update ops headers

4 years ago · d91cff537e
--- a/third_party/fwkacllib/inc/ops/all_ops.h
+++ b/third_party/fwkacllib/inc/ops/all_ops.h
@@ -31,9 +31,7 @@
 #include "functional_ops.h"
 #include "get_data_ops.h"
 #include "hcom_ops.h"
 #include "hvd_ops.h"
 #include "image_ops.h"
 #include "internal_ops.h"
 #include "linalg_ops.h"
 #include "logging_ops.h"
 #include "lookup_ops.h"
--- a/third_party/fwkacllib/inc/ops/array_ops.h
+++ b/third_party/fwkacllib/inc/ops/array_ops.h
@@ -1084,43 +1084,6 @@ REG_OP(TransShape)
    .ATTR(outShape,ListInt ,{})
    .OP_END_FACTORY_REG(TransShape);
 /**
 *@brief Computes the (possibly normalized) Levenshtein Edit Distance.
 *@par Inputs:
 *@li hypothesis_indices: The indices of the hypothesis list SparseTensor.\n
 This is an N x R int64 matrix.
 *@li hypothesis_shape: The values of the hypothesis list SparseTensor.\n
 This is an N-length vector.
 *@li hypothesis_shape: The shape of the hypothesis list SparseTensor.\n
 This is an R-length vector.
 *@li truth_indices: The indices of the truth list SparseTensor.\n
 This is an M x R int64 matrix.
 *@li truth_shape: The values of the truth list SparseTensor.\n
 This is an M-length vector.
 *@li truth_shape: The shape of the truth list SparseTensor.\n
 This is an R-length vector
 *@par Attributes:
 *@li normalize: boolean (if true, edit distances are normalized by length of truth).
 *@par Outputs:
 *@li output: A dense float tensor with rank R - 1.
 *@par Third-party framework compatibility
 * Compatible with TensorFlow EditDistance operator.
 */
 REG_OP(EditDistance)
    .INPUT(hypothesis_indices, TensorType({DT_INT64}))
    .INPUT(hypothesis_values, TensorType::BasicType())
    .INPUT(hypothesis_shape, TensorType({DT_INT64}))
    .INPUT(truth_indices, TensorType({DT_INT64}))
    .INPUT(truth_values, TensorType::BasicType())
    .INPUT(truth_shape, TensorType({DT_INT64}))
    .ATTR(normalize, Bool, true)
    .OUTPUT(output, TensorType({DT_FLOAT}))
    .OP_END_FACTORY_REG(EditDistance)
 }  // namespace ge
 #endif  // GE_OP_ARRAY_OPS_H_
--- a/third_party/fwkacllib/inc/ops/ctc_ops.h
+++ b/third_party/fwkacllib/inc/ops/ctc_ops.h
@@ -50,6 +50,7 @@ If not specified, defaults to true
 *@par Third-party framework compatibility
 * Compatible with TensorFlow CTCLoss operator.
 */
 REG_OP(CTCLoss)
    .INPUT(inputs, TensorType({DT_FLOAT, DT_DOUBLE}))
    .INPUT(labels_indices, TensorType({DT_INT64}))
@@ -62,77 +63,6 @@ REG_OP(CTCLoss)
    .ATTR(ignore_longer_outputs_than_inputs, Bool, false)
    .OP_END_FACTORY_REG(CTCLoss)
 /**
 *@brief Performs greedy decoding on the logits given in inputs.
 *@par Inputs:
 *@li inputs: 3-D, shape: `(max_time x batch_size x num_classes)`, the logits.
 *@li sequence_length: A vector containing sequence lengths, size `(batch_size)`.
 *@par Attributes:
 *@li merge_repeated: If True, merge repeated classes in output.
 *@par Outputs:
 *@li decoded_indices: Indices matrix, size `(total_decoded_outputs x 2)`,\n
 of a `SparseTensor<int64, 2>`.  The rows store: [batch, time].
 *@li decoded_values: Values vector, size: `(total_decoded_outputs)`,\n
 of a `SparseTensor<int64, 2>`.  The vector stores the decoded classes.
 *@li decoded_shape: Shape vector, size `(2)`, of the decoded SparseTensor.\n
 Values are: `[batch_size, max_decoded_length]`.
 *@li log_probability: Matrix, size `(batch_size x 1)`, containing sequence\n
 log-probabilities.
 *@par Third-party framework compatibility
 * Compatible with TensorFlow CTCGreedyDecoder operator.
 */
 REG_OP(CTCGreedyDecoder)
    .INPUT(inputs, TensorType({DT_FLOAT, DT_DOUBLE}))
    .INPUT(sequence_length, TensorType({DT_INT32}))
    .ATTR(merge_repeated, Bool, false)
    .OUTPUT(decoded_indices, TensorType({DT_INT64}))
    .OUTPUT(decoded_values, TensorType({DT_INT64}))
    .OUTPUT(decoded_shape, TensorType({DT_INT64}))
    .OUTPUT(log_probability, TensorType({DT_FLOAT, DT_DOUBLE}))
    .OP_END_FACTORY_REG(CTCGreedyDecoder)
 /**
 *@brief Performs beam search decoding on the logits given in input.
 *@par Inputs:
 *@li inputs: 3-D, shape: `(max_time x batch_size x num_classes)`, the logits.
 *@li sequence_length: A vector containing sequence lengths, size `(batch_size)`.
 *@par Attributes:
 *@li merge_repeated: If True, merge repeated classes in output.
 *@par Outputs:
 *@li decoded_indices: A list (length: top_paths) of indices matrices.  Matrix j,\n
 size `(total_decoded_outputs[j] x 2)`, has indices of a\n
 `SparseTensor<int64, 2>`.  The rows store: [batch, time].
 *@li decoded_values: A list (length: top_paths) of values vectors.  Vector j,\n
 size `(length total_decoded_outputs[j])`, has the values of a\n
 `SparseTensor<int64, 2>`.  The vector stores the decoded classes for beam j.
 *@li decoded_shape: A list (length: top_paths) of shape vector.  Vector j,\n
 size `(2)`, stores the shape of the decoded `SparseTensor[j]`.\n
 Its values are: `[batch_size, max_decoded_length[j]]`.
 *@li log_probability: A matrix, shaped: `(batch_size x top_paths)`.  The\n
 sequence log-probabilities.
 *@par Third-party framework compatibility
 * Compatible with TensorFlow CTCBeamSearchDecoder operator.
 */
 REG_OP(CTCBeamSearchDecoder)
    .INPUT(inputs, TensorType({DT_FLOAT, DT_DOUBLE}))
    .INPUT(sequence_length, TensorType({DT_INT32}))
    .REQUIRED_ATTR(beam_width, Int)
    .REQUIRED_ATTR(top_paths, Int)
    .ATTR(merge_repeated, Bool, true)
    .DYNAMIC_OUTPUT(decoded_indices, TensorType({DT_INT64}))
    .DYNAMIC_OUTPUT(decoded_values, TensorType({DT_INT64}))
    .DYNAMIC_OUTPUT(decoded_shape, TensorType({DT_INT64}))
    .OUTPUT(log_probability, TensorType({DT_FLOAT, DT_DOUBLE}))
    .OP_END_FACTORY_REG(CTCBeamSearchDecoder)
 }  // namespace ge
 #endif //GE_OP_CTC_OPS_H
--- a/third_party/fwkacllib/inc/ops/elewise_calculation_ops.h
+++ b/third_party/fwkacllib/inc/ops/elewise_calculation_ops.h
@@ -483,9 +483,9 @@ REG_OP(Equal)
 *x: A Tensor. Must be one of the following types: float16, float32, double, complex64, complex128.
 *@par Attributes:
 *@li base: An optional attribute of type float32, specifying the base gamma. Defaults to "-1.0".
 *@li scale: An optional attribute of type float32, specifying the scale alpha. Defaults to "1.0".
 *@li shift: An optional attribute of type float32, specifying the shift beta. Defaults to "0.0".
 *@li base: An optional attribute of type float32, specifying the base gamma. Defaults to "-1".
 *@li scale: An optional attribute of type float32, specifying the scale alpha. Defaults to "1".
 *@li shift: An optional attribute of type float32, specifying the shift beta. Defaults to "0".
 *@par Outputs:
 *y: A Tensor of the same type as "x".
@@ -1016,17 +1016,17 @@ REG_OP(BesselI1e)
 * y = log_base(shift + scale * x), with "base" > 0.
 * @par Inputs:
 * @li x: A Tensor of type complex64, complex128, float16, float32 or double.
 * @li x: A Tensor of type UnaryDataType.
 * @par Attributes:
 * @li base: An optional float32, specifying the base "e". Defaults to "-1.0"
 * @li base: An optional float32, specifying the base "e". Defaults to "-1"
 * @li scale: An optional float32, specifying the scale of input "x". Defaults
 * to "1.0"
 * @li shift: An optional float32, specifying the shift. Defaults to "0.0"
 * to "1"
 * @li shift: An optional float32, specifying the shift. Defaults to "0"
 * @par Outputs:
 * y: A Tensor has same type as "x".
 * y: A Tensor of type UnaryDataType.
 * @attention Constraints:
 * @li "base" is supposed to be greater than 0. Retaining the default
@@ -2262,7 +2262,7 @@ REG_OP(ArgMinD)
 *dtype: The output type, either "int32" or "int64". Defaults to "int64".
 *@par Outputs: 
 *y: A multi-dimensional Tensor of type int32 or int64, specifying the index with the largest value. The dimension is one less than that of "x".
 *y: A multi-dimensional Tensor of type int32, specifying the index with the largest value. The dimension is one less than that of "x".
 *@attention Constraints:
 *@li x: If there are multiple maximum values, the index of the first maximum value is used.
@@ -2398,8 +2398,8 @@ REG_OP(ArgMinWithValue)
 *y: A Tensor. Has the same type and format as "x".
 *@par Attributes:
 *@li N: A required attribute. the number of input x, max size is 32. Type is int.
 *@li model: An optional attribute. Type is int. Defaults to "1".
 *@li N: A required attribute. the number of input x, max size is 32.
 *@li model: An optional attribute. Defaults to "1".
 *    "0": product, "1": sum, "2": max.
 *@li coeff: A required attribute. Must met all of following rules:
 *    size of "coeff" must be equal to len("x") or is null.
@@ -2693,86 +2693,6 @@ REG_OP(AdamApplyOne)
    .OP_END_FACTORY_REG(AdamApplyOne)
 /**
 *@brief A fusion operator for bert lamb.
 *@par Inputs:
 *Eleven inputs, including:
 * @li input0: A Tensor. Must be one of the following types: float16, float32.
 * @li input1: A Tensor. Must be one of the following types: float16, float32.
 * @li input2: A Tensor. Must be one of the following types: float16, float32.
 * @li input3: A Tensor. Must be one of the following types: float16, float32.
 * @li input4: A Tensor. Must be one of the following types: float16, float32.
 * @li mul0_x: A Tensor. Must be one of the following types: float16, float32.
 * @li mul1_x: A Tensor. Must be one of the following types: float16, float32.
 * @li mul2_x: A Tensor. Must be one of the following types: float16, float32.
 * @li mul3_x: A Tensor. Must be one of the following types: float16, float32.
 * @li mul4_x: A Tensor. Must be one of the following types: float16, float32.
 * @li add2_y: A Tensor. Must be one of the following types: float16, float32.
 *@par Outputs:
 *Three outputs, including:
 * @li output0: A Tensor. Must be one of the following types: float16, float32.
 * @li output1: A Tensor. Must be one of the following types: float16, float32.
 * @li output2: A Tensor. Must be one of the following types: float16, float32.
