mindspore 2.5.0__cp311-cp311-win_amd64.whl → 2.6.0__cp311-cp311-win_amd64.whl

mindspore/train/loss_scale_manager.py

@@ -51,9 +51,10 @@ class FixedLossScaleManager(LossScaleManager):
     inherits from :class:`mindspore.amp.LossScaleManager`.
 
     Args:
-        loss_scale (float): Magnification factor of gradients. Note that if `drop_overflow_update` is set to ``False`` ,
+        loss_scale (float, optional): Magnification factor of gradients.
+            Note that if `drop_overflow_update` is set to ``False`` ,
             the value of `loss_scale` in optimizer should be set to the same as here. Default: ``128.0`` .
-        drop_overflow_update (bool): Whether to execute optimizer if there is an overflow.
+        drop_overflow_update (bool, optional): Whether to execute optimizer if there is an overflow.
             If ``True`` , the optimizer will
             not executed when overflow occurs. Default: ``True`` .
 
@@ -110,8 +111,8 @@ class FixedLossScaleManager(LossScaleManager):
 
         Returns:
             None or :class:`mindspore.nn.FixedLossScaleUpdateCell`. Instance of
-            :class:`mindspore.nn.FixedLossScaleUpdateCell` when `drop_overflow_update` is True. None when
-            `drop_overflow_update` is False.
+            :class:`mindspore.nn.FixedLossScaleUpdateCell` when `drop_overflow_update` is ``True``. None when
+            `drop_overflow_update` is ``False``.
         """
         if not self._drop_overflow_update:
             return None
@@ -124,9 +125,9 @@ class DynamicLossScaleManager(LossScaleManager):
     adjusted, inherits from :class:`mindspore.amp.LossScaleManager`.
 
     Args:
-        init_loss_scale (float): Initialize loss scale. Default: ``2 ** 24`` .
-        scale_factor (int): Coefficient of increase and decrease. Default: ``2`` .
-        scale_window (int): Maximum continuous normal steps when there is no overflow. Default: ``2000`` .
+        init_loss_scale (float, optional): Initialize loss scale. Default: ``2 ** 24`` .
+        scale_factor (int, optional): Coefficient of increase and decrease. Default: ``2`` .
+        scale_window (int, optional): Maximum continuous normal steps when there is no overflow. Default: ``2000`` .
 
     Supported Platforms:
         ``Ascend`` ``GPU``

mindspore/train/metrics/accuracy.py

@@ -45,11 +45,11 @@ class Accuracy(EvaluationBase):
         >>> from mindspore import Tensor
         >>> from mindspore.train import Accuracy
         >>>
-        >>> x = Tensor(np.array([[0.2, 0.5], [0.3, 0.1], [0.9, 0.6]]), mindspore.float32)
-        >>> y = Tensor(np.array([1, 0, 1]), mindspore.float32)
+        >>> y_pred = Tensor(np.array([[0.2, 0.5], [0.3, 0.1], [0.9, 0.6]]), mindspore.float32)
+        >>> y_true = Tensor(np.array([1, 0, 1]), mindspore.float32)
         >>> metric = Accuracy('classification')
         >>> metric.clear()
-        >>> metric.update(x, y)
+        >>> metric.update(y_pred, y_true)
         >>> accuracy = metric.eval()
         >>> print(accuracy)
         0.6666666666666666

mindspore/train/metrics/confusion_matrix.py

@@ -23,15 +23,15 @@ from mindspore.train.metrics.metric import Metric, rearrange_inputs
 
 class ConfusionMatrix(Metric):
     """
-    Computes the confusion matrix, which is commonly used to evaluate the performance of classification models,
+    Computes the Confusion Matrix, which is commonly used to evaluate the performance of classification models,
     including binary classification and multiple classification.
 
-    If you only need confusion matrix, use this class. If you want to calculate other metrics, such as 'PPV',
+    If you only need Confusion Matrix, use this class. If you want to calculate other metrics, such as 'PPV',
     'TPR', 'TNR', etc., use class :class:`mindspore.train.ConfusionMatrixMetric` .
 
     Args:
         num_classes (int): Number of classes in the dataset.
-        normalize (str): Normalization mode for confusion matrix. Default: ``"no_norm"`` . Choose from:
+        normalize (str): Normalization mode for Confusion Matrix. Default: ``"no_norm"`` . Choose from:
 
             - ``"no_norm"`` : No Normalization is used. Default: ``None``.
             - ``"target"`` : Normalization based on target value.
@@ -78,7 +78,7 @@ class ConfusionMatrix(Metric):
     @rearrange_inputs
     def update(self, *inputs):
         """
-        Update state with y_pred and y.
+        Update state with `y_pred` and `y`.
 
         Args:
             inputs(tuple): Input `y_pred` and `y`. `y_pred` and `y` are a `Tensor`, list or numpy.ndarray.
@@ -88,7 +88,7 @@ class ConfusionMatrix(Metric):
 
         Raises:
             ValueError: If the number of inputs is not 2.
-            ValueError: If the dim of y_pred and y are not equal.
+            ValueError: If the dims of `y_pred` and `y` are not equal.
         """
         if len(inputs) != 2:
             raise ValueError("For 'ConfusionMatrix.update', it needs 2 inputs (predicted value, true value), "
@@ -151,8 +151,8 @@ class ConfusionMatrixMetric(Metric):
     batch, class channel and iteration are collected. All metrics supported by the interface are listed in comments
     of `metric_name`.
 
-    If you want to calculate metrics related to confusion matrix, such as 'PPV', 'TPR', 'TNR', use this class.
-    If you only want to calculate confusion matrix, please use :class:`mindspore.train.ConfusionMatrix` .
+    - If you want to calculate metrics related to confusion matrix, such as 'PPV', 'TPR', 'TNR', use this class.
+    - If you only want to calculate confusion matrix, please use :class:`mindspore.train.ConfusionMatrix` .
 
     Args:
         skip_channel (bool): Whether to skip the measurement calculation on the first channel of the predicted output.
@@ -163,9 +163,9 @@ class ConfusionMatrixMetric(Metric):
                            "threat score", "accuracy", "balanced accuracy", "f1 score",
                            "matthews correlation coefficient", "fowlkes mallows index", "informedness", "markedness"].
                            Default: ``"sensitivity"`` .
-        calculation_method (bool): If true, the measurement for each sample will be calculated first.
+        calculation_method (bool): If ``True``, the measurement for each sample will be calculated first.
                            If not, the confusion matrix of all samples will be accumulated first.
-                           As for classification task, 'calculation_method' should be False. Default: ``False`` .
+                           As for classification task, 'calculation_method' should be ``False``. Default: ``False`` .
         decrease (str): The reduction method on data batch. `decrease` takes effect only when calculation_method
                         is True. Default: ``"mean"`` . Choose from:
                         ["none", "mean", "sum", "mean_batch", "sum_batch", "mean_channel", "sum_channel"].

mindspore/train/metrics/error.py

@@ -25,7 +25,7 @@ class MAE(Metric):
     Calculates the mean absolute error(MAE).
 
