// 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});

      });
    }
    filter_value = filter.getValue();
    mul_value = multiplier.getValue();
    // In MHLO, Conv filter is in HWIO format, Depthwise conv filter is in HW1O
    // format and backprop input conv filter is in HWOI format.
    // Only fuses multiplier if all dimensions other than the out channel
    // dimension are equal to 1.
    if (!TFL::IsDimensionsDegenerateExceptLastOne(

    // CHECK: %[[BACKPROP:.*]] = "tf.Conv2DBackpropFilter"
    // CHECK-SAME: strides = [1, 1, 1, 1]
    // CHECK-SAME: (tensor<2x115x115x12xf32>, tensor<4xi32>, tensor<2x112x112x64xf32>) -> tensor<4x4x12x64xf32>

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

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

                                        {dx, dy, dz}, &grad_outputs));
    }
  }
  CompareTestAndExpectedGraphs();
}

TEST_F(GradientsTest, StackUnstack_StopBackprop) {
  // Tests that backprop stops before calculating gradients for Stack (because
  // only gradients w.r.t the output of Stack are requested).
  for (const bool expected : {false, true}) {
    const Scope& scope = expected ? scope_expected_ : scope_test_;

      Add(params_->body_inputs[0], {one, 0}, params_->body_graph, s_);
  ASSERT_EQ(TF_OK, TF_GetCode(s_)) << TF_Message(s_);
  params_->body_outputs[0] = {add, 0};

  ExpectOK();

  // Create backprop graph
  TF_Output grad_output;
  TF_AddGradients(graph_, outputs_.data(), outputs_.size(), inputs_.data(), 1,
                  nullptr, s_, &grad_output);
  ASSERT_EQ(TF_OK, TF_GetCode(s_)) << TF_Message(s_);

      Value scratch2 =
          ApplyReduction(loc, weighted_grad, reduce_dims, &rewriter);

      // x_backprop = y_backprop * (scale * scratch1)
      auto scaled_grad =
          rewriter.create<mhlo::MulOp>(loc, op.getScale(), scratch1);
      x_backprop = rewriter.create<mhlo::MulOp>(
          loc, grad,
          Broadcast1DToFeatureDim(loc, act, scaled_grad, feature_dim,