 */
 REG_OP(AdamApplyOneWithDecayAssign)
    .INPUT(input0, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(input1, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(input2, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(input3, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(input4, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(mul0_x, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(mul1_x, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(mul2_x, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(mul3_x, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(mul4_x, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(add2_y, TensorType({DT_FLOAT16,DT_FLOAT}))
    .OUTPUT(output0, TensorType({DT_FLOAT16,DT_FLOAT}))
    .OUTPUT(output1, TensorType({DT_FLOAT16,DT_FLOAT}))
    .OUTPUT(output2, TensorType({DT_FLOAT16,DT_FLOAT}))
    .OP_END_FACTORY_REG(AdamApplyOneWithDecayAssign)
 /**
 *@brief A fusion operator for bert lamb.
 *@par Inputs:
 *Ten inputs, including:
 * @li input0: A Tensor. Must be one of the following types: float16, float32.
 * @li input1: A Tensor. Must be one of the following types: float16, float32.
 * @li input2: A Tensor. Must be one of the following types: float16, float32.
 * @li input3: A Tensor. Must be one of the following types: float16, float32.
 * @li input4: A Tensor. Must be one of the following types: float16, float32.
 * @li mul0_x: A Tensor. Must be one of the following types: float16, float32.
 * @li mul1_x: A Tensor. Must be one of the following types: float16, float32.
 * @li mul2_x: A Tensor. Must be one of the following types: float16, float32.
 * @li mul3_x: A Tensor. Must be one of the following types: float16, float32.
 * @li add2_y: A Tensor. Must be one of the following types: float16, float32.
 *@par Outputs:
 *Three outputs, including:
 * @li output0: A Tensor. Must be one of the following types: float16, float32.
 * @li output1: A Tensor. Must be one of the following types: float16, float32.
 * @li output2: A Tensor. Must be one of the following types: float16, float32.
 */
 REG_OP(AdamApplyOneAssign)
    .INPUT(input0, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(input1, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(input2, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(input3, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(input4, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(mul0_x, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(mul1_x, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(mul2_x, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(mul3_x, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(add2_y, TensorType({DT_FLOAT16,DT_FLOAT}))
    .OUTPUT(output0, TensorType({DT_FLOAT16,DT_FLOAT}))
    .OUTPUT(output1, TensorType({DT_FLOAT16,DT_FLOAT}))
    .OUTPUT(output2, TensorType({DT_FLOAT16,DT_FLOAT}))
    .OP_END_FACTORY_REG(AdamApplyOneAssign)
 /**
 *@brief Confuse select, maximum, greater and sqrt.
 *@par Inputs:
@@ -3122,22 +3042,6 @@ REG_OP(KLDiv)
    .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT, DT_DOUBLE}))
    .OP_END_FACTORY_REG(KLDiv)
 /**
 *@brief copy data from x to y..
 *@par Inputs:
 *One inputs, including:
 * @li x: A Tensor. Must be one of the following types: float16, float32, int8, uint8, int32, bool.
 *@par Outputs:
 *y: A Tensor. Has the same type as "x".
 *@par Third-party framework compatibility
 */
 REG_OP(TensorMove)
    .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT, DT_INT32, DT_INT8, DT_UINT8, DT_BOOL}))
    .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT, DT_INT32, DT_INT8, DT_UINT8, DT_BOOL}))
    .OP_END_FACTORY_REG(TensorMove)
 }  // namespace ge
--- a/third_party/fwkacllib/inc/ops/image_ops.h
+++ b/third_party/fwkacllib/inc/ops/image_ops.h
@@ -934,7 +934,6 @@ REG_OP(EncodeJpeg)
 /**
 *@brief PNG-encode an image.
 *@par Inputs:
 *Input image must be unit8 or uint16 type. Inputs include: \n
 *image: is a 3-D uint8 or uint16 Tensor of shape [height, width, channels] \n
@@ -1224,6 +1223,16 @@ REG_OP(CombinedNonMaxSuppression)
    .ATTR(clip_boxes, Bool, true)
    .OP_END_FACTORY_REG(CombinedNonMaxSuppression)
 REG_OP(SpatialTransformerD)
    .INPUT(x, TensorType({DT_FLOAT,DT_FLOAT16}))
    .OPTIONAL_INPUT(theta, TensorType({DT_FLOAT,DT_FLOAT16}))
    .OUTPUT(y, TensorType({DT_FLOAT,DT_FLOAT16}))
    .ATTR(output_size, ListInt, {-1, -1})
    .ATTR(default_theta, ListFloat, {})
    .ATTR(align_corners, Bool, false)
    .ATTR(use_default_theta, ListBool, {})
    .OP_END_FACTORY_REG(SpatialTransformerD)
 }  // namespace ge
 #endif  // GE_OP_MAGE_OPS_H_
--- a/third_party/fwkacllib/inc/ops/math_ops.h
+++ b/third_party/fwkacllib/inc/ops/math_ops.h
@@ -29,9 +29,9 @@ namespace ge {
 * x: A Tensor of type float16 or float32.
 *@par Attributes:
 *@li power: Optional. Must be one of the following types: float32. Defaults to 1.0.
 *@li scale: Optional. Must be one of the following types: float32. Defaults to 1.0.
 *@li shift: Optional. Must be one of the following types: float32. Defaults to 0.0.
 *@li power: Optional. Defaults to 1.0.
 *@li scale: Optional. Defaults to 1.0.
 *@li shift: Optional. Defaults to 0.0.
 *@par Outputs:
 * y: A Tensor. Has the same type and shape as "x".
--- a/third_party/fwkacllib/inc/ops/matrix_calculation_ops.h
+++ b/third_party/fwkacllib/inc/ops/matrix_calculation_ops.h
@@ -699,45 +699,6 @@ REG_OP(FullyConnection)
    .OP_END_FACTORY_REG(FullyConnection)
 /**
 *@brief Also known as a "fully-connected-compress" layer, computes an inner product with a set of learned weights, and (optionally) adds biases.
 *@par Inputs:
 * Four inputs, including:
 *@li x: A Tensor of type uint8, int8.
 *@li w: A weight matrix of type int8, int8.
 *@li w: A compress index matrix of type int8, int8.
 *@li b: A Tensor of type float16, int32, int32.
 *@li offset_w: A Tensor of type int8.i
 *@par Attributes:
 *@li num_output: Reserved.
 *@li transpose: A bool, specifying whether to transpose, either "true" or "false". Defaults to "false".
 *@li axis: Reserved.
 *@li offset_x: Reserved.
 *@par Outputs:
 *y: The result tensor of type int32.
 *@par Third-party framework compatibility
 * Compatible with the Caffe operator InnerProduct.
 *@par Quantization supported or not
 * Yes
 */
 REG_OP(FullyConnectionCompress)
    .INPUT(x, TensorType({DT_UINT8, DT_INT8}))
    .INPUT(w, TensorType({DT_INT8}))
    .INPUT(comress_index, TensorType({DT_INT8}))
    .OPTIONAL_INPUT(b, TensorType({DT_INT32}))
    .OPTIONAL_INPUT(offset_w, TensorType({DT_INT8}))
    .OUTPUT(y, TensorType({DT_INT32}))
    .REQUIRED_ATTR(num_output, Int)
    .ATTR(transpose, Bool, false)
    .ATTR(axis, Int, 1)
    .ATTR(offset_x, Int, 0)
    .OP_END_FACTORY_REG(FullyConnectionCompress)
 /**
 *@brief Computes the confusion matrix from predictions and labels.
 *@par Inputs:
--- a/third_party/fwkacllib/inc/ops/nn_batch_norm_ops.h
+++ b/third_party/fwkacllib/inc/ops/nn_batch_norm_ops.h
@@ -33,12 +33,12 @@ namespace ge {
 * @li variance: A Tensor. Must be one of the following types: float32.
 *@par Attributes:
 * @li mode: A Tensor. Must be one of the following types: int. defaults: 1.
 * @li epsilon: A Tensor. Must be one of the following types: float32. Defaults to 0.000001.
 * @li momentum: A Tensor. Must be one of the following types: float32. Defaults to 0.9.
 * @li is_training: A Tensor. Must be one of the following types: bool. Defaults to true.
 * @li is_training_fusion: A Tensor. Must be one of the following types: bool. Defaults to true.
 * @li moving_average_fraction: A Tensor. Must be one of the following types: float32. Defaults to 0.00300002098.
 * @li mode: A Tensor. Must be one of the following types: int.
 * @li epsilon: A Tensor. Must be one of the following types: float32.
 * @li momentum: A Tensor. Must be one of the following types: float32.
 * @li is_training: A Tensor. Must be one of the following types: bool.
 * @li is_training_fusion: A Tensor. Must be one of the following types: bool.
 * @li moving_average_fraction: A Tensor. Must be one of the following types: float32.
 *@par Outputs:
 *Three outputs, including:
@@ -83,8 +83,8 @@ REG_OP(FusedBatchNorm)
 * @li save_inv_variance1: A Tensor. Must be one of the following types: float32.
 *@par Attributes:
 * @li epsilon: A Tensor. Must be one of the following types: float32. Defaults to 0.0.
 * @li momentum: A Tensor. Must be one of the following types: float32. Defaults to 0.0.
 * @li epsilon: A Tensor. Must be one of the following types: float32.
 * @li momentum: A Tensor. Must be one of the following types: float32.
 *@par Outputs:
 *Three outputs, including:
@@ -361,14 +361,14 @@ REG_OP(BatchNormGradExt2)
 *@par Inputs:
 *@li x: A 4D or 5D Tensor of type float16 or float32, with format NHWC or NCHW for 4D or NC1HWC0 for 5D.
 *@li mean: A Tensor of type float32 or float16. Must be 1D if input "x"  Specifies the mean used for inference.
 *@li variance: A Tensor of type float32 or float16 . Must be 1D if input "x"  Specifies the variance used for inference.
 *@li momentum: A Tensor,represents the mean and the variance's scale factor
 *@li variance: A Tensor of type float32 or float16. Must be 1D if input "x"  Specifies the variance used for inference.
 *@li momentum:  A Tensor of type float32 or float16, represents the mean and the variance's scale factor
 *@li scale: An optional tensor of type float16 or float32, no use
 *@li offset: An optional tensor of type float16 or float32, no use
 *@par Attributes:
 *@li epsilon: An optional float32, specifying the small value added to variance to avoid dividing by zero. Defaults to "0.00001".
 *@li use_global_stats: mean inference mode , only can be "True".
 *@li mode: An optional input, not use
 *@li mode: An optional attr, not use
 *@par Outputs:\n
 *@li y: A 4D or 5D Tensor of type float16 or float32 for the normalized "x"
 */
@@ -391,11 +391,11 @@ REG_OP(BNInference)
 *@li mean: A Tensor of type float32 or float16. Must be 1D if input "x"  Specifies the mean used for inference.
 *@li variance: A Tensor of type float32 or float16 . Must be 1D if input "x"  Specifies the variance used for inference.
 *@li momentum: An optional float, mean and variance's Scale factor
 *@li momentum: A Tensor of type float32 or float16, the mean and the variance's Scale factor
 *@par Attributes:
 *@li epsilon: An optional float32, specifying the small value added to variance to avoid dividing by zero. Defaults to "0.00001".
 *@li use_global_stats: mean inference mode , only can be "True".
 *@li mode: An optional attr, not use
 *@li mode: An optional inpout, not use
 *@par Outputs:
 *@li alpha: A Tensor of type float16 or float32 for the cpu calculate mean
 *@li beta: A Tensor of type float16 or float32 for the cpu calculate variance
@@ -418,8 +418,8 @@ REG_OP(BnHost)
 *@par Inputs:
 *@li x: A 4D or 5D Tensor of type float16 or float32, with format NHWC or NCHW for 4D or NC1HWC0 for 5D.
 *@li mean: A Tensor of type float32 or float16. Must be 1D if input "x" Specifies the mean used for inference.
 *@li variance: A Tensor of type float32 or float16 . Must be 1D if input "x" Specifies the variance used for inference.