     Creates a criterion that measures the MAE between each element
-    in the input: :math:`x` and the target: :math:`y`.
+    in the input: :math:`y\_pred` and the target: :math:`y`.
 
     .. math::
         \text{MAE} = \frac{\sum_{i=1}^n \|{y\_pred}_i - y_i\|}{n}
@@ -142,8 +142,8 @@ class MSE(Metric):
         Updates the internal evaluation result :math:`y_{pred}` and :math:`y`.
 
         Args:
-            inputs: Input `y_pred` and `y` for calculating the MSE where the shape of
-                `y_pred` and `y` are both N-D and the shape should be the same.
+            inputs: Input :math:`y_pred` and :math:`y` for calculating the MSE where the shape of
+                :math:`y_pred` and :math:`y` are both N-D and the shape should be the same.
 
         Raises:
             ValueError: If the number of inputs is not 2.

mindspore/train/metrics/hausdorff_distance.py

@@ -84,7 +84,7 @@ class HausdorffDistance(Metric):
     :math:`h(A, B)` is not equal to :math:`h(B, A)`. :math:`H(A, B)` is the two-way Hausdorff distance.
 
     Args:
-        distance_metric (string): Three distance measurement methods are supported:
+        distance_metric (str): Three distance measurement methods are supported:
                     ``"euclidean"`` (Euclidean Distance) ,  ``"chessboard"`` (Chessboard Distance, Chebyshev Distance)
                     or  ``"taxicab"`` (Taxicab Distance, Manhattan Distance). Default: ``"euclidean"`` .
         percentile (float): Floating point numbers between 0 and 100. Specify the percentile parameter to get the
@@ -270,9 +270,9 @@ class HausdorffDistance(Metric):
 
         Raises:
             ValueError: If the number of the inputs is not 3.
-            TypeError: If the data type of label_idx is not int or float.
-            ValueError: If the value of label_idx is not in y_pred or y.
-            ValueError: If y_pred and y have different shapes.
+            TypeError: If the data type of `label_idx` is not int or float.
+            ValueError: If the value of `label_idx` is not in `y_pred` or `y`.
+            ValueError: If `y_pred` and `y` have different shapes.
         """
         self._is_update = True
 

mindspore/train/metrics/mean_surface_distance.py

@@ -49,7 +49,7 @@ class MeanSurfaceDistance(Metric):
         \left | S(B) \right |}
 
     Args:
-        distance_metric (string): Three measurement methods are supported: ``"euclidean"`` (Euclidean Distance) ,
+        distance_metric (str): Three measurement methods are supported: ``"euclidean"`` (Euclidean Distance) ,
                                 ``"chessboard"`` (Chessboard Distance, Chebyshev Distance) or
                                 ``"taxicab"`` (Taxicab Distance, Manhattan Distance) Default: ``"euclidean"`` .
         symmetric (bool): Whether to calculate the Mean Surface Distance between y_pred and y.
@@ -125,8 +125,8 @@ class MeanSurfaceDistance(Metric):
         Raises:
             ValueError: If the number of the inputs is not 3.
             TypeError: If the data type of label_idx is not int or float.
-            ValueError: If the value of label_idx is not in y_pred or y.
-            ValueError: If y_pred and y have different shapes.
+            ValueError: If the value of label_idx is not in `y_pred` or `y`.
+            ValueError: If `y_pred` and `y` have different shapes.
         """
         if len(inputs) != 3:
             raise ValueError("For 'MeanSurfaceDistance.update', it needs 3 inputs (predicted value, true value, "

mindspore/train/metrics/metric.py

@@ -197,10 +197,6 @@ class Metric(metaclass=ABCMeta):
 
         Note:
             All subclasses must override this interface.
-
-        Tutorial Examples:
-            - `Evaluation Metrics - Customized Metrics
-              <https://mindspore.cn/docs/en/master/model_train/train_process/model/metric.html#customized-metrics>`_
         """
         raise NotImplementedError('Must define clear function to use this base class')
 
@@ -211,10 +207,6 @@ class Metric(metaclass=ABCMeta):
 
         Note:
             All subclasses must override this interface.
-
-        Tutorial Examples:
-            - `Evaluation Metrics - Customized Metrics
-              <https://mindspore.cn/docs/en/master/model_train/train_process/model/metric.html#customized-metrics>`_
         """
         raise NotImplementedError('Must define eval function to use this base class')
 
@@ -228,10 +220,6 @@ class Metric(metaclass=ABCMeta):
 
         Args:
             inputs: A variable-length input argument list, usually are the logits and the corresponding labels.
-
-        Tutorial Examples:
-            - `Evaluation Metrics - Customized Metrics
-              <https://mindspore.cn/docs/en/master/model_train/train_process/model/metric.html#customized-metrics>`_
         """
         raise NotImplementedError('Must define update function to use this base class')
 

mindspore/train/metrics/occlusion_sensitivity.py

@@ -36,12 +36,14 @@ class OcclusionSensitivity(Metric):
     most important for a network's classification.
 
     Occlusion sensitivity refers to how the predicted probability changes with the change of the occluded
-    part of an image. The higher the value in the output image is, the greater the decline of certainty, indicating
+    part of an image. The higher the value in the output image is, the greater the certainty decline
+    of the category after masking, indicating
     that the occluded area is more important in the decision-making process.
 
     Args:
         pad_val (float): The padding value of the occluded part in an image. Default: ``0.0`` .
-        margin (Union[int, Sequence]): Create a cuboid / cube around the voxel you want to occlude. Default: ``2`` .
+        margin (Union[int, Sequence]): Create a cuboid / cube size of pixel points
+                                       around the voxel you want to occlude. Default: ``2`` .
         n_batch (int): number of images in a batch. Default: ``128`` .
         b_box (Sequence): Bounding box on which to perform the analysis. The output image will also match in size.
                           There should be a minimum and maximum for all dimensions except batch:

mindspore/train/metrics/precision.py

@@ -74,18 +74,20 @@ class Precision(EvaluationBase):
     @rearrange_inputs
     def update(self, *inputs):
         """
-        Updates the internal evaluation result with `y_pred` and `y`. In the multi-label cases, the elements of
+        Updates the internal evaluation result with :math:`y_pred` and :math:`y`.
+        In the multi-label cases, the elements of
         :math:`y` and :math:`y_pred` must be 0 or 1.
 
