rRedrawOverlay();if(!preventEvent)plot.getPlaceholder().trigger("plotunselected",[])}}function extractRange(ranges,coord){var axis,from,to,key,axes=plot.getAxes();for(var k in axes){axis=axes[k];if(axis.direction==coord){key=coord+axis.n+"axis";if(!ranges[key]&&axis.n==1)key=coord+"axis";if(ranges[key]){from=ranges[key].from;to=ranges[key].to;break}}}if(!ranges[key]){axis=coord=="x"?plot.getXAxes()[0]:plot.getYAxes()[0];from=ranges[coord+"1"];to=ranges[coord+"2"]}if(from!=null&&to!=null&&from>to){var...

}

inline bool IsUnknownDimOrRank(int64_t dim_or_rank) {
  return dim_or_rank == -1;
}

// Returns dimension index for the given TensorFlow axis that supports negative
// indexing.
inline int64_t GetDimForAxis(int64_t axis, int64_t rank) {
  return axis >= 0 ? axis : axis + rank;
}

// Returns the tf.Equal/tf.NotEqual result type given `x` and `y` and inputs. If

                $.each(plot.getXAxes(), function(_, axis) {
                    const opts = axis.options;
                    opts.min = reset ? null : ranges.xaxis.from;
                    opts.max = reset ? null : ranges.xaxis.to;
                });
                $.each(plot.getYAxes(), function(_, axis) {
                    const opts = axis.options;
                    opts.min = reset ? 0 : ranges.yaxis.from;

    %0 = "tfl.pack"(%arg0, %arg1) {axis = 0 : i32, values_count = 2 : i32} : (tensor<1xf32>, tensor<1xf32>) -> tensor<2x1xf32>
    func.return %0 : tensor<2x1xf32>
    // CHECK: %[[VAL_0:.*]] = arith.constant dense<[2, 1]> : tensor<2xi32>
    // CHECK: %[[CONCAT:.*]] = "tfl.concatenation"(%arg0, %arg1) <{axis = 0 : i32, fused_activation_function = "NONE"}> : (tensor<1xf32>, tensor<1xf32>) -> tensor<2xf32>

  }

  SmallVector<double, 4> scales;
  SmallVector<int64_t, 4> zeroPoints;
  scales.reserve(axisSize);
  zeroPoints.reserve(axisSize);
  for (size_t axis = 0; axis != axisSize; ++axis) {
    double rmin = rmins[axis];
    double rmax = rmaxs[axis];
    if (std::fabs(rmax - rmin) < std::numeric_limits<double>::epsilon()) {
      scales.push_back(1.0);
      zeroPoints.push_back(qmin);
      continue;
    }

  %2 = "tfl.add"(%arg0, %arg3) {fused_activation_function = "RELU6"} : (tensor<1xf32>, tensor<1xf32>) -> tensor<1xf32>
  %3 = "tfl.pack"(%1, %2) {axis = 0 : i32, values_count = 2 : i32} : (tensor<1xf32>, tensor<1xf32>) -> tensor<2x1xf32>
  func.return %3 : tensor<2x1xf32>
}

// CHECK: %[[CST:.*]] = arith.constant dense<1> : tensor<4xi32>

    func.func @main(%arg0: tensor<3x3x!tf_type.qint8>, %arg1: tensor<3x3x!tf_type.qint8>) -> tensor<6x3x!tf_type.qint8> {
      %axis = "tf.Const"() { value = dense<0> : tensor<i64> } : () -> tensor<i64>
      %1 = "tf.ConcatV2"(%arg0, %arg1, %axis) : (tensor<3x3x!tf_type.qint8>, tensor<3x3x!tf_type.qint8>, tensor<i64>) -> tensor<6x3x!tf_type.qint8>
      func.return %1 : tensor<6x3x!tf_type.qint8>
    }
  })";

             ">::Impl")>;

// Specify the operand index of the coefficient operand for an affine op
// and also the quantization dimension if per-axis quantization is support.
// If the quantization dimension is -1, per-axis quantization isn't supported.
class AffineOpCoefficient<int dim, int index> : NativeOpTrait<
  !strconcat("quant::AffineOpCoefficient<",
             !interleave([dim, index], ", "),

    Value operand = reduce_op.getInputs().front();
    int64_t axis = reduce_op.getDimensions().getValues<int64_t>()[0];

    auto dim_type = RankedTensorType::get({1}, rewriter.getI32Type());
    auto reduction_indices = rewriter.create<arith::ConstantOp>(
        reduce_op.getLoc(), dim_type,
        rewriter.getI32TensorAttr({static_cast<int32_t>(axis)}));

    // Generate a Max and an ArgMax of as the mhlo op returns both while in TF

      return emitOpError("layerStats must have shape [2]");
    }
  }
  // Verify axisStats (optional) attribute.
  if (getAxisStats()) {
    if (!getAxis()) return emitOpError("axis must be specified for axisStats");

    auto shape = tensorArg.getShape();
    auto argSliceSize =
        std::accumulate(std::next(shape.begin(), *getAxis()), shape.end(), 1,