 *@li mean: A Tensor of type float32 or float16. Must be 1D if input "x"  Specifies the mean used for inference.
 *@li variance: A Tensor of type float32 or float16 . Must be 1D if input "x"  Specifies the variance used for inference.
 *@li scale: An optional tensor of type float16 or float32, no use
 *@li offset: An optional tensor of type float16 or float32, no use
 *@par Attributes:
--- a/third_party/fwkacllib/inc/ops/nn_calculation_ops.h
+++ b/third_party/fwkacllib/inc/ops/nn_calculation_ops.h
@@ -143,29 +143,31 @@ REG_OP(DepthwiseConv2DBackpropFilterD)
 * @par Inputs:
 * Three inputs include: \n
 * @li input_size: 4D shape of input tensor [N, C, H, W] or [N, H, W, C],
 * support int32, int64
 * @li filter: 4D filter tensor with shape of [H, W, C, K], support float16.
 * support int32
 * @li filter: 4D filter tensor with shape of [H, W, C, K], support float16,
 * float32, double
 * @li out_backprop: 4D tensor with shape [N, C, H, W] or [N, H, W, C].
 * Must be one of the following types: float16.
 * Must be one of the following types: float16, float32, double.
 * @par Attributes:
 * @li strides: A required list or tuple of int32. The stride of the sliding window for
 * @li strides: A required list or tuple. The stride of the sliding window for
 * height and width of input "x" of the convolution.
 * Must be with shape [1, 1, stride_height, stride_width] or [1, stride_height,
 * stride_width, 1].
 * @li dilations: An optional list or tuple of int32. The dilation factor for each
 * dimension of input "x". Defaults to "[1, 1, 1, 1]".
 * @li dilations: An optional list or tuple. The dilation factor for each
 * dimension of input "x".
 * If set to k > 1, there will be k-1 skipped cells between each filter element
 * on that dimension. Must be with shape [1, 1, dilation_height, dilation_width]
 * or [1, dilation_height, dilation_width, 1].
 * @li pads: A required list or tuple of int32. Padding added to each dimension of the
 * @li pads: A required list or tuple. Padding added to each dimension of the
 * input.
 * @li data_format: An optional string. Input data format, either "NHWC" or
 * "NCHW". Defaults to "NHWC".
 * "NCHW".
 * @par Outputs:
 * input_grad: Gradient of the deep convolution relative to the input with shape
 * [N, C, H, W] or [N, H, W, C] Must be one of the following types: float16.
 * [N, C, H, W] or [N, H, W, C] Must be one of the following types: float16,
 * float32, double.
 * @attention Constraints:\n
 * The feature map is 4D with shape [N, C, Hi, Wi] or [N, Hi, Wi, C], but
@@ -257,8 +259,8 @@ REG_OP(DepthwiseConv2DBackpropInputD)
 *@par Inputs:
 *Two required inputs and two optional inputs, including: \n
 * @li x: A 4D tensor of type float16 or int8, with shape [N, C, H, W] or [N, H, W, C]
 * @li filter: A 4D tensor of type float16 or int8, with shape [H, W, C, K]
 * @li x: A 4D tensor of type float16, with shape [N, C, H, W] or [N, H, W, C]
 * @li filter: A 4D tensor of type float16, with shape [H, W, C, K]
 * @li bias: An optional tensor of type float16 or int32
 * @li offset_w: An optional float16 or int8, used for quantized inference
@@ -271,8 +273,8 @@ REG_OP(DepthwiseConv2DBackpropInputD)
 * dimension of input "x".
 * If set to k > 1, there will be k-1 skipped cells between each filter element
 * on that dimension. Must be with shape [1, 1, dilation_height, dilation_width]
 * or [1, dilation_height, dilation_width, 1]. Defaults to "[1, 1, 1, 1]".
 * @li pads: A required list or tuple of int32. Padding added to each dimension of the
 * or [1, dilation_height, dilation_width, 1].
 * @li pads: A required list or tuple. Padding added to each dimension of the
 * input.
 * @li data_format: An optional string. Input data format, either "NHWC" or
 * "NCHW". Defaults to "NHWC".
@@ -280,7 +282,7 @@ REG_OP(DepthwiseConv2DBackpropInputD)
 * Defaults to 0.
 * @par Outputs:
 * y: 4D tensor of type float16 or int32, with shape [N, C, H, W] or [N, H, W, C]
 * y: 4D tensor of type float16, with shape [N, C, H, W] or [N, H, W, C]
 * @attention Constraints:\n
 * The feature map is 4D with shape [N, C, Hi, Wi] or [N, Hi, Wi, C], but
@@ -460,24 +462,24 @@ REG_OP(Conv2DBackpropInputD)
 * @li x: A Tensor. Must have the same type as "filter". 4D with shape
 * [batch, out_channels, out_height, out_width]. Gradients with respect
 * to the output of the convolution.
 * @li filter: A Tensor of type float16, float32, double or int8.
 * @li filter: A Tensor of type float16.
 * 4D with shape [out_channels, in_channel, filter_height, filter_width].\n
 * Two optional inputs:
 * @li bias: An optional tensor of type float16, float32, int32 or int64.
 * @li offset_w: An optional 1D tensor for quantized deconvolution. Type is int8. Reserved.\n
 * @li bias: An optional tensor of type float16
 * @li offset_w: An optional 1D tensor for quantized deconvolution. Reserved.\n
 *@par Attributes:
 * Six attributes:
 * @li strides: A tuple or list of 2 integers. The stride of the sliding window
 * for H/W dimension. Defaults to [1, 1, 1, 1].
 * for H/W dimension.
 * @li pads: A tuple or list of 4 integers. The [top, bottom, left, right]
 * padding on the feature map. Defaults to [0, 0, 0, 0].
 * padding on the feature map
 * @li dilations: A tuple or list of 4 integers. The dilation factor for each
 * dimension of input. Must be [1, 1, 1, 1].
 * @li groups: Number of blocked connections from input channels to
 output channels. Defaults to "1".
 * @li data_format: An optional string from: "NCHW". Defaults to "NCHW". \n
 * output channels.
 * @li data_format: An optional string from: "NCHW". Defaults to "NCHW".\n
  Specify the data format of the input and output data.
 * @li offset_x: An optional integer for quantized deconvolution. Defaults to "0".
 * @li offset_x: An optional integer for quantized deconvolution.
 *@par Outputs:
 * y: A Tensor. Has the same type as "filter". 4D tensor with shape
 * [batch, channels, height, width].
@@ -575,19 +577,17 @@ REG_OP(Conv2DBackpropFilterD)
 * 
 * The input and output tensor attributes are listed as follows:
 * @verbatim
    |Tensor    | x       | filter  | bias    | offset_w | y
     Tensor    | x       | filter  | bias    | offset_w | y
    -----------|---------|---------|---------|----------|--------
    |Data Type | float16 | float16 | float16 | _        | float16
    |          |---------|---------|---------|----------|--------
    |          | float32 | float32 | float32 | _        | float32
    |          |---------|---------|---------|----------|--------
    |          | float64 | float64 | float64 | _        | float64
    |          |---------|---------|---------|----------|--------
    |          | int8    | int8    | int32   | int8     | int32
     Data Type | float16 | float16 | float16 | _        | float16
               |---------|---------|---------|----------|--------
               | float32 | float32 | float32 | _        | float32
               |---------|---------|---------|----------|--------
               | int8    | int8    | int32   | int8     | int32
    -----------|---------|---------|---------|----------|--------
    |Format    | NCHW    | NCHW    | ND      | ND       | NCHW
    |          | NHWC    | NHWC    |         |          | NHWC
    |          |         | HWCN    |         |          |
     Format    | NCHW    | NCHW    | ND      | ND       | NCHW
               | NHWC    | NHWC    |         |          | NHWC
               |         | HWCN    |         |          |
@endverbatim
 * It should be noted that the data types must correspond to each other, but the
 * format does not need to.
@@ -602,10 +602,10 @@ REG_OP(Conv2DBackpropFilterD)
 * for dilated convolution. Has the same dimension order and value as "strides".
 * @li groups: Number of blocked connections from input channels to output
 * channels. Input channels and output channels must both be divisible by
 * "groups".Type is int32.  Must be set to 1.
 * @li offset_x: An optional integer for quantized convolution. Type is int32. Defaults to "0".
 * "groups".
 * @li offset_x: An optional integer for quantized convolution.
 * @li data_format: An optional string from: "NHWC", "NCHW". Specifying the
 * data format of the input and output images. Type is string. Defaults to "NHWC". Reserved.
 * data format of the input and output images. Reserved.
 *@par Outputs:
 * @li y: A 4D Tensor of output images.
@@ -613,23 +613,23 @@ REG_OP(Conv2DBackpropFilterD)
 *@attention
 * @li The parameter scope is listed as follows:
 * @verbatim
    |Name             | Field        | Scope
     Name             | Field        | Scope
    ------------------|--------------|----------
    |Input Image Size | H dimension  | [1, 4096]
    |                 | W dimension  | [1, 4096]
     Input Image Size | H dimension  | [1, 4096]
                      | W dimension  | [1, 4096]
    ------------------|--------------|----------
    |Filter Size      | H dimension  | [1, 255]
    |                 | W dimension  | [1, 255]
     Filter Size      | H dimension  | [1, 255]
                      | W dimension  | [1, 255]
    ------------------|--------------|----------
    |Stride Size      | H dimension  | [1, 63]
    |                 | W dimension  | [1, 63]
     Stride Size      | H dimension  | [1, 63]
                      | W dimension  | [1, 63]
    ------------------|--------------|----------
    |Padding Size     | top side     | [0, 255]
    |                 | bottom side  | [0, 255]
    |                 | left side    | [0, 255]
    |                 | right side   | [0, 255]
     Padding Size     | top side     | [0, 255]
                      | bottom side  | [0, 255]
                      | left side    | [0, 255]
                      | right side   | [0, 255]
    ------------------|--------------|----------
    |Dilation Size    | H dimension  | [1, 255]
     Dilation Size    | H dimension  | [1, 255]
                      | W dimension  | [1, 255]
@endverbatim
@@ -654,11 +654,11 @@ REG_OP(Conv2DBackpropFilterD)
 *@li Compatible with the Caffe operator 2D "Convolution".