         Args:
-            inputs: Input `y_pred` and `y`. `y_pred` and `y` are Tensor, list or numpy.ndarray.
-                For 'classification' evaluation type, `y_pred` is in most cases (not strictly) a list
+            inputs: Input :math:`y_pred` and :math:`y`. :math:`y_pred` and :math:`y`
+                are Tensor, list or numpy.ndarray.
+                For 'classification' evaluation type, :math:`y_pred` is in most cases (not strictly) a list
                 of floating numbers in range :math:`[0, 1]`
                 and the shape is :math:`(N, C)`, where :math:`N` is the number of cases and :math:`C`
-                is the number of categories. Shape of `y` can be :math:`(N, C)` with values 0 and 1 if one-hot
+                is the number of categories. Shape of :math:`y` can be :math:`(N, C)` with values 0 and 1 if one-hot
                 encoding is used or the shape is :math:`(N,)` with integer values if index of category is used.
-                For 'multilabel' evaluation type, `y_pred` and `y` can only be one-hot encoding with
-                values 0 or 1. Indices with 1 indicate positive category. The shape of `y_pred` and `y`
+                For 'multilabel' evaluation type, :math:`y_pred` and :math:`y` can only be one-hot encoding with
+                values 0 or 1. Indices with 1 indicate positive category. The shape of :math:`y_pred` and :math:`y`
                 are both :math:`(N, C)`.
 
         Raises:

mindspore/train/metrics/recall.py

@@ -36,7 +36,7 @@ class Recall(EvaluationBase):
         In the multi-label cases, the elements of :math:`y` and :math:`y_{pred}` must be 0 or 1.
 
     Args:
-        eval_type (str): ``'classification'`` or ``'multilabel'`` are supported. Default: ``'classification'`` .
+        eval_type (str): ``'classification'`` or ``'multilabel'`` is supported. Default: ``'classification'`` .
 
     Supported Platforms:
         ``Ascend`` ``GPU`` ``CPU``
@@ -79,15 +79,15 @@ class Recall(EvaluationBase):
 
         Args:
             inputs: Input `y_pred` and `y`. `y_pred` and `y` are a `Tensor`, a list or an array.
-                For 'classification' evaluation type, `y_pred` is in most cases (not strictly) a list
-                of floating numbers in range :math:`[0, 1]`
-                and the shape is :math:`(N, C)`, where :math:`N` is the number of cases and :math:`C`
-                is the number of categories. Shape of `y` can be :math:`(N, C)` with values 0 and 1 if one-hot
-                encoding is used or the shape is :math:`(N,)` with integer values if index of category is used.
-                For 'multilabel' evaluation type, `y_pred` and `y` can only be one-hot encoding with
-                values 0 or 1. Indices with 1 indicate positive category. The shape of `y_pred` and `y`
-                are both :math:`(N, C)`.
 
+                - For 'classification' scenario, `y_pred` is in most cases (not strictly) a list
+                  of floating numbers in range :math:`[0, 1]`
+                  and the shape is :math:`(N, C)`, where :math:`N` is the number of cases and :math:`C`
+                  is the number of categories. Shape of `y` can be :math:`(N, C)` with values 0 and 1 if one-hot
+                  encoding is used or the shape is :math:`(N,)` with integer values if index of category is used.
+                - For 'multilabel' scenario, `y_pred` and `y` can only be one-hot encoding with
+                  values 0 or 1. Indices with 1 indicate positive category. The shape of `y_pred` and `y`
+                  are both :math:`(N, C)`.
 
         Raises:
             ValueError: If the number of inputs is not 2.

mindspore/train/metrics/root_mean_square_surface_distance.py

@@ -48,11 +48,11 @@ class RootMeanSquareDistance(Metric):
         \right | + \left | S(B) \right |}}
 
     Args:
-        distance_metric (string): Three measurement methods are supported:
+        distance_metric (str): Three measurement methods are supported:
                 ``"euclidean"`` (Euclidean Distance) ,  ``"chessboard"`` (Chessboard Distance, Chebyshev Distance)
                 or  ``"taxicab"`` (Taxicab Distance, Manhattan Distance). Default: ``"euclidean"`` .
         symmetric (bool):  Whether to calculate the symmetric average root mean square distance between
-                y_pred and y. If False, only calculates :math:`RmsSurDis(y\_pred, y)` surface distance,
+                `y_pred` and `y`. If False, only calculates :math:`RmsSurDis(y\_pred, y)` surface distance,
                 otherwise, the mean of  distance from `y_pred` to `y` and from `y` to `y_pred`, i.e.
                 :math:`RmsSurDis(y\_pred \leftrightarrow y)` will be returned. Default: ``False`` .
 

