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

  // CHECK: %[[RES_TPOSE:[0-9]*]] = "tf.Transpose"
  // CHECK-SAME: (%x_backprop, %[[RES_PERM]])
  // CHECK: return %[[RES_TPOSE]]

  %x_backprop, %scale_backprop, %offset_backprop, %reserve_1, %reserve_2
    = "tf.FusedBatchNormGradV3"(%arg0, %arg1, %arg2, %arg2, %arg2, %arg2)
       {
         data_format = "NHWC",

    absl::Span<AbstractTensorHandle*> outputs) {
  AbstractTensorHandle* loss;
  AbstractTensorHandle* backprop;
  TF_RETURN_IF_ERROR(ops::SparseSoftmaxCrossEntropyWithLogits(
      ctx, inputs[0], inputs[1], &loss, &backprop,
      "SparseSoftmaxCrossEntropyWithLogits"));
  // `gradient_checker` only works with model that returns only 1 tensor.

//
Status SparseSoftmaxCrossEntropyWithLogits(AbstractContext* ctx, AbstractTensorHandle* const features, AbstractTensorHandle* const labels, AbstractTensorHandle** loss, AbstractTensorHandle** backprop, const char* name = nullptr, const char* raw_device_name = nullptr);

//

// Summary:
//
// Description:
Status SparseSoftmaxCrossEntropyWithLogits(AbstractContext* ctx, AbstractTensorHandle* const features, AbstractTensorHandle* const labels, AbstractTensorHandle** loss, AbstractTensorHandle** backprop, const char* name, const char* raw_device_name) {
  AbstractOperationPtr op_ptr(ctx->CreateOperation());
  TF_RETURN_IF_ERROR(op_ptr->Reset("SparseSoftmaxCrossEntropyWithLogits", raw_device_name));

// computes loss and backprop of the loss with respect to 'features'.
//
// Softmax cross entropy loss is defined as follows:
//
//  loss = Sum(-labels * Log(Exp(features) / Sum(Exp(features)))
//  loss = Sum(-labels * LogSoftmax(features))
//
// Computing gradient of the loss with respect to features gives us,
//
//  backprop = (Exp(features) / Sum(Exp(features))) - labels

//   backprop such that dx = g(dy). In Python,
//
//   ```python
//   with tf.get_default_graph().gradient_override_map(
//       {'IdentityN': 'OverrideGradientWithG'}):
//     y, _ = identity_n([f(x), x])
//
//   @tf.RegisterGradient('OverrideGradientWithG')
//   def ApplyG(op, dy, _):
//     return [None, g(dy)]  # Do not backprop to f(x).
//   ```
Status IdentityN(AbstractContext* ctx,

// any gradients to be computed).
//
// Finally, we start a backprop stack with a set of tape entries for which we
// have all gradients available. This set usually is a subset of the set of
// targets (not all since targets which have outputs in the tape will not have
// gradients available initially).
//
// Then we repeatedly pop an entry from the stack, run its backprop, and update

    // CHECK: %[[offset_backprop:.*]] = mhlo.convert %[[red2]] : tensor<8xf32>

    // CHECK: %[[x_backprop:.*]] = mhlo.convert %[[mul3]] : tensor<8x8x8x8xf32>
    // CHECK: return %[[x_backprop]] : tensor<8x8x8x8xf32>

s":" ","--tw-backdrop-contrast":" ","--tw-backdrop-grayscale":" ","--tw-backdrop-hue-rotate":" ","--tw-backdrop-invert":" ","--tw-backdrop-opacity":" ","--tw-backdrop-saturate":" ","--tw-backdrop-sepia":" "}),e({".backdrop-filter":{"@defaults backdrop-filter":{},"backdrop-filter":Fe},".backdrop-filter-none":{"backdrop-filter":"none"}})},transitionProperty:({matchUtilities:i,theme:e})=>{let t=e("transitionTimingFunction.DEFAULT"),r=e("transitionDuration.DEFAULT");i({transition:n=>({"transition-pr...

  auto y =
      tensorflow::ops::SoftmaxCrossEntropyWithLogits(scope_, logits, labels);
  // Note the reversal of the backprop and loss orders. Issue #18734 has been
  // opened for this.
  RunTest({logits, labels}, {logits_shape, logits_shape}, {y.backprop, y.loss},
          {logits_shape, loss_shape});
}

TEST_F(NNGradTest, LogSoftmaxGrad) {
  TensorShape shape({5, 3});