 */
 REG_OP(Conv2D)
    .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT, DT_DOUBLE, DT_INT8}))
    .INPUT(filter, TensorType({DT_FLOAT16, DT_FLOAT, DT_DOUBLE, DT_INT8}))
    .OPTIONAL_INPUT(bias, TensorType({DT_FLOAT16, DT_FLOAT, DT_DOUBLE, DT_INT32}))
    .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT, DT_INT8}))
    .INPUT(filter, TensorType({DT_FLOAT16, DT_FLOAT, DT_INT8}))
    .OPTIONAL_INPUT(bias, TensorType({DT_FLOAT16, DT_FLOAT, DT_INT32}))
    .OPTIONAL_INPUT(offset_w, TensorType({DT_INT8}))
    .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT, DT_DOUBLE, DT_INT32}))
    .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT, DT_INT32}))
    .REQUIRED_ATTR(strides, ListInt)
    .REQUIRED_ATTR(pads, ListInt)
    .ATTR(dilations, ListInt, {1, 1, 1, 1})
@@ -710,8 +710,8 @@ REG_OP(Conv3D)
    .INPUT(filter, TensorType({DT_FLOAT16, DT_FLOAT, DT_DOUBLE}))
    .OPTIONAL_INPUT(bias, TensorType({DT_FLOAT16, DT_FLOAT, DT_DOUBLE}))
    .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT, DT_DOUBLE}))
    .REQUIRED_ATTR(strides, ListInt)
    .REQUIRED_ATTR(pads, ListInt)
    .ATTR(strides, ListInt, {1, 1, 1, 1, 1})
    .ATTR(pads, ListInt, {0, 0, 0, 0, 0, 0})
    .ATTR(data_format, String, "NDHWC")
    .ATTR(dilations, ListInt, {1, 1, 1, 1, 1})
    .OP_END_FACTORY_REG(Conv3D)
@@ -742,7 +742,7 @@ REG_OP(Conv3DBackpropInput)
    .INPUT(grads, TensorType({DT_FLOAT16, DT_FLOAT, DT_DOUBLE}))
    .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT, DT_DOUBLE}))
    .REQUIRED_ATTR(strides, ListInt)
    .REQUIRED_ATTR(pads, ListInt)
    .ATTR(pads, ListInt, {0, 0, 0, 0, 0, 0})
    .ATTR(data_format, String, "NDHWC")
    .ATTR(dilations, ListInt, {1, 1, 1, 1, 1})
    .OP_END_FACTORY_REG(Conv3DBackpropInput)
@@ -771,7 +771,7 @@ REG_OP(Conv3DBackpropInputD)
    .OUTPUT(y, TensorType({DT_FLOAT16}))
    .REQUIRED_ATTR(input_size, ListInt)
    .REQUIRED_ATTR(strides, ListInt)
    .REQUIRED_ATTR(pads, ListInt)
    .ATTR(pads, ListInt, {0, 0, 0, 0, 0, 0})
    .ATTR(data_format, String, "NDHWC")
    .ATTR(dilations, ListInt, {1, 1, 1, 1, 1})
    .OP_END_FACTORY_REG(Conv3DBackpropInputD)
--- a/third_party/fwkacllib/inc/ops/nn_detect_ops.h
+++ b/third_party/fwkacllib/inc/ops/nn_detect_ops.h
@@ -187,15 +187,14 @@ REG_OP(ROIAlignGrad)
 *@li features: A 5HD Tensor of type float32 or float16.
 *@li rois: ROI position. A 2D Tensor of float32 or float16 with shape (N, 5). "N" indicates the number of ROIs, the value "5" indicates the indexes of images where the ROIs are located, 
 * "x0", "y0", "x1", and "y1".
 *@li rois_n: An optional input of type int32, specifying the number of valid ROIs. This parameter is reserved.
 *@li rois_n: An optional input, specifying the number of valid ROIs. This parameter is reserved.
 *@par Attributes:
 *@li spatial_scale: A required attribute of type float32, specifying the scaling ratio of "features" to the original image.
 *@li pooled_height: A required attribute of type int32, specifying the H dimension.
 *@li pooled_width: A required attribute of type int32, specifying the W dimension.
 *@li sample_num: An optional attribute of type int32, specifying the horizontal and vertical sampling frequency of each output. If this attribute is set to "0",
 *@li spatial_scale: A required attribute of type float, specifying the scaling ratio of "features" to the original image.
 *@li pooled_height: A required attribute of type int, specifying the H dimension.
 *@li pooled_width: A required attribute of type int, specifying the W dimension.
 *@li sample_num: An optional attribute of type int, specifying the horizontal and vertical sampling frequency of each output. If this attribute is set to "0",
 * the sampling frequency is equal to the rounded up value of "rois", which is a floating point number. Defaults to "2".
 *@li roi_end_mode: An optional attribute of type int32. Defaults to "1".
 *@par Outputs:
 * output: Outputs the feature sample of each ROI position. The format is 5HD Tensor of type float32 or float16. The axis N is the number of input ROIs. Axes H, W, and C are consistent
@@ -363,15 +362,15 @@ REG_OP(PSROIPooling)
 *@li im_info: An ND tensor of type float16 or float32, specifying the Image information.
 *@li actual_rois_num: An optional NCHW tensor of type int32, specifying the number of valid boxes per batch.
 *@par Attributes:
 *@li batch_rois: An optional int32, specifying the number of images to be predicted. Defaults to "1".
 *@li batch_rois: An optional int32, specifying the number of images to be predicted.
 *@li num_classes: An required int32, specifying the number of classes to be predicted. The value must be greater than 0.
 *@li score_threshold: An required float32, specifying the threshold for box filtering. The value range is [0.0, 1.0].
 *@li iou_threshold: An required float32, specifying the confidence threshold for box filtering, which is the output "obj" of operator Region. The value range is (0.0, 1.0).
 *@par Outputs:
 *@li box: A tensor of type float16 or float32 for proposal of actual output, with output shape [batch, numBoxes,8].
 * 8 means [x1, y1, x2, y2, score, label, batchID, NULL], the maximum value of numBoxes is 1024.
 *@li box: An NCHW tensor of type float16 or float32, describing the information of each output box, including the coordinates, class, and confidence.
 Proposal of actual output, with output shape [batch, numBoxes,8], 8 means [x1, y1, x2, y2, score, label, batchID, NULL], the maximum value of numBoxes is 1024.
 That is, take min (the maximum number of input boxes, 1024)
 *@li actual_bbox_num: A tensor of type int32 With shape [bacth, num_classes], specifying the number of output boxes.
 *@li actual_bbox_num: An NCHW tensor of type int32 With shape [bacth, num_classes], specifying the number of output boxes.
 *@attention Constraints:\n
 *@li totalnum < max_rois_num * batch_rois.
@@ -415,9 +414,9 @@ REG_OP(FSRDetectionOutput)
 *@li confidence_threshold: An optional float32, specify the topk filter threshold. Only consider detections with confidence greater than the threshold
 *@li kernel_name: An optional string, specifying the operator name. Defaults to "ssd_detection_output".
 *@par Outputs:
 *@li out_boxnum: A tensor of type int32, specifying the number of output boxes.
 *@li y: A tensor of type float16 or float32 with shape [batch,keep_top_k, 8], describing the information of each output box.
 * In output shape, 8 means (batchID, label(classID), score (class probability), xmin, ymin, xmax, ymax, null)
 *@li out_boxnum: An NCHW tensor of type int32, specifying the number of output boxes.
 *@li y: An NCHW tensor of type float16 or float32 with shape [batch,keep_top_k, 8], describing the information of each output box, including the coordinates,
 * class, and confidence. In output shape, 8 means (batchID, label(classID), score (class probability), xmin, ymin, xmax, ymax, null)
 * It is a custom operator. It has no corresponding operator in Caffe.
 */
 REG_OP(SSDDetectionOutput)
@@ -448,10 +447,10 @@ REG_OP(SSDDetectionOutput)
 *@li boxes: A required int32, specifying the number of anchor boxes. Defaults to "5" for V2 or "3" for V3.
 *@li coords: An int32, specifying the number of parameters required for locating an object. The value is fixed at "4", corresponding to (x,y,w,h).
 *@li classes: An int32, specifying the number of prediction classes. Defaults to "80". The value range is [1, 1024].
 *@li yolo_version: A string, specifying the YOLO version, either "V2" or "V3".Defaults to "V3"
 *@li softmax: A bool, specifying whether to perform softmax, valid only when "yolo_version = V2". Defaults to "false".
 *@li background: A bool, specifying the operation types of the obj and classes, used in conjunction with "softmax" and valid only when "yolo_version = V2". Defaults to "false".
 *@li softmaxtree: A bool, Fixed to False, defined in Lite, but not used. Defaults to "false".
 *@li yolo_version: A string, specifying the YOLO version, either "V2" or "V3".
 *@li softmax: A bool, specifying whether to perform softmax, valid only when "yolo_version = V2".
 *@li background: A bool, specifying the operation types of the obj and classes, used in conjunction with "softmax" and valid only when "yolo_version = V2".
 *@li softmaxtree: A bool, Fixed to False, defined in Lite, but not used.
 *@par Outputs:
 *@li coord_data: A float16 or float32 with shape [N, boxes*coords, ceilx(height*width*2+32, 32)/2], where "ceil" indicates that a detected box is aligned upwards with the second parameter. Specifies the coordinates of a detected box.
@@ -502,10 +501,10 @@ and the actual image height and width.
 *@li pre_nms_topn: An optional int, specifying the number of boxes for non-maximum suppression (NMS). Defaults to "512".
 *
 *@par Outputs:
 *@li boxout: A tensor of type float16 or float32 with shape [batch,6,post_nms_topn]. describing the information of each output box,
 * In output shape, 6 means x1, y1, x2, y2, score, label(class). Output by the number of box_out_num.
 *@li boxoutnum: A tensor of type int32 with shape [batch,8,1,1], specifying the number of output boxes. It means only the first one of the 8 numbers is valid,
 * the number of valid boxes in each batch, the maximum number of valid boxes in each batch is 1024
 *@li boxout: An NCHW tensor of type float16 or float32 with shape [batch,6,post_nms_topn]. describing the information of each output box, including the coordinates, class,
 and confidence. In output shape, 6 means x1, y1, x2, y2, score, label(class). Output by the number of box_out_num.
 *@li boxoutnum: An NCHW tensor of type int32 with shape [batch,8,1,1], specifying the number of output boxes. It means only the first one of the 8 numbers is valid,
 the number of valid boxes in each batch, the maximum number of valid boxes in each batch is 1024
 *
 *@attention Constraints:\n
 *@li This operator applies only to the YOLO v2 network.
@@ -562,10 +561,10 @@ and the actual image height and width.
 *@li pre_nms_topn: An optional int, specifying the number of boxes for non-maximum suppression (NMS). Defaults to "512".
 *
 *@par Outputs:
 *@li boxout: A tensor of type float16 or float32 with shape [batch,6,post_nms_topn]. describing the information of each output box,
 * In output shape, 6 means x1, y1, x2, y2, score, label(class). Output by the number of box_out_num.
 *@li boxoutnum: A tensor of type int32 with shape [batch,8,1,1], specifying the number of output boxes. It means only the first one of the 8 numbers is valid,
 * the number of valid boxes in each batch, the maximum number of valid boxes in each batch is 1024
 *@li boxout: An NCHW tensor of type float16, describing the information of each output box, including the coordinates, class, and confidence.
 With shape [batch,6,post_nms_topn], 6 means x1, y1, x2, y2, score, label(class). Output by the number of box_out_num.
 *@li boxoutnum: An NCHW tensor of type int32, specifying the number of output boxes.
 With shape [batch,8,1,1], means only the first one of the 8 numbers is valid, the number of valid boxes in each batch, the maximum number of valid boxes in each batch is 1024
 *
 *@attention Constraints:\n
 *@li This operator applies only to the YOLO v2 network.
@@ -622,11 +621,11 @@ and the actual image height and width.
 *@li pre_nms_topn: An optional int, specifying the number of boxes for non-maximum suppression (NMS). Defaults to "512".
 *
 *@par Outputs:
 *@li boxout: A tensor of type float16 or float32 with shape [batch,6,post_nms_topn], describing the information of each output box.
 * In output shape, 6 means x1, y1, x2, y2, score, label(class). Output by the number of box_out_num.
 *@li boxoutnum: A tensor of type int32 with shape [batch,8,1,1], specifying the number of output boxes.
 * The output shape means only the first one of the 8 numbers is valid, the number of valid boxes in each batch, the maximum number of valid boxes in each batch is 1024
 *
 *@li boxout: An NCHW tensor of type float16 or float32 with shape [batch,6,post_nms_topn], describing the information of each output box, including the coordinates, class, and confidence.
 In output shape, 6 means x1, y1, x2, y2, score, label(class). Output by the number of box_out_num.
 *@li boxoutnum: An NCHW tensor of type int32 with shape [batch,8,1,1], specifying the number of output boxes.
 The output shape means only the first one of the 8 numbers is valid, the number of valid boxes in each batch, the maximum number of valid boxes in each batch is 1024
 *@attention Constraints:\n
 *@li This operator applies only to the YOLO v3 network.
 *@li The preceding layer of operator Yolov3DetectionOutput must be three Yolo operators.
@@ -689,11 +688,12 @@ and the actual image height and width.
 *@li pre_nms_topn: An optional int, specifying the number of boxes for non-maximum suppression (NMS). Defaults to "512".