mindspore/train/mind_ir_pb2.py

@@ -20,7 +20,7 @@ DESCRIPTOR = _descriptor.FileDescriptor(
   syntax='proto2',
   serialized_options=None,
   create_key=_descriptor._internal_create_key,
-  serialized_pb=b'\n\rmind_ir.proto\x12\x07mind_ir\"\xd8\t\n\x0e\x41ttributeProto\x12\x0c\n\x04name\x18\x01 \x01(\t\x12\t\n\x01\x66\x18\x02 \x01(\x02\x12\t\n\x01i\x18\x03 \x01(\x03\x12\t\n\x01\x64\x18\x04 \x01(\x01\x12\t\n\x01s\x18\x05 \x01(\x0c\x12\x1f\n\x01t\x18\x06 \x01(\x0b\x32\x14.mind_ir.TensorProto\x12\x1e\n\x01g\x18\x07 \x01(\x0b\x32\x13.mind_ir.GraphProto\x12\x0e\n\x06\x66loats\x18\x08 \x03(\x02\x12\x0f\n\x07\x64oubles\x18\t \x03(\x01\x12\x0c\n\x04ints\x18\n \x03(\x03\x12\x0f\n\x07strings\x18\x0b \x03(\x0c\x12%\n\x07tensors\x18\x0c \x03(\x0b\x32\x14.mind_ir.TensorProto\x12#\n\x06graphs\x18\r \x03(\x0b\x32\x13.mind_ir.GraphProto\x12\x12\n\ndoc_string\x18\x0e \x01(\t\x12\x15\n\rref_attr_name\x18\x0f \x01(\t\x12\x33\n\x04type\x18\x10 \x01(\x0e\x32%.mind_ir.AttributeProto.AttributeType\x12\'\n\x06values\x18\x11 \x03(\x0b\x32\x17.mind_ir.AttributeProto\x12\x36\n\x08seq_info\x18\x12 \x01(\x0b\x32$.mind_ir.AttributeProto.SeqInfoProto\x12&\n\x07\x66unctor\x18\x13 \x01(\x0b\x32\x15.mind_ir.FunctorProto\x12\x35\n\x0cgraph_holder\x18\x14 \x01(\x0b\x32\x1f.mind_ir.ScalarGraphHolderProto\x1aT\n\x0cSeqInfoProto\x12\x12\n\nis_dyn_len\x18\x01 \x01(\x08\x12\x30\n\x0ftuple_elem_item\x18\x02 \x01(\x0b\x32\x17.mind_ir.AttributeProto\"\xc8\x04\n\rAttributeType\x12\r\n\tUNDEFINED\x10\x00\x12\t\n\x05\x46LOAT\x10\x01\x12\t\n\x05UINT8\x10\x02\x12\x08\n\x04INT8\x10\x03\x12\n\n\x06UINT16\x10\x04\x12\t\n\x05INT16\x10\x05\x12\t\n\x05INT32\x10\x06\x12\t\n\x05INT64\x10\x07\x12\n\n\x06STRING\x10\x08\x12\x08\n\x04\x42OOL\x10\t\x12\x0b\n\x07\x46LOAT16\x10\n\x12\n\n\x06\x44OUBLE\x10\x0b\x12\n\n\x06UINT32\x10\x0c\x12\n\n\x06UINT64\x10\r\x12\r\n\tCOMPLEX64\x10\x0e\x12\x0e\n\nCOMPLEX128\x10\x0f\x12\x0c\n\x08\x42\x46LOAT16\x10\x10\x12\n\n\x06TENSOR\x10\x11\x12\t\n\x05GRAPH\x10\x12\x12\x0b\n\x07TENSORS\x10\x13\x12\t\n\x05TUPLE\x10\x14\x12\x08\n\x04LIST\x10\x15\x12\x08\n\x04\x44ICT\x10\x16\x12\n\n\x06UMONAD\x10\x17\x12\x0b\n\x07IOMONAD\x10\x18\x12\x08\n\x04NONE\x10\x19\x12\x14\n\x10PRIMITIVECLOSURE\x10\x1a\x12\x14\n\x10\x46UNCGRAPHCLOSURE\x10\x1b\x12\x12\n\x0ePARTIALCLOSURE\x10\x1c\x12\x14\n\x10UNIONFUNCCLOSURE\x10\x1d\x12\x0e\n\nCSR_TENSOR\x10\x1e\x12\x0e\n\nCOO_TENSOR\x10\x1f\x12\x0e\n\nROW_TENSOR\x10 \x12\x0e\n\nCLASS_TYPE\x10!\x12\x0e\n\nNAME_SPACE\x10\"\x12\n\n\x06SYMBOL\x10#\x12\r\n\tTYPE_NULL\x10$\x12\x0e\n\nMAP_TENSOR\x10%\x12\x0b\n\x07\x46UNCTOR\x10&\x12\n\n\x06SCALAR\x10\'\x12\x17\n\x13SCALAR_GRAPH_HOLDER\x10(\"\xae\x01\n\x0c\x46unctorProto\x12/\n\x04type\x18\x01 \x01(\x0e\x32!.mind_ir.FunctorProto.FunctorType\x12\x0c\n\x04name\x18\x02 \x01(\t\x12\'\n\x06values\x18\x03 \x03(\x0b\x32\x17.mind_ir.AttributeProto\"6\n\x0b\x46unctorType\x12\x16\n\x12SHAPE_CALC_FUNCTOR\x10\x01\x12\x0f\n\x0b\x41NY_FUNCTOR\x10\x02\"\x98\x01\n\x0eValueInfoProto\x12\x0c\n\x04name\x18\x01 \x01(\t\x12$\n\x06tensor\x18\x02 \x03(\x0b\x32\x14.mind_ir.TensorProto\x12\x12\n\ndoc_string\x18\x03 \x01(\t\x12\x12\n\ndenotation\x18\x04 \x01(\t\x12*\n\tattr_info\x18\x05 \x01(\x0b\x32\x17.mind_ir.AttributeProto\"\xf3\x01\n\tNodeProto\x12\r\n\x05input\x18\x01 \x03(\t\x12\x0e\n\x06output\x18\x02 \x03(\t\x12\x0c\n\x04name\x18\x03 \x01(\t\x12\x0f\n\x07op_type\x18\x04 \x01(\t\x12*\n\tattribute\x18\x05 \x03(\x0b\x32\x17.mind_ir.AttributeProto\x12\x12\n\ndoc_string\x18\x06 \x01(\t\x12\x0e\n\x06\x64omain\x18\x07 \x01(\t\x12*\n\tnode_attr\x18\x08 \x03(\x0b\x32\x17.mind_ir.AttributeProto\x12,\n\x0bprimal_attr\x18\t \x03(\x0b\x32\x17.mind_ir.AttributeProto\"\xf8\x03\n\nModelProto\x12\x12\n\nir_version\x18\x01 \x01(\t\x12\x15\n\rproducer_name\x18\x02 \x01(\t\x12\x18\n\x10producer_version\x18\x03 \x01(\t\x12\x0e\n\x06\x64omain\x18\x04 \x01(\t\x12\x15\n\rmodel_version\x18\x05 \x01(\t\x12\x12\n\ndoc_string\x18\x06 \x01(\t\x12\"\n\x05graph\x18\x07 \x01(\x0b\x32\x13.mind_ir.GraphProto\x12&\n\tfunctions\x18\x08 \x03(\x0b\x32\x13.mind_ir.GraphProto\x12\x30\n\x0cpreprocessor\x18\t \x01(\x0b\x32\x1a.mind_ir.PreprocessorProto\x12\x15\n\rlittle_endian\x18\n \x01(\x08\x12(\n\x08parallel\x18\x0b \x01(\x0b\x32\x16.mind_ir.ParallelProto\x12+\n\nprimitives\x18\x0c \x03(\x0b\x32\x17.mind_ir.PrimitiveProto\x12\x17\n\x0fmind_ir_version\x18\r \x01(\x03\x12\x34\n\tuser_info\x18\x0e \x03(\x0b\x32!.mind_ir.ModelProto.UserInfoEntry\x1a/\n\rUserInfoEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\t:\x02\x38\x01\";\n\x11PreprocessorProto\x12&\n\x02op\x18\x01 \x03(\x0b\x32\x1a.mind_ir.PreprocessOpProto\"\x91\x01\n\x11PreprocessOpProto\x12\x15\n\rinput_columns\x18\x01 \x01(\t\x12\x16\n\x0eoutput_columns\x18\x02 \x01(\t\x12\x17\n\x0fproject_columns\x18\x03 \x01(\t\x12\x0f\n\x07op_type\x18\x04 \x01(\t\x12\x12\n\noperations\x18\x05 \x01(\t\x12\x0f\n\x07offload\x18\x06 \x01(\x08\"\xd2\x02\n\nGraphProto\x12 \n\x04node\x18\x01 \x03(\x0b\x32\x12.mind_ir.NodeProto\x12\x0c\n\x04name\x18\x02 \x01(\t\x12\'\n\tparameter\x18\x03 \x03(\x0b\x32\x14.mind_ir.TensorProto\x12\x12\n\ndoc_string\x18\x04 \x01(\t\x12&\n\x05input\x18\x05 \x03(\x0b\x32\x17.mind_ir.ValueInfoProto\x12\'\n\x06output\x18\x06 \x03(\x0b\x32\x17.mind_ir.ValueInfoProto\x12\x12\n\nbprop_hash\x18\x07 \x01(\t\x12*\n\tattribute\x18\x08 \x03(\x0b\x32\x17.mind_ir.AttributeProto\x12\x16\n\x0e\x62prop_filepath\x18\t \x01(\t\x12.\n\rmap_parameter\x18\n \x03(\x0b\x32\x17.mind_ir.MapTensorProto\"\xda\x07\n\x0bTensorProto\x12\x0c\n\x04\x64ims\x18\x01 \x03(\x03\x12\x11\n\tdata_type\x18\x02 \x01(\x05\x12\x12\n\nfloat_data\x18\x03 \x03(\x02\x12\x12\n\nint32_data\x18\x04 \x03(\x05\x12\x13\n\x0bstring_data\x18\x05 \x03(\x0c\x12\x12\n\nint64_data\x18\x06 \x03(\x03\x12\x0c\n\x04name\x18\x07 \x01(\t\x12\x12\n\ndoc_string\x18\x08 \x01(\t\x12\x10\n\x08raw_data\x18\t \x01(\x0c\x12\x13\n\x0b\x64ouble_data\x18\n \x03(\x01\x12\x13\n\x0buint64_data\x18\x0b \x03(\x04\x12=\n\rexternal_data\x18\x0c \x01(\x0b\x32&.mind_ir.TensorProto.ExternalDataProto\x12\x0f\n\x07ref_key\x18\r \x01(\t\x12\x10\n\x08min_dims\x18\x0e \x03(\x03\x12\x10\n\x08max_dims\x18\x0f \x03(\x03\x12>\n\x10\x63ompression_type\x18\x10 \x01(\x0e\x32$.mind_ir.TensorProto.CompressionType\x12:\n\x0cquant_params\x18\x11 \x03(\x0b\x32$.mind_ir.TensorProto.QuantParamProto\x1a\x45\n\x11\x45xternalDataProto\x12\x10\n\x08location\x18\x01 \x01(\t\x12\x0e\n\x06offset\x18\x02 \x01(\x03\x12\x0e\n\x06length\x18\x03 \x01(\x03\x1aV\n\x0fQuantParamProto\x12\x17\n\x0fquant_algo_name\x18\x01 \x02(\t\x12*\n\tattribute\x18\x02 \x03(\x0b\x32\x17.mind_ir.AttributeProto\"\xf4\x01\n\x08\x44\x61taType\x12\r\n\tUNDEFINED\x10\x00\x12\t\n\x05\x46LOAT\x10\x01\x12\t\n\x05UINT8\x10\x02\x12\x08\n\x04INT8\x10\x03\x12\n\n\x06UINT16\x10\x04\x12\t\n\x05INT16\x10\x05\x12\t\n\x05INT32\x10\x06\x12\t\n\x05INT64\x10\x07\x12\n\n\x06STRING\x10\x08\x12\x08\n\x04\x42OOL\x10\t\x12\x0b\n\x07\x46LOAT16\x10\n\x12\n\n\x06\x44OUBLE\x10\x0b\x12\n\n\x06UINT32\x10\x0c\x12\n\n\x06UINT64\x10\r\x12\r\n\tCOMPLEX64\x10\x0e\x12\x0e\n\nCOMPLEX128\x10\x0f\x12\x0c\n\x08\x42\x46LOAT16\x10\x10\x12\x0b\n\x07\x46LOAT64\x10\x11\x12\x0b\n\x07QINT4X2\x10\x12\"u\n\x0f\x43ompressionType\x12\x12\n\x0eNO_COMPRESSION\x10\x00\x12\x0c\n\x08INDEXING\x10\x01\x12\n\n\x06SPARSE\x10\x02\x12\x07\n\x03\x46SE\x10\x03\x12\x0f\n\x0b\x42IT_PACKING\x10\x04\x12\x0b\n\x07\x46SE_INT\x10\x05\x12\r\n\tFSE_INFER\x10\x06\"\xd1\x01\n\x0eMapTensorProto\x12\x0c\n\x04name\x18\x01 \x02(\t\x12.\n\rdefault_value\x18\x02 \x02(\x0b\x32\x17.mind_ir.AttributeProto\x12(\n\nkey_tensor\x18\x03 \x02(\x0b\x32\x14.mind_ir.TensorProto\x12*\n\x0cvalue_tensor\x18\x04 \x02(\x0b\x32\x14.mind_ir.TensorProto\x12+\n\rstatus_tensor\x18\x05 \x02(\x0b\x32\x14.mind_ir.TensorProto\"5\n\rParallelProto\x12$\n\x06layout\x18\x01 \x03(\x0b\x32\x14.mind_ir.LayoutProto\"\xfd\x01\n\x0bLayoutProto\x12\x0c\n\x04name\x18\x01 \x01(\t\x12\x1e\n\x16\x64\x65vice_arrangement_int\x18\x02 \x03(\x03\x12\x16\n\x0etensor_map_int\x18\x03 \x03(\x03\x12\x17\n\x0fslice_shape_int\x18\x04 \x03(\x03\x12\x12\n\nfield_size\x18\x05 \x01(\x03\x12\x15\n\runiform_split\x18\x06 \x01(\x08\x12\x17\n\x0fopt_shard_group\x18\x07 \x01(\t\x12\x17\n\x0fpipeline_shared\x18\x08 \x01(\x08\x12\x0f\n\x07is_send\x18\t \x01(\x08\x12\x11\n\tpeer_rank\x18\n \x01(\x03\x12\x0e\n\x06sr_tag\x18\x0b \x01(\x03\"\xda\x01\n\x0ePrimitiveProto\x12\x0c\n\x04name\x18\x01 \x01(\t\x12\x0f\n\x07op_type\x18\x02 \x01(\t\x12*\n\tattribute\x18\x03 \x03(\x0b\x32\x17.mind_ir.AttributeProto\x12\x15\n\rinstance_name\x18\x04 \x01(\t\x12\x33\n\tprim_type\x18\x05 \x01(\x0e\x32 .mind_ir.PrimitiveProto.PrimType\"1\n\x08PrimType\x12\r\n\tPRIMITIVE\x10\x01\x12\x16\n\x12PRIMITIVE_FUNCTION\x10\x02\"J\n\x0fScalarNodeProto\x12\x16\n\x0escalar_op_type\x18\x01 \x01(\x03\x12\x10\n\x08in_index\x18\x02 \x03(\x03\x12\r\n\x05value\x18\x03 \x03(\x03\"b\n\x16ScalarGraphHolderProto\x12-\n\x0bscalar_node\x18\x01 \x03(\x0b\x32\x18.mind_ir.ScalarNodeProto\x12\x19\n\x11input_shape_index\x18\x02 \x03(\x04*{\n\x07Version\x12\x14\n\x10IR_VERSION_START\x10\x00\x12\x0e\n\nIR_VERSION\x10\x01\x12!\n\x1dIR_VERSION_WITH_PRIM_FUNCTION\x10\x02\x12\'\n#IR_VERSION_WITH_SCALAR_GRAPH_HOLDER\x10\x03'
