1
 Mean 1
 Mul 218
 Pad 2
 ReadVariableOp 538
 Relu 49
 ReluGrad 49
 Reshape 2

  // CHECK: %[[ARG_PERM:.*]] = "tf.Const"() <{value = dense<[0, 3, 1, 2]> : tensor<4xi64>}>
  // CHECK: %[[OUT_BP_TRANSPOSE:[0-9]*]] = "tf.Transpose"(%arg2, %[[ARG_PERM]])

  // CHECK: %[[CONV2D_BACKPROP:[0-9]*]] = "tf.Conv2DBackpropInput"
  // CHECK-SAME: (%[[INPUT_PERM]], %arg1, %[[OUT_BP_TRANSPOSE]])
  // CHECK-SAME: data_format = "NCHW"
  // CHECK-SAME: dilations = [1, 4, 2, 3]
  // CHECK-SAME: explicit_paddings = [1, 2, 7, 8, 3, 4, 5, 6]

  }
  attr {
    key: "index"
    value {
      i: 1
    }
  }
}
node {
  name: "training/LossScaleOptimizer/gradients/res5c_branch2c_1/Conv2D_grad/Conv2DBackpropInput"
  op: "Conv2DBackpropInput"
  input: "ConstantFolding/training/LossScaleOptimizer/gradients/res5c_branch2c_1/Conv2D_grad/ShapeN-matshapes-0"
  input: "res5c_branch2c_1/Conv2D/Cast"

    }
  }
  attr {
    key: "use_nesterov"
    value {
      b: false
    }
  }
}
node {
  name: "training/SGD/gradients/res5c_branch2c_1/Conv2D_grad/Conv2DBackpropInput"
  op: "Conv2DBackpropInput"
  input: "training/SGD/gradients/res5c_branch2c_1/Conv2D_grad/ShapeN"
  input: "res5c_branch2c_1/Conv2D/ReadVariableOp"