 *
 *@par Outputs:
 *@li boxout: A tensor of type float16 or float32 with shape [batch,6,post_nms_topn], describing the information of each output box.
 * In output shape, 6 means x1, y1, x2, y2, score, label(class). Output by the number of box_out_num.
 *@li boxoutnum: A tensor of type int32 with shape [batch,8,1,1], specifying the number of output boxes.
 * The output shape means only the first one of the 8 numbers is valid, the number of valid boxes in each batch, the maximum number of valid boxes in each batch is 1024
 *@li boxout: An NCHW tensor of type float16, describing the information of each output box, including the coordinates, class, and confidence.
 With shape [batch,6,post_nms_topn], 6 means x1, y1, x2, y2, score, label(class). Output by the number of box_out_num.
 *@li boxoutnum: An NCHW tensor of type int32, specifying the number of output boxes.
 With shape [batch,8,1,1], means only the first one of the 8 numbers is valid, the number of valid boxes in each batch, the maximum number of valid boxes in each batch is 1024
 *
 *@attention Constraints:\n
 *@li This operator applies only to the YOLO v3 network.
 *@li The preceding layer of operator Yolov3DetectionOutput must be three Yolo operators.
--- a/third_party/fwkacllib/inc/ops/nn_norm_ops.h
+++ b/third_party/fwkacllib/inc/ops/nn_norm_ops.h
@@ -291,8 +291,8 @@ REG_OP(BinaryCrossEntropyGrad)
 * double. Should be a Variable Tensor.
 *@par Attributes:
 *axes: A list of int. The dimension softmax would be performed on. Defaults
 * to "[-1]".
 *axes: A list of ints. The dimension softmax would be performed on. Defaults
 * to "{-1}".
 *@par Outputs:
 *y: A Tensor. Has the same dimensionality and shape as the "x" with values in
@@ -632,7 +632,7 @@ REG_OP(DropOutDoMask)
 * Three inputs, including:
 *@li x: An ND tensor of type float16 or float32.
 *@li scale: An ND tensor of type float16 or float32.
 *@li bias: An optional ND tensor of type float16 or float32.
 *@li bias: An ND tensor of type float16 or float32.
 *@par Attributes:
 *@li axis: An optional int32 used to compute the shape of scale and bias input from the online bottoms. Defaults to "1".
@@ -679,9 +679,9 @@ REG_OP(Scale)
 * depth_radius = (local_size - 1) / 2. local_size is the number of channels to sum over (for ACROSS_CHANNELS)
 * or the side length of the square region to sum over (for WITHIN_CHANNEL).
 *@li bias: An optional float32. An offset, usually > 0 to avoid dividing by 0.
 * Defaults to "1.0".
 * Defaults to "1".
 *@li alpha: An optional float32. A scaling factor, usually positive.
 * Defaults to "1.0".
 * Defaults to "1".
 *@li beta: An optional float32. An exponent. Defaults to "0.75" for the caffe framework, Defaults to "0.5" for others.
 *@li norm_region: An optional string. A mode option. "ACROSS_CHANNELS":0, "WITHIN_CHANNEL":1. Defaults to "ACROSS_CHANNELS".
@@ -836,56 +836,6 @@ REG_OP(GroupNorm)
    .ATTR(num_groups, Int, 2)
    .OP_END_FACTORY_REG(GroupNorm)
 /**
 *@brief Performs instance normalization.
 *@par Inputs:\n
 * Five inputs, including: (NC1HWC0, supported)
 *@li x: A 5D Tensor of type float16 or float32, NC1HWC0.
 *@li gamma: A Tensor of type float32.
 A 5D Tensor for scaling factor, to scale the normalized x.
 *@li beta: A Tensor of type float32. 
 A 5D Tensor for offset, to shift to the normalized x.
 *@li mean: A Tensor of type float32. 
 A 5D Tensor Specifies the mean used for inference. Reserved.
 *@li variance: A Tensor of type float32. 
 A 5D Tensor Specifies the variance used for inference. Reserved.
 *@par Attributes:
 *@li is_training: An optional bool, specifying if the operation is used for \n
 training or inference. Defaults to "True".
 *@li momentum: An optional float32, \n
 the value used for the running_mean and running_var computation. Default: "0.1".
 *@li epsilon: An optional float32, specifying the small value added to \n
 variance to avoid dividing by zero. Defaults to "0.00001".
 *@par Outputs:\n
 * Three outputs, including: (NHWC, NCHW NC1HWC0 supported)
 *@li y: A 5D tensor of type float16 or float32 for the normalized "x", \n
 *@li batch_mean: A Tensor of type float32. 
 Specifies the mean of "x".
 *@li batch_variance: A Tensor of type float32. 
 Specifies the variance of "x".
 *@par Third-party framework compatibility
 *@li Compatible with the PyTorch operator InstanceNorm.
 */
 REG_OP(InstanceNormV2)
    .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT}))
    .OPTIONAL_INPUT(gamma, TensorType({DT_FLOAT}))
    .OPTIONAL_INPUT(beta, TensorType({DT_FLOAT}))
    .OPTIONAL_INPUT(mean, TensorType({DT_FLOAT}))
    .OPTIONAL_INPUT(variance, TensorType({DT_FLOAT}))
    .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT}))
    .OUTPUT(batch_mean, TensorType({DT_FLOAT}))
    .OUTPUT(batch_variance, TensorType({DT_FLOAT}))
    .ATTR(is_training, Bool, true)
    .ATTR(momentum, Float, 0.1)
    .ATTR(epsilon, Float, 0.00001)
    .OP_END_FACTORY_REG(InstanceNormV2)
 }  // namespace ge
 #endif  //GE_OP_NN_NORM_OPS_H
--- a/third_party/fwkacllib/inc/ops/nn_pooling_ops.h
+++ b/third_party/fwkacllib/inc/ops/nn_pooling_ops.h
@@ -102,42 +102,6 @@ REG_OP(AvgPool)
    .OP_END_FACTORY_REG(AvgPool)
 /**
 *@brief Performs average pooling on the input.
 *@par Inputs:
 *x: A 5-D Tensor of shape [batch, depth, height, width, channels] and type float16, float32, double.
 *@par Attributes:
 *@li ksize: List of ints that has length 1, 3 or 5. The size of the window for each dimension of the input tensor.
 *@li strides:List of ints that has length 1, 3 or 5. The stride of the sliding window for each dimension of the input tensor.
 *@li pads: List of ints, implicit zero paddings on both sides of the input.
 *@li ceil_mode: When true, will use ceil instead of floor in the formula to compute the output shape.
 *@li count_include_pad: When true, will include the zero-padding in the averaging calculation.
 *@li divisor_override: if specified, it will be used as divisor, otherwise size of the pooling region will be used.
 *@li data_format: A string, format of input data.
 *@par Outputs:
 *y: The average pooled output tensor.
 *@attention Constraints:
 *@li "ksize" is in the range [1, 255]. "strides" is in the range [1, 63]
 *@par Third-party framework compatibility
 * Compatible with the TensorFlow operator AvgPool3D.
 */
 REG_OP(AvgPool3D)
    .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT32, DT_DOUBLE}))
    .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT32, DT_DOUBLE}))
    .REQUIRED_ATTR(ksize, ListInt)
    .REQUIRED_ATTR(strides, ListInt)
    .REQUIRED_ATTR(pads, ListInt)
    .ATTR(ceil_mode, Bool, false)
    .ATTR(count_include_pad, Bool, true)
    .ATTR(divisor_override, Int, 0)
    .ATTR(data_format, String, "NDHWC")
    .OP_END_FACTORY_REG(AvgPool3D)
 /**
 *@brief Performs max_pool_ext2 on the input.
 *@par Inputs:
@@ -220,62 +184,17 @@ REG_OP(MaxPool)
    .OP_END_FACTORY_REG(MaxPool)
 REG_OP(MaxPool3D)
    .INPUT(x, TensorType({DT_FLOAT16, DT_FLOAT32, DT_DOUBLE}))
    .OUTPUT(y, TensorType({DT_FLOAT16, DT_FLOAT32, DT_DOUBLE}))
    .INPUT(x, TensorType({DT_FLOAT16}))
    .OUTPUT(y, TensorType({DT_FLOAT16}))
    .REQUIRED_ATTR(ksize, ListInt)
    .REQUIRED_ATTR(strides, ListInt)
    .REQUIRED_ATTR(padding, String)
    .ATTR(pads, ListInt, {0,0,0})
    .ATTR(dilation, ListInt, {1,1,1})
    .ATTR(dilation, ListInt, {0,0,0})
    .ATTR(ceil_mode, Int, 0)
    .ATTR(data_format, String, "NDHWC")
    .OP_END_FACTORY_REG(MaxPool3D)
 /**
 * @brief Computes second-order gradients of the maxpooling3d function.
 * @par Inputs:
 * @li orig_x: Original forward input tensor(NDC1HWC0) of type float16
 * @li orig_y: Original forward output tensor(NDC1HWC0) of type float16
 * @li grads: Gradient tensor(NDC1HWC0) of type float16
 * @li assist: Assist tensor(NDC1HWC0) of type float16
 * @par Attributes:
 * @li ksize: A required list or tuple,
 * specifying the size of the sliding window.
 * @li strides: A required list or tuple,
 * specifying the stride of the sliding window.
 * @li pads: A required list or tuple
 * @li padding: A required string, window sliding mode. Either SAME or VALID.
 * @li data_format: An optional string.
 * Format of the original input, either NCDHW or NDHWC. Defaults to NDHWC.
 * @attention Constraints:
 * @li Only the Ascend 910 platform is supported.
 * @li "orig_x" and "grads" must have the same shape.
 * @li "orig_y" and "y" must have the same shape. Otherwise, an error is reported.
 * @li "orig_x", "orig_y", "grads", and "y" must be NDC1HWC0 tensors.
 * @par Outputs:
 * @li y: Result tensor of type float16
 * @par Third-party framework compatibility
 * @li Compatible with the TensorFlow operator MaxPool3DGradGrad.
 */
 REG_OP(MaxPool3DGradGrad)
    .INPUT(orig_x, TensorType::RealNumberType())
    .INPUT(orig_y, TensorType::RealNumberType())
    .INPUT(grads, TensorType::RealNumberType())
    .OUTPUT(y, TensorType::RealNumberType())
    .REQUIRED_ATTR(ksize, ListInt)
    .REQUIRED_ATTR(strides, ListInt)
    .REQUIRED_ATTR(pads, ListInt)
    .ATTR(data_format, String, "NDHWC")
    .OP_END_FACTORY_REG(MaxPool3DGradGrad)
 /**
 * @brief Computes gradients of the maxpooling function.
@@ -320,10 +239,9 @@ REG_OP(MaxPoolGrad)
 * @brief Computes second-order gradients of the maxpooling function.
 * @par Inputs:
 * @li x1: Original forward input tensor. Supported type:float, double, int32,
 * uint8, int16, int8, int64, uint16, half, uint32, uint64.
 * @li x2: Has the same type and format as input "x1".
 * @li grad:Has the same type and format as input "x1".
 * @li x1: Original forward input tensor of type RealNumberType
 * @li x2: Original forward output tensor of type RealNumberType
 * @li grad: Gradient tensor of type RealNumberType
 * @par Attributes:
 * @li ksize: A required list or tuple,
@@ -344,7 +262,7 @@ REG_OP(MaxPoolGrad)
 * @li Other dimensions of ksize and strides is 1.
 * @par Outputs:
 * @li y: Has the same type and format as input "x1".
 * @li y: Result tensor of type RealNumberType
 * @par Third-party framework compatibility
 * @li Compatible with the TensorFlow operator MaxPoolGradGrad.
@@ -480,55 +398,18 @@ REG_OP(MaxPoolGradWithArgmax)
    .OP_END_FACTORY_REG(MaxPoolGradWithArgmax)
 /**
 *@brief Performs transform mask to argmax.