+  serialized_pb=b'\n\rmind_ir.proto\x12\x07mind_ir\"\xd8\t\n\x0e\x41ttributeProto\x12\x0c\n\x04name\x18\x01 \x01(\t\x12\t\n\x01\x66\x18\x02 \x01(\x02\x12\t\n\x01i\x18\x03 \x01(\x03\x12\t\n\x01\x64\x18\x04 \x01(\x01\x12\t\n\x01s\x18\x05 \x01(\x0c\x12\x1f\n\x01t\x18\x06 \x01(\x0b\x32\x14.mind_ir.TensorProto\x12\x1e\n\x01g\x18\x07 \x01(\x0b\x32\x13.mind_ir.GraphProto\x12\x0e\n\x06\x66loats\x18\x08 \x03(\x02\x12\x0f\n\x07\x64oubles\x18\t \x03(\x01\x12\x0c\n\x04ints\x18\n \x03(\x03\x12\x0f\n\x07strings\x18\x0b \x03(\x0c\x12%\n\x07tensors\x18\x0c \x03(\x0b\x32\x14.mind_ir.TensorProto\x12#\n\x06graphs\x18\r \x03(\x0b\x32\x13.mind_ir.GraphProto\x12\x12\n\ndoc_string\x18\x0e \x01(\t\x12\x15\n\rref_attr_name\x18\x0f \x01(\t\x12\x33\n\x04type\x18\x10 \x01(\x0e\x32%.mind_ir.AttributeProto.AttributeType\x12\'\n\x06values\x18\x11 \x03(\x0b\x32\x17.mind_ir.AttributeProto\x12\x36\n\x08seq_info\x18\x12 \x01(\x0b\x32$.mind_ir.AttributeProto.SeqInfoProto\x12&\n\x07\x66unctor\x18\x13 \x01(\x0b\x32\x15.mind_ir.FunctorProto\x12\x35\n\x0cgraph_holder\x18\x14 \x01(\x0b\x32\x1f.mind_ir.ScalarGraphHolderProto\x1aT\n\x0cSeqInfoProto\x12\x12\n\nis_dyn_len\x18\x01 \x01(\x08\x12\x30\n\x0ftuple_elem_item\x18\x02 \x01(\x0b\x32\x17.mind_ir.AttributeProto\"\xc8\x04\n\rAttributeType\x12\r\n\tUNDEFINED\x10\x00\x12\t\n\x05\x46LOAT\x10\x01\x12\t\n\x05UINT8\x10\x02\x12\x08\n\x04INT8\x10\x03\x12\n\n\x06UINT16\x10\x04\x12\t\n\x05INT16\x10\x05\x12\t\n\x05INT32\x10\x06\x12\t\n\x05INT64\x10\x07\x12\n\n\x06STRING\x10\x08\x12\x08\n\x04\x42OOL\x10\t\x12\x0b\n\x07\x46LOAT16\x10\n\x12\n\n\x06\x44OUBLE\x10\x0b\x12\n\n\x06UINT32\x10\x0c\x12\n\n\x06UINT64\x10\r\x12\r\n\tCOMPLEX64\x10\x0e\x12\x0e\n\nCOMPLEX128\x10\x0f\x12\x0c\n\x08\x42\x46LOAT16\x10\x10\x12\n\n\x06TENSOR\x10\x11\x12\t\n\x05GRAPH\x10\x12\x12\x0b\n\x07TENSORS\x10\x13\x12\t\n\x05TUPLE\x10\x14\x12\x08\n\x04LIST\x10\x15\x12\x08\n\x04\x44ICT\x10\x16\x12\n\n\x06UMONAD\x10\x17\x12\x0b\n\x07IOMONAD\x10\x18\x12\x08\n\x04NONE\x10\x19\x12\x14\n\x10PRIMITIVECLOSURE\x10\x1a\x12\x14\n\x10\x46UNCGRAPHCLOSURE\x10\x1b\x12\x12\n\x0ePARTIALCLOSURE\x10\x1c\x12\x14\n\x10UNIONFUNCCLOSURE\x10\x1d\x12\x0e\n\nCSR_TENSOR\x10\x1e\x12\x0e\n\nCOO_TENSOR\x10\x1f\x12\x0e\n\nROW_TENSOR\x10 \x12\x0e\n\nCLASS_TYPE\x10!\x12\x0e\n\nNAME_SPACE\x10\"\x12\n\n\x06SYMBOL\x10#\x12\r\n\tTYPE_NULL\x10$\x12\x0e\n\nMAP_TENSOR\x10%\x12\x0b\n\x07\x46UNCTOR\x10&\x12\n\n\x06SCALAR\x10\'\x12\x17\n\x13SCALAR_GRAPH_HOLDER\x10(\"\xae\x01\n\x0c\x46unctorProto\x12/\n\x04type\x18\x01 \x01(\x0e\x32!.mind_ir.FunctorProto.FunctorType\x12\x0c\n\x04name\x18\x02 \x01(\t\x12\'\n\x06values\x18\x03 \x03(\x0b\x32\x17.mind_ir.AttributeProto\"6\n\x0b\x46unctorType\x12\x16\n\x12SHAPE_CALC_FUNCTOR\x10\x01\x12\x0f\n\x0b\x41NY_FUNCTOR\x10\x02\"\x98\x01\n\x0eValueInfoProto\x12\x0c\n\x04name\x18\x01 \x01(\t\x12$\n\x06tensor\x18\x02 \x03(\x0b\x32\x14.mind_ir.TensorProto\x12\x12\n\ndoc_string\x18\x03 \x01(\t\x12\x12\n\ndenotation\x18\x04 \x01(\t\x12*\n\tattr_info\x18\x05 \x01(\x0b\x32\x17.mind_ir.AttributeProto\"\xf3\x01\n\tNodeProto\x12\r\n\x05input\x18\x01 \x03(\t\x12\x0e\n\x06output\x18\x02 \x03(\t\x12\x0c\n\x04name\x18\x03 \x01(\t\x12\x0f\n\x07op_type\x18\x04 \x01(\t\x12*\n\tattribute\x18\x05 \x03(\x0b\x32\x17.mind_ir.AttributeProto\x12\x12\n\ndoc_string\x18\x06 \x01(\t\x12\x0e\n\x06\x64omain\x18\x07 \x01(\t\x12*\n\tnode_attr\x18\x08 \x03(\x0b\x32\x17.mind_ir.AttributeProto\x12,\n\x0bprimal_attr\x18\t \x03(\x0b\x32\x17.mind_ir.AttributeProto\"\xf8\x03\n\nModelProto\x12\x12\n\nir_version\x18\x01 \x01(\t\x12\x15\n\rproducer_name\x18\x02 \x01(\t\x12\x18\n\x10producer_version\x18\x03 \x01(\t\x12\x0e\n\x06\x64omain\x18\x04 \x01(\t\x12\x15\n\rmodel_version\x18\x05 \x01(\t\x12\x12\n\ndoc_string\x18\x06 \x01(\t\x12\"\n\x05graph\x18\x07 \x01(\x0b\x32\x13.mind_ir.GraphProto\x12&\n\tfunctions\x18\x08 \x03(\x0b\x32\x13.mind_ir.GraphProto\x12\x30\n\x0cpreprocessor\x18\t \x01(\x0b\x32\x1a.mind_ir.PreprocessorProto\x12\x15\n\rlittle_endian\x18\n \x01(\x08\x12(\n\x08parallel\x18\x0b \x01(\x0b\x32\x16.mind_ir.ParallelProto\x12+\n\nprimitives\x18\x0c \x03(\x0b\x32\x17.mind_ir.PrimitiveProto\x12\x17\n\x0fmind_ir_version\x18\r \x01(\x03\x12\x34\n\tuser_info\x18\x0e \x03(\x0b\x32!.mind_ir.ModelProto.UserInfoEntry\x1a/\n\rUserInfoEntry\x12\x0b\n\x03key\x18\x01 \x01(\t\x12\r\n\x05value\x18\x02 \x01(\t:\x02\x38\x01\";\n\x11PreprocessorProto\x12&\n\x02op\x18\x01 \x03(\x0b\x32\x1a.mind_ir.PreprocessOpProto\"\x91\x01\n\x11PreprocessOpProto\x12\x15\n\rinput_columns\x18\x01 \x01(\t\x12\x16\n\x0eoutput_columns\x18\x02 \x01(\t\x12\x17\n\x0fproject_columns\x18\x03 \x01(\t\x12\x0f\n\x07op_type\x18\x04 \x01(\t\x12\x12\n\noperations\x18\x05 \x01(\t\x12\x0f\n\x07offload\x18\x06 \x01(\x08\"\xd2\x02\n\nGraphProto\x12 \n\x04node\x18\x01 \x03(\x0b\x32\x12.mind_ir.NodeProto\x12\x0c\n\x04name\x18\x02 \x01(\t\x12\'\n\tparameter\x18\x03 \x03(\x0b\x32\x14.mind_ir.TensorProto\x12\x12\n\ndoc_string\x18\x04 \x01(\t\x12&\n\x05input\x18\x05 \x03(\x0b\x32\x17.mind_ir.ValueInfoProto\x12\'\n\x06output\x18\x06 \x03(\x0b\x32\x17.mind_ir.ValueInfoProto\x12\x12\n\nbprop_hash\x18\x07 \x01(\t\x12*\n\tattribute\x18\x08 \x03(\x0b\x32\x17.mind_ir.AttributeProto\x12\x16\n\x0e\x62prop_filepath\x18\t \x01(\t\x12.\n\rmap_parameter\x18\n \x03(\x0b\x32\x17.mind_ir.MapTensorProto\"\xda\x07\n\x0bTensorProto\x12\x0c\n\x04\x64ims\x18\x01 \x03(\x03\x12\x11\n\tdata_type\x18\x02 \x01(\x05\x12\x12\n\nfloat_data\x18\x03 \x03(\x02\x12\x12\n\nint32_data\x18\x04 \x03(\x05\x12\x13\n\x0bstring_data\x18\x05 \x03(\x0c\x12\x12\n\nint64_data\x18\x06 \x03(\x03\x12\x0c\n\x04name\x18\x07 \x01(\t\x12\x12\n\ndoc_string\x18\x08 \x01(\t\x12\x10\n\x08raw_data\x18\t \x01(\x0c\x12\x13\n\x0b\x64ouble_data\x18\n \x03(\x01\x12\x13\n\x0buint64_data\x18\x0b \x03(\x04\x12=\n\rexternal_data\x18\x0c \x01(\x0b\x32&.mind_ir.TensorProto.ExternalDataProto\x12\x0f\n\x07ref_key\x18\r \x01(\t\x12\x10\n\x08min_dims\x18\x0e \x03(\x03\x12\x10\n\x08max_dims\x18\x0f \x03(\x03\x12>\n\x10\x63ompression_type\x18\x10 \x01(\x0e\x32$.mind_ir.TensorProto.CompressionType\x12:\n\x0cquant_params\x18\x11 \x03(\x0b\x32$.mind_ir.TensorProto.QuantParamProto\x1a\x45\n\x11\x45xternalDataProto\x12\x10\n\x08location\x18\x01 \x01(\t\x12\x0e\n\x06offset\x18\x02 \x01(\x03\x12\x0e\n\x06length\x18\x03 \x01(\x03\x1aV\n\x0fQuantParamProto\x12\x17\n\x0fquant_algo_name\x18\x01 \x02(\t\x12*\n\tattribute\x18\x02 \x03(\x0b\x32\x17.mind_ir.AttributeProto\"\xf4\x01\n\x08\x44\x61taType\x12\r\n\tUNDEFINED\x10\x00\x12\t\n\x05\x46LOAT\x10\x01\x12\t\n\x05UINT8\x10\x02\x12\x08\n\x04INT8\x10\x03\x12\n\n\x06UINT16\x10\x04\x12\t\n\x05INT16\x10\x05\x12\t\n\x05INT32\x10\x06\x12\t\n\x05INT64\x10\x07\x12\n\n\x06STRING\x10\x08\x12\x08\n\x04\x42OOL\x10\t\x12\x0b\n\x07\x46LOAT16\x10\n\x12\n\n\x06\x44OUBLE\x10\x0b\x12\n\n\x06UINT32\x10\x0c\x12\n\n\x06UINT64\x10\r\x12\r\n\tCOMPLEX64\x10\x0e\x12\x0e\n\nCOMPLEX128\x10\x0f\x12\x0c\n\x08\x42\x46LOAT16\x10\x10\x12\x0b\n\x07\x46LOAT64\x10\x11\x12\x0b\n\x07QINT4X2\x10\x12\"u\n\x0f\x43ompressionType\x12\x12\n\x0eNO_COMPRESSION\x10\x00\x12\x0c\n\x08INDEXING\x10\x01\x12\n\n\x06SPARSE\x10\x02\x12\x07\n\x03\x46SE\x10\x03\x12\x0f\n\x0b\x42IT_PACKING\x10\x04\x12\x0b\n\x07\x46SE_INT\x10\x05\x12\r\n\tFSE_INFER\x10\x06\"\xd1\x01\n\x0eMapTensorProto\x12\x0c\n\x04name\x18\x01 \x02(\t\x12.\n\rdefault_value\x18\x02 \x02(\x0b\x32\x17.mind_ir.AttributeProto\x12(\n\nkey_tensor\x18\x03 \x02(\x0b\x32\x14.mind_ir.TensorProto\x12*\n\x0cvalue_tensor\x18\x04 \x02(\x0b\x32\x14.mind_ir.TensorProto\x12+\n\rstatus_tensor\x18\x05 \x02(\x0b\x32\x14.mind_ir.TensorProto\"5\n\rParallelProto\x12$\n\x06layout\x18\x01 \x03(\x0b\x32\x14.mind_ir.LayoutProto\"\xa0\x02\n\x0bLayoutProto\x12\x0c\n\x04name\x18\x01 \x01(\t\x12\x1e\n\x16\x64\x65vice_arrangement_int\x18\x02 \x03(\x03\x12\x16\n\x0etensor_map_int\x18\x03 \x03(\x03\x12\x17\n\x0fslice_shape_int\x18\x04 \x03(\x03\x12\x12\n\nfield_size\x18\x05 \x01(\x03\x12\x15\n\runiform_split\x18\x06 \x01(\x08\x12\x17\n\x0fopt_shard_group\x18\x07 \x01(\t\x12\x17\n\x0fpipeline_shared\x18\x08 \x01(\x08\x12\x0f\n\x07is_send\x18\t \x01(\x08\x12\x11\n\tpeer_rank\x18\n \x01(\x03\x12\x0e\n\x06sr_tag\x18\x0b \x01(\x03\x12!\n\x19opt_shard_slice_shape_int\x18\x0c \x03(\x03\"\xda\x01\n\x0ePrimitiveProto\x12\x0c\n\x04name\x18\x01 \x01(\t\x12\x0f\n\x07op_type\x18\x02 \x01(\t\x12*\n\tattribute\x18\x03 \x03(\x0b\x32\x17.mind_ir.AttributeProto\x12\x15\n\rinstance_name\x18\x04 \x01(\t\x12\x33\n\tprim_type\x18\x05 \x01(\x0e\x32 .mind_ir.PrimitiveProto.PrimType\"1\n\x08PrimType\x12\r\n\tPRIMITIVE\x10\x01\x12\x16\n\x12PRIMITIVE_FUNCTION\x10\x02\"J\n\x0fScalarNodeProto\x12\x16\n\x0escalar_op_type\x18\x01 \x01(\x03\x12\x10\n\x08in_index\x18\x02 \x03(\x03\x12\r\n\x05value\x18\x03 \x03(\x03\"b\n\x16ScalarGraphHolderProto\x12-\n\x0bscalar_node\x18\x01 \x03(\x0b\x32\x18.mind_ir.ScalarNodeProto\x12\x19\n\x11input_shape_index\x18\x02 \x03(\x04*{\n\x07Version\x12\x14\n\x10IR_VERSION_START\x10\x00\x12\x0e\n\nIR_VERSION\x10\x01\x12!\n\x1dIR_VERSION_WITH_PRIM_FUNCTION\x10\x02\x12\'\n#IR_VERSION_WITH_SCALAR_GRAPH_HOLDER\x10\x03'
 )
 