 *@par Inputs:
 * Two input:
 *x: An NC1HWC0 Tensor of type float16.
 *mask: An NC1HWC0 Tensor of type uint16.
 *@par Attributes:
 *@li ksize: A required list of int8, int16, int32, or int64 values, specifying the size of the window for each dimension of the input tensor. No default value.
 *@li strides: A required list of int8, int16, int32, or int64 values, specifying the stride of the sliding window for each dimension of the input tensor. No default value.
 *@li padding: A required string. No default value.
 *@par Outputs:
 *argmax: An NC1HWC0 Tensor of type int32.
 *@attention Constraints:
 *@li "ksize" is a list that has length 4: ksize[0] = 1 or ksize[3] = 1, ksize[1] * ksize[2] <= 255.
 *@li "stride is a list that has length 4: strides[0] = 1 or strides[3] = 1, strides[1] <= 63, strides[0] >= 1, strides[2] <= 63, strides[2] >= 1.
 *@li "padding" is either "SAME" or "VALID".
 *@par Third-party framework compatibility
 * Compatible with the TensorFlow operator Mask2Argmax.
 */
 REG_OP(Mask2Argmax)
    .INPUT(x, TensorType::RealNumberType())
    .INPUT(mask, TensorType::IndexNumberType())
    .OUTPUT(argmax, TensorType::IndexNumberType())
    .REQUIRED_ATTR(ksize, ListInt)
    .REQUIRED_ATTR(strides, ListInt)
    .REQUIRED_ATTR(padding, String)
    .REQUIRED_ATTR(originshape, ListInt)
    .OP_END_FACTORY_REG(Mask2Argmax)
 /**
 * @brief Computes second-order gradients of the maxpooling function.
 * @par Inputs:
 * @li x: Original forward input tensor. Supported type: float, double, int32,
 * uint8, int16, int8, int64, uint16, half, uint32, uint64.
 * @li grad: Gradient tensor. Supported type: float, double, int32,
 * uint8, int16, int8, int64, uint16, half, uint32, uint64.
 * @li argmax: An tensor of type int32 or int64.
 * @li x: Original forward input tensor of type RealNumberType
 * @li grad: Gradient tensor of type RealNumberType
 * @li argmax: An tensor of type IndexNumberType
 * @par Attributes:
 * @li ksize: A required list, specifying the size of the sliding window.
 * @li strides: A required list, specifying the stride of the sliding window.
 * @li padding: A required string, window sliding mode. Either SAME or VALID.
 * @par Outputs:
 * @li y:Result tensor. Supported type: float, double, int32,
 * uint8, int16, int8, int64, uint16, half, uint32, uint64
 * @li y:Result tensor of type RealNumberType
 * @attention Constraints:
 * @li Only the cloud platform is supported.
@@ -650,7 +531,7 @@ REG_OP(MaxPoolGradWithArgmaxCCE)
 * one input, including:
 *@li x: A tensor of type float16 or float32.
 *@par Attributes:
 *@li  scale: A optional float32, scale factor of x. Defaults to "1.0".
 *@li  scale: A optional float, scale factor of x. Defaults to "1.0".
 *@li  stride_h: An optional int32, broadcast the axis of h. Defaults to "2".
 *@li  stride_w: An optional int32, broadcast the axis of w. Defaults to "2".
 *@par Outputs:
@@ -868,186 +749,7 @@ REG_OP(DataFormatVecPermute)
    .ATTR(dst_format, String, "NCHW")
    .OP_END_FACTORY_REG(DataFormatVecPermute)
 /**
 * @brief Computes gradients of the MaxPool3D function.
 * @par Inputs:
 * @li orig_x: A mutable NDC1HWC0 tensor of type float16.
 * @li orig_y: A mutable NDC1HWC0 tensor of type float16.
 * @li grads: A mutable NDC1HWC0 tensor of type float16.
 * @par Attributes:
 * @li ksize: A required tuple or list, specifying the size of the window for
 * each dimension of the input tensor.
 * @li strides: A required tuple or list, specifying the stride of the sliding
 * window for each dimension of the input tensor.
 * @li pads: A list of 6 ints. Supports only padding along the D,
 * H and W dimensions in sequence of head, tail, top, bottom, left and right.
 * to use.
 * @li data_format: An optional string, Specify the data format of the input and
 * output data. With the default format "NDHWC".
 * @par Outputs:
 * y: A mutable tensor. Has the same shape as "orig_x", but type is float32.
 * @par Third-party framework compatibility
 * Compatible with the TensorFlow operator MaxPool3DGrad.
 */
 REG_OP(MaxPool3DGrad)
    .INPUT(orig_x, TensorType::RealNumberType())
    .INPUT(orig_y, TensorType::RealNumberType())
    .INPUT(grads, TensorType::RealNumberType())
    .OUTPUT(y, TensorType::RealNumberType())
    .REQUIRED_ATTR(ksize, ListInt)
    .REQUIRED_ATTR(strides, ListInt)
    .REQUIRED_ATTR(pads, ListInt)
    .ATTR(data_format, String, "NDHWC")
    .OP_END_FACTORY_REG(MaxPool3DGrad)
 /**
 *@brief Performs AvgPool1D on the input.
 *@par Inputs:
 *x: A Tensor. Must be one of the following types: int8, uint8, int16, int32, int64, float16, float32, float64.
 *@par Attributes:
 *@li ksize: An required int, specifying the size of the window.
 *@li strides: An required int.
 *@li pads: A required tuple or list.
 *@li ceil_mode: An optional bool. Defaults to False.
 *@li count_include_pad: An optional bool. Defaults to False.
 *@par Outputs:
 *y: A Tensor. Has the same type as x.
 *@par Third-party framework compatibility
 *@li compatible with pytorch AvgPool1D operator.
 */
 REG_OP(AvgPool1D)
    .INPUT(x, TensorType({DT_INT8, DT_UINT8, DT_INT16, DT_INT32, DT_INT64, DT_FLOAT16, DT_FLOAT, DT_DOUBLE}))
    .OUTPUT(y, TensorType({DT_INT8, DT_UINT8, DT_INT16, DT_INT32, DT_INT64, DT_FLOAT16, DT_FLOAT, DT_DOUBLE}))
    .REQUIRED_ATTR(ksize, Int)
    .REQUIRED_ATTR(strides, Int)
    .REQUIRED_ATTR(pads, ListInt)
    .ATTR(ceil_mode, Bool, false)
    .ATTR(count_include_pad, Bool, false)
    .OP_END_FACTORY_REG(AvgPool1D)
 /**
 *@brief Performs AvgPool1D on the input.
 *@par Inputs:
 *x: A Tensor. Must be one of the following types: int8, uint8, int16, int32, int64, float16, float32, float64.
 *@par Attributes:
 *@li ksize: An required int, specifying the size of the window.
 *@li strides: An required int.
 *@li pads: A required tuple or list.
 *@li ceil_mode: An optional bool. Defaults to False.
 *@li count_include_pad: An optional bool. Defaults to False.
 *@par Outputs:
 *y: A Tensor. Has the same type as x.
 *@par Third-party framework compatibility
 *@li compatible with pytorch AvgPool1D operator.
 */
 REG_OP(AvgPool1DD)
    .INPUT(x, TensorType({DT_INT8, DT_UINT8, DT_INT16, DT_INT32, DT_INT64, DT_FLOAT16, DT_FLOAT, DT_DOUBLE}))
    .INPUT(assist_matrix, TensorType({DT_INT8, DT_UINT8, DT_INT16, DT_INT32, DT_INT64, DT_FLOAT16, DT_FLOAT, DT_DOUBLE}))
    .OUTPUT(y, TensorType({DT_INT8, DT_UINT8, DT_INT16, DT_INT32, DT_INT64, DT_FLOAT16, DT_FLOAT, DT_DOUBLE}))
    .REQUIRED_ATTR(ksize, Int)
    .REQUIRED_ATTR(strides, Int)
    .REQUIRED_ATTR(pads, ListInt)
    .ATTR(ceil_mode, Bool, false)
    .ATTR(count_include_pad, Bool, false)
    .OP_END_FACTORY_REG(AvgPool1DD)
 /**
 *@brief Performs max pooling on the input and outputs both max values and indices.
 *@par Inputs:
 * One input:
 *x: An NC1HWC0 Tensor of type float16.
 *@par Attributes:
 *@li ksize: A required list of int8, int16, int32, or int64 values, specifying the size of the window for
 * each dimension of the input tensor. No default value.
 *@li strides: A required list of int8, int16, int32, or int64 values, specifying the stride of the sliding window for
 * each dimension of the input tensor. No default value.
 *@li pads: A required string. No default value.
 *@li dtype: A optional int. default value is 3.
 *@li dilation: A optional list of int8, int16, int32, or int64 values.
 *@li ceil_mode: A optional bool. default value is false.
 *@par Outputs:
 *y: A Tensor. Has the same type and format as input "x".
 *argmax:  A Tensor. type:uint16, format:NC1HWC0.
 *@attention Constraints:
 *@li "ksize" is a list that has length 4: ksize[0] = 1 or ksize[3] = 1, ksize[1] * ksize[2] <= 255.
 *@li "strides is a list that has length 4: strides[0] = 1 or strides[3] = 1, strides[1] <= 63, strides[0] >= 1,
 * strides[2] <= 63, strides[2] >= 1.
 *@li "dilation" is a list that has length 4.
 *@li "ceil_mode" is a bool, default is false.
 *@par Third-party framework compatibility
 * Compatible with the TensorFlow operator MaxPoolWithArgmax.
 */
 REG_OP(MaxPoolWithArgmaxV2)
    .INPUT(x, TensorType({DT_FLOAT16}))
    .OUTPUT(y, TensorType({DT_FLOAT16}))
    .OUTPUT(argmax, TensorType({DT_UINT16}))
    .REQUIRED_ATTR(ksize, ListInt)
    .REQUIRED_ATTR(strides, ListInt)
    .REQUIRED_ATTR(pads, ListInt)
    .ATTR(dtype, Int, 3)
    .ATTR(dilation, ListInt, {1, 1, 1, 1})
    .ATTR(ceil_mode, Bool, false)
    .OP_END_FACTORY_REG(MaxPoolWithArgmaxV2)
 /**
 *@brief Performs the backpropagation of MaxPoolWithArgmaxV2.
 *@par Inputs:
 * Three inputs, including:
 *@li x: An NC1HWC0 tensor of type float16.
 *@li grad: An NC1HWC0 tensor of type float16.
 *@li argmx: An NC1HWC0 tensor of type uint16 or int64.
 *@par Attributes:
 *@li ksize: A required list of int8, int16, int32, or int64 values, specifying the size of the window for
 * each dimension of the input tensor. No default value.
 *@li strides: A required list of int8, int16, int32, or int64 values, specifying the stride of the sliding window for
 * each dimension of the input tensor. No default value.
 *@li pads: A required string. No default value.
 *@li dtype: A optional int. default value is 3.
 *@li dilation: A optional list of int8, int16, int32, or int64 values.
 *@li ceil_mode: A optional bool. default value is false.
 *@par Outputs:
 *y: A Tensor. Has the same type and format as input "x".
 *@attention Constraints:
 *@li "ksize" is a list that has length 4: ksize[0] = 1 or ksize[3] = 1, ksize[1] * ksize[2] <= 255.
 *@li "strides" is a list that has length 4: strides[0] = 1 or strides[3] = 1
 *@li "dilation" is a list that has length 4.
 *@li "ceil_mode" is a bool, default is false.
 *@see max_pool_grad_with_argmaxv2
 *@par Third-party framework compatibility
 * Compatible with the TensorFlow operator MaxPoolGradWithArgmaxV2.
 */
 REG_OP(MaxPoolGradWithArgmaxV2)
    .INPUT(x, TensorType({DT_FLOAT16}))
    .INPUT(grad, TensorType({DT_FLOAT16}))
    .INPUT(argmax, TensorType({DT_UINT16}))
    .OUTPUT(y, TensorType({DT_FLOAT16}))
    .REQUIRED_ATTR(ksize, ListInt)
    .REQUIRED_ATTR(strides, ListInt)
    .REQUIRED_ATTR(pads, ListInt)
    .ATTR(dtype, Int, 3)
    .ATTR(dilation, ListInt, {1,1,1,1})
    .ATTR(ceil_mode, Bool, false)
    .OP_END_FACTORY_REG(MaxPoolGradWithArgmaxV2)
 }  // namespace ge
 #endif  // GE_OP_NN_POOLING_OPS_H
--- a/third_party/fwkacllib/inc/ops/nn_training_ops.h
+++ b/third_party/fwkacllib/inc/ops/nn_training_ops.h
@@ -1508,7 +1508,7 @@ REG_OP(ApplyProximalAdagradD)
 *@par Attributes:
 *use_locking: An optional bool. Defaults to "False".\n
 *     If "True", updating of the var and accum tensors will be protected by a lock; \n
 *     If "False", the behavior is undefined, but may exhibit less contention. 
 *     If "False", the behavior is undefined, but may exhibit less contention.
 *@par Outputs:
 *var: A mutable Tensor. Has the same type as "var".
--- a/third_party/fwkacllib/inc/ops/nonlinear_fuc_ops.h
+++ b/third_party/fwkacllib/inc/ops/nonlinear_fuc_ops.h
@@ -83,7 +83,7 @@ REG_OP(TanhGrad)
 *@par Inputs:
 *One input:
 *x: A Tensor. Must be one of the following types: float16, float32, complex64, complex128, double.
 *x: A Tensor. Must be one of the following types: float16, float32, complex64, complex128, int32, int64
 *@par Outputs:
 *y: A Tensor. Has the same type as "x".
@@ -184,7 +184,7 @@ REG_OP(Relu6Grad)
 * @brief Compute sigmoid of "x" element-wise.
 * @par Inputs:
 * A Tensor of type complex64, complex128, float16, float32 or double.
 * A Tensor of type UnaryDataType.
 * @par Outputs:
 * A Tensor. Has the same type as "x".
@@ -220,7 +220,7 @@ REG_OP(SigmoidGrad)
 *if x>0, x+log(1+exp(-x)); otherwise log(1+exp(x)).
 *@par Inputs:
 *x: A Tensor of type double, float16 or float32.
 *x: A Tensor of type float16 or float32.
 *@par Outputs:
 *y: A tensor. Has the same type and format as input "x".
@@ -442,7 +442,7 @@ REG_OP(PReluGrad)
 *x: A float16, float32 or double, for the input data type.
 *@par Attributes:
 *alpha: A float32. Defines at which negative value the ELU saturates. Defaults to "1.0".
 *alpha: A float. Defines at which negative value the ELU saturates. Defaults to "1.0".
 *@par Outputs:
 *y: A float16, float32 or double, for the normalized result.
--- a/third_party/fwkacllib/inc/ops/reduce_ops.h
+++ b/third_party/fwkacllib/inc/ops/reduce_ops.h
@@ -673,7 +673,7 @@ REG_OP(ReduceAnyD)
 *@par Attributes:
 *@li operation: An optional int32 from 1(SUM), 2(ASUM), 3(SUMSQ), and 4(MEAN), 
 *specifying the reduction algorithm. Defaults to "1".
 *specifying the reduction algorithm. Defaults to 1.
 *@li axis: An optional int32, specifying the first axis to reduce. Defaults to "0". 
 *The value range is [-N, N-1], where N is the input tensor rank.
 *@li coeff: An optional float32, specifying the scale coefficient. Defaults to "1.0".
@@ -745,190 +745,7 @@ REG_OP(EuclideanNormD)
    .ATTR(keep_dims, Bool, false)
    .OP_END_FACTORY_REG(EuclideanNormD)
 /**
 *@brief Performs instance normalization for inference.
 *@par Inputs:\n
 * Five inputs, including: (NC1HWC0 supported)
 *@li x: A Tensor of type float16 or float32.
 *@li gamma: A [N, C1, 1, 1, C0] Tensor of type float32, for the scaling gamma.
 *@li beta: A [N, C1, 1, 1, C0] Tensor of type float32, for the scaling beta.
 *@li mean: A [N, C1, 1, 1, C0] ensor of type float32, for the mean.
 *@li variance: A [N, C1, 1, 1, C0] Tensor of type float32, for the variance.
 *@par Attributes:
 *epsilon: An optional float32, specifying the small value added to variance to avoid dividing by zero. 
 Defaults to "0.00001".
 *@par Outputs:\n
 *y: A Tensor of type float16 or float32 for the normalized "x".
 *batch_mean: A Tensor of type float32 for the result mean.
 *batch_ variance: A Tensor of type float32 for the result variance.
 *@attention Constraints:
 *For Ascend 310, the result accuracy fails to reach 1‰ due to the square root instruction.
 */
 REG_OP(INInferV2)
    .INPUT(x, TensorType({DT_FLOAT16,DT_FLOAT}))
    .OPTIONAL_INPUT(gamma, TensorType({DT_FLOAT}))
    .OPTIONAL_INPUT(beta, TensorType({DT_FLOAT}))
    .OPTIONAL_INPUT(mean, TensorType({DT_FLOAT}))
    .OPTIONAL_INPUT(variance, TensorType({DT_FLOAT}))
    .ATTR(epsilon, Float, 0.00001)
    .OUTPUT(y, TensorType({DT_FLOAT16,DT_FLOAT}))
    .OUTPUT(batch_mean, TensorType({DT_FLOAT}))
    .OUTPUT(batch_variance, TensorType({DT_FLOAT}))
    .OP_END_FACTORY_REG(INInferV2)
 /**
 *@brief Performs reduced instance normalization.
 *@par Inputs:\n
 *x: A Tensor of type float16 or float32, with format NC1HWC0.
 *@par Outputs:
 *@li sum: A Tensor of type float32 for SUM reduced "x".
 *@li square_sum: A Tensor of type float32 for SUMSQ reduced "x".
 *@attention Constraints:\n
 * This operator is a InstanceNorm fusion operator for updating the moving averages for training. \n 
 * This operator is used in conjunction with INTrainingUpdateV2.
 */
 REG_OP(INTrainingReduceV2)
    .INPUT(x, TensorType({DT_FLOAT16,DT_FLOAT}))
    .OUTPUT(sum, TensorType({DT_FLOAT}))
    .OUTPUT(square_sum, TensorType({DT_FLOAT}))
    .OP_END_FACTORY_REG(INTrainingReduceV2)
 /**
 *@brief Performs update instance normalization.
 *@par Inputs:\n
 * Seven inputs, including: (NC1HWC0supported)
 *@li x: A Tensor of type float16 or float32.
 *@li sum: A T [N, C1, 1, 1, C0] ensor of type float32 for the output of operator INTrainingReduceV2.
 *@li square_sum: A  [N, C1, 1, 1, C0] Tensor of type float32 for the output of operator INTrainingReduceV2.
 *@li gamma: A  [N, C1, 1, 1, C0] Tensor of type float32, for the scaling gamma.
 *@li beta: A  [N, C1, 1, 1, C0] Tensor of type float32, for the scaling beta.
 *@li mean: A  [N, C1, 1, 1, C0] Tensor of type float32, for the updated mean.
 *@li variance: A  [N, C1, 1, 1, C0] Tensor of type float32, for the updated variance.
 *@par Attributes:
 *@li momentum: A required float32, specifying the momentum to update mean and var.
 *@li epsilon: A required float32, specifying the small value added to variance to avoid dividing by zero.
 *@par Outputs:\n
 * Three outputs, including: (NC1HWC0 supported)
 *@li y: A Tensor of type float16 or float32, for normalized "x".
 *@li batch_mean: A Tensor of type float32, for the updated mean.
 *@li batch_variance: A Tensor of type float32, for the updated variance.
 *@attention Constraints:
 *@li This operator is a InstanceNorm fusion operator for updating the moving averages for training. \n 
 * This operator is used in conjunction with INTrainingReduceV2.
 *@li For Ascend 310, the result accuracy fails to reach 1‰ due to the square root instruction.
 */
 REG_OP(INTrainingUpdateV2)
    .INPUT(x, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(sum, TensorType({DT_FLOAT}))
    .INPUT(square_sum, TensorType({DT_FLOAT}))
    .OPTIONAL_INPUT(gamma, TensorType({DT_FLOAT}))
    .OPTIONAL_INPUT(beta, TensorType({DT_FLOAT}))
    .OPTIONAL_INPUT(mean, TensorType({DT_FLOAT}))
    .OPTIONAL_INPUT(variance, TensorType({DT_FLOAT}))
    .ATTR(momentum, Float, 0.1)
    .ATTR(epsilon, Float, 0.00001)
    .OUTPUT(y, TensorType({DT_FLOAT16,DT_FLOAT}))
    .OUTPUT(batch_mean, TensorType({DT_FLOAT}))
    .OUTPUT(batch_variance, TensorType({DT_FLOAT}))
    .OP_END_FACTORY_REG(INTrainingUpdateV2)
 /**
 *@brief Performs reduced group normalization.
 *@par Inputs:\n
 *x: A Tensor of type float16 or float32, with format NCHW NHWC.
 *@par Outputs:
 *@li sum: A Tensor of type float32 for SUM reduced "x".
 *@li square_sum: A Tensor of type float32 for SUMSQ reduced "x".
 *@par Attributes:
 *@li num_groups: Int, specifying the num of groups. required, same to GNTrainingUpdate.
 *@attention Constraints:\n
 * This operator is a GroupNorm fusion operator for updating the moving averages for training. \n 
 * This operator is used in conjunction with GNTrainingUpdate.
 */
 REG_OP(GNTrainingReduce)
    .INPUT(x, TensorType({DT_FLOAT16,DT_FLOAT}))
    .OUTPUT(sum, TensorType({DT_FLOAT}))
    .OUTPUT(square_sum, TensorType({DT_FLOAT}))
    .ATTR(num_groups, Int, 2)
    .OP_END_FACTORY_REG(GNTrainingReduce)
 /**
 *@brief Performs update group normalization.
 *@par Inputs:\n
 * Eight inputs, including: (NCHW NHWC supported)
 *@li x: A Tensor of type float16 or float32.
 *@li sum: A 5D Tensor of type float32, 
 shape is [N, G, D, 1, 1] for NCHW, [N, 1, 1, G, D] for NHWC
 for the output of operator GNTrainingReduce.
 *@li square_sum: A 5D Tensor of type float32, 
 shape is [N, G, D, 1, 1] for NCHW, [N, 1, 1, G, D] for NHWC
 for the output of operator GNTrainingReduce.
 *@li scale: A 5D Tensor of type float32, 
 shape is [1, G, D, 1, 1] for NCHW, [1, 1, 1, G, D] for NHWC
 is for the scaling gamma.
 *@li offset: A 5D Tensor of type float32, 
 shape is [1, G, D, 1, 1] for NCHW, [1, 1, 1, G, D] for NHWC
 for the scaling beta.
 *@li mean: A 5D Tensor of type float32, 
 shape is [N, G, D, 1, 1] for NCHW, [N, 1, 1, G, D] for NHWC
 for the updated mean.
 *@li variance: A 5D Tensor of type float32, 
 shape is [N, G, D, 1, 1] for NCHW, [N, 1, 1, G, D] for NHWC
 for the updated variance.
 *@par Attributes:
 *@li epsilon: A float32, specifying the small value added to variance to avoid dividing by zero.
 *@li num_groups: Int, specifying the num of groups. required, same to GNTrainingReduce
 *@par Outputs:\n
 * Three outputs, including: (NC1HWC0 supported)
 *@li y: A Tensor of type float16 or float32, for normalized "x".
 *@li batch_mean: A Tensor of type float32, for the updated mean.
 *@li batch_variance: A Tensor of type float32, for the updated variance.
 *@attention Constraints:
 *@li This operator is a InstanceNorm fusion operator for updating the moving averages for training. \n 
 * This operator is used in conjunction with GNTrainingUpdate.
 *@li For Ascend 310, the result accuracy fails to reach 1‰ due to the square root instruction.
 */
 REG_OP(GNTrainingUpdate)
    .INPUT(x, TensorType({DT_FLOAT16,DT_FLOAT}))
    .INPUT(sum, TensorType({DT_FLOAT}))
    .INPUT(square_sum, TensorType({DT_FLOAT}))
    .OPTIONAL_INPUT(scale, TensorType({DT_FLOAT}))
    .OPTIONAL_INPUT(offset, TensorType({DT_FLOAT}))
    .OPTIONAL_INPUT(mean, TensorType({DT_FLOAT}))
    .OPTIONAL_INPUT(variance, TensorType({DT_FLOAT}))
    .ATTR(num_groups, Int, 2)
    .ATTR(epsilon, Float, 0.0001)
    .OUTPUT(y, TensorType({DT_FLOAT16,DT_FLOAT}))
    .OUTPUT(batch_mean, TensorType({DT_FLOAT}))
    .OUTPUT(batch_variance, TensorType({DT_FLOAT}))
    .OP_END_FACTORY_REG(GNTrainingUpdate)
 } //namespace ge
 #endif /* GE_OP_REDUCE_OPS_H */
--- a/third_party/fwkacllib/inc/ops/rnn.h
+++ b/third_party/fwkacllib/inc/ops/rnn.h
@@ -67,13 +67,6 @@ REG_OP(BasicLSTMCell)
    .ATTR(activation, String, "tanh")
    .OP_END_FACTORY_REG(BasicLSTMCell)
 REG_OP(DynamicLSTM)
    .INPUT(x, TensorType({DT_FLOAT32}))
    .INPUT(w, TensorType({DT_FLOAT32}))
    .INPUT(b, TensorType({DT_FLOAT32}))
    .OUTPUT(output_h, TensorType({DT_FLOAT32}))
    .OP_END_FACTORY_REG(DynamicLSTM)
 /**
 *@brief: Basic LSTM Cell backward calculation.Calculate the gradient of input and hidden state.
 *@par Inputs:
@@ -94,7 +87,7 @@ REG_OP(BasicLSTMCellInputGrad)
    .INPUT(dgate, TensorType({DT_FLOAT16}))
    .INPUT(w, TensorType({DT_FLOAT16}))
    .OPTIONAL_INPUT(dropout_mask, TensorType({DT_UINT8}))
    .OUTPUT(dxt, TensorType({DT_FLOAT16, DT_FLOAT32}))
    .OUTPUT(dxt, TensorType({DT_FLOAT16}))
    .OUTPUT(dht, TensorType({DT_FLOAT16, DT_FLOAT32}))
    .ATTR(keep_prob, Float, 1.0)
    .OP_END_FACTORY_REG(BasicLSTMCellInputGrad)
--- a/third_party/fwkacllib/inc/ops/selection_ops.h
+++ b/third_party/fwkacllib/inc/ops/selection_ops.h
@@ -89,8 +89,7 @@ REG_OP(RangeD)
 *@par Inputs:
 *Two inputs, including:
 * @li x: A Tensor. 
 * Must be one of the following types: float16, float32, double, int64, int32, uint8, uint16, uint32, uint64, int8, int16, complex64, complex128, qint8, quint8, qint16, quint16, qint32. 
 * @li x: A Tensor of type TensorType::BasicType().
 * @li multiples: A 1D Tensor of type int32 or int64.
 *     The length must be the same as the number of dimensions in "input"
@@ -497,7 +496,7 @@ REG_OP(UnsortedSegmentSumD)
 *@par Inputs:
 * Two inputs, including:\n
 *@li x: An ND Tensor (up to 8D). \n
 *Must be one of the following types: int8, uint8, int16, uint16, int32, int64, bool, float16, float32, double, complex64, complex128, string.
 *Must be one of the following types: int8, uint8, int16, uint16, int32, int64, bool, float32, double
 *@li axis: A 1D Tensor.\n
 *Must be one of the following types: int32, int64
@@ -1560,14 +1559,14 @@ REG_OP(ProposalD)
 * If reverse=false: (N, H, W, C)->(N, H/stride, W/stride, C*(stride*stride))
 *@par Inputs:
 *x: An (N, H, W, C) tensor. Type is float16, float32, int8, uint8, int16, uint16, int32, uint32, int64 or uint64..
 *x: An (N, H, W, C) tensor. All types except double are supported.
 *@par Attributes:
 *@li stride: An optional int32, specifying the plane or channel scaling factor. Defaults to "2".
 *@li reverse: An optional bool, specifying the conversion mode. If "true", depth to space conversion is performed. If "false", space to depth conversion is performed. Defaults to "false".
 *@par Outputs:
 *y: An (N, H, W, C) tensor. Has same type as "x".
 *y: An (N, H, W, C) tensor. All types except double are supported.
 *@attention Constraints:
 *@li If reverse=true: C/(stride*stride) yields an integer result. If reverse=false: W/stride and H/stride yield integer results.
@@ -1594,7 +1593,7 @@ REG_OP(PassThrough)
 * @li x: A required Tensor. Must be one of the following types: float16, float32, int8, uint8, int16, uint16, int32, uint32,int64, uint64.
 * @li size: A required Tensor. Must be one of the following types: float16, float32, int8, uint8, int16, uint16, int32, uint32, int64, uint64.
 *@par Attributes:
 *@li axis: A required int32, specifying the first dimension to crop. Defaults to "2".
 *@li axis: A required int32, specifying the first dimension to crop.
 *@li offset: A required array, specifying the shift for all/each dimension to align the cropped bottom with the reference bottom. Must be one of the following types: float16, float32, int8, uint8, int16, uint16, int32, uint32, int64, uint64.
 *@par Outputs:
 *y: A required Tensor. Has the same type and shape as "size".
--- a/third_party/fwkacllib/inc/ops/split_combination_ops.h
+++ b/third_party/fwkacllib/inc/ops/split_combination_ops.h
@@ -25,11 +25,11 @@ namespace ge {
 *@par Inputs:
 * Two inputs, including:
 *@li x: An ND Tensor.
 *Must be one of the types:float16, float32, double, int64, int32, uint8, uint16, uint32, uint64, int8, int16, complex64, complex128, qint8, quint8, qint16, quint16, qint32. 
 *Must be one of the following types: float16, float32, int32, int8, int16, int64, uint8, uint16, uint32, uint64
 *@li split_dim: Must be the following type:int32. Specifies the dimension along which to split.
 *@par Attributes:
 *num_split: A required int32. Specifies the number of output tensors. No default value.
 *num_split: A required int8, int16, int32, or int64. Specifies the number of output tensors. No default value.
 *@par Outputs:
 *y: Dynamic output.A list of output tensors. Has the same type and format as "x".
@@ -186,7 +186,6 @@ REG_OP(ParallelConcat)
 *@par Attributes:
 *concat_dim: A required int8, int16, int32, or int64. Specifies the dimension along which to concatenate. No default value.
 *N: An attribute int8, int16, int32, or int64. Specifies the number of elements in "x". Defaults to "1". 
 *@par Outputs:
 *y: A Tensor. Has the same type and format as "x".
@@ -268,9 +267,7 @@ REG_OP(ConcatD)
 *@par Inputs:
 * Two inputs, including:
 *@li x: Dynamic input.An NC1HWC0 or ND Tensor.
 *Must be one of the following types: float16, float32, double, int32,
 *     uint8, int16, int8, complex64, int64, qint8, quint8, qint32, uint16,
 *     complex128, uint32, uint64, qint16, quint16.
 *Must be one of the following types: float16, float32, int32, int8, int16, int64, uint8, uint16, uint32, uint64
 *@li concat_dim: An int32, or int64. Specifies the dimension along which to concatenate.
 *@par Attributes:
--- a/third_party/fwkacllib/inc/ops/transformation_ops.h
+++ b/third_party/fwkacllib/inc/ops/transformation_ops.h
@@ -94,13 +94,6 @@ REG_OP(Transpose)
    .OUTPUT(y, TensorType::BasicType())
    .OP_END_FACTORY_REG(Transpose)
 REG_OP(TransData)
    .INPUT(src, TensorType::BasicType())
    .OUTPUT(dst, TensorType::BasicType())
    .REQUIRED_ATTR(src_format, String)
    .REQUIRED_ATTR(dst_format, String)
    .OP_END_FACTORY_REG(TransData)
 /**
 *@brief Permutes the dimensions according to order.\n
        The returned tensor's dimension i will correspond to the input dimension order[i].
@@ -109,7 +102,7 @@ REG_OP(TransData)
 *x: A Tensor. Must be one of the following types: float16, float32.
 *@par Attributes:
 *order: A permutation of the dimensions of "x".Type is int32.support any axis transformation.Defaults to "{0}"
 *order: A permutation of the dimensions of "x".support any axis transformation
 *@par Outputs:
 *y: A Tensor. Has the same type as "x".
@@ -298,7 +291,7 @@ REG_OP(DepthToSpace)
 *@brief Permutes data into spatial data blocks and then prunes them.
 *@par Inputs:
 *@li x: A 4D Tensor with format NHWC.
 *@li x: A 4D Tensor with format NC1HWC0.
 *@li crops: A 1D list or tuple of int32 or int64.
 *Must be one of the following types: float16, float32
@@ -307,7 +300,7 @@ REG_OP(DepthToSpace)
 *block_size: A required int8, int16, int32, or int64. No default value.
 *@par Outputs:
 *y: A 4D Tensor with format NHWC,
 *y: A 4D Tensor with format NC1HWC0,
 * of type float16 or float32.
@@ -372,7 +365,7 @@ REG_OP(BatchToSpaceD)
 *@par Inputs:
 * Two inputs, including:
 *@li x: An NHWC Tensor. Must be one of the following types:
 *@li x: An NC1HWC0 Tensor. Must be one of the following types:
 * float16, float32, double, int64, int32, uint8, uint16, uint32, uint64, int8,
 * int16, complex64, complex128, qint8, quint8, qint16, quint16, qint32.
 *@li paddings: A 2D tensor of type int, specifying the input.
@@ -396,7 +389,7 @@ REG_OP(SpaceToBatch)
 *@brief Outputs a copy of the input tensor where values from the "height" and "width" dimensions are padded and rearranged to the "batch" dimension.
 *@par Inputs:
 *x: An NHWC Tensor. Must be one of the following types: float16, float32, double, int64, int32, uint8, uint16, uint32, uint64, int8, int16, complex64, complex128, qint8, quint8, qint16, quint16, qint32.
 *x: An NC1HWC0 Tensor. Must be one of the following types: float16, float32, double, int64, int32, uint8, uint16, uint32, uint64, int8, int16, complex64, complex128, qint8, quint8, qint16, quint16, qint32.
 *@par Attributes:
@@ -605,13 +598,6 @@ REG_OP(Compress)
    .OUTPUT(compress_index, TensorType({DT_INT8}))
    .REQUIRED_ATTR(compress_parameters, ListInt)
    .OP_END_FACTORY_REG(Compress)
 REG_OP(CompressFcOp)
    .INPUT(weight, TensorType({DT_INT8}))
    .OUTPUT(weight_compress, TensorType({DT_INT8}))
    .OUTPUT(compress_index, TensorType({DT_INT8}))
    .REQUIRED_ATTR(compress_parameters, ListInt)
    .OP_END_FACTORY_REG(CompressFcOp)
 }  // namespace ge
 #endif  // GE_OP_TRANSFORMATION_OPS_H