 _VERSION = _descriptor.EnumDescriptor(
@@ -53,8 +53,8 @@ _VERSION = _descriptor.EnumDescriptor(
   ],
   containing_type=None,
   serialized_options=None,
-  serialized_start=4813,
-  serialized_end=4936,
+  serialized_start=4848,
+  serialized_end=4971,
 )
 _sym_db.RegisterEnumDescriptor(_VERSION)
 
@@ -490,8 +490,8 @@ _PRIMITIVEPROTO_PRIMTYPE = _descriptor.EnumDescriptor(
   ],
   containing_type=None,
   serialized_options=None,
-  serialized_start=4586,
-  serialized_end=4635,
+  serialized_start=4621,
+  serialized_end=4670,
 )
 _sym_db.RegisterEnumDescriptor(_PRIMITIVEPROTO_PRIMTYPE)
 
@@ -1656,6 +1656,13 @@ _LAYOUTPROTO = _descriptor.Descriptor(
       message_type=None, enum_type=None, containing_type=None,
       is_extension=False, extension_scope=None,
       serialized_options=None, file=DESCRIPTOR,  create_key=_descriptor._internal_create_key),
+    _descriptor.FieldDescriptor(
+      name='opt_shard_slice_shape_int', full_name='mind_ir.LayoutProto.opt_shard_slice_shape_int', index=11,
+      number=12, type=3, cpp_type=2, label=3,
+      has_default_value=False, default_value=[],
+      message_type=None, enum_type=None, containing_type=None,
+      is_extension=False, extension_scope=None,
+      serialized_options=None, file=DESCRIPTOR,  create_key=_descriptor._internal_create_key),
   ],
   extensions=[
   ],
@@ -1669,7 +1676,7 @@ _LAYOUTPROTO = _descriptor.Descriptor(
   oneofs=[
   ],
   serialized_start=4161,
-  serialized_end=4414,
+  serialized_end=4449,
 )
 
 
@@ -1729,8 +1736,8 @@ _PRIMITIVEPROTO = _descriptor.Descriptor(
   extension_ranges=[],
   oneofs=[
   ],
-  serialized_start=4417,
-  serialized_end=4635,
+  serialized_start=4452,
+  serialized_end=4670,
 )
 
 
@@ -1775,8 +1782,8 @@ _SCALARNODEPROTO = _descriptor.Descriptor(
   extension_ranges=[],
   oneofs=[
   ],
-  serialized_start=4637,
-  serialized_end=4711,
+  serialized_start=4672,
+  serialized_end=4746,
 )
 
 
@@ -1814,8 +1821,8 @@ _SCALARGRAPHHOLDERPROTO = _descriptor.Descriptor(
   extension_ranges=[],
   oneofs=[
   ],
-  serialized_start=4713,
-  serialized_end=4811,
+  serialized_start=4748,
+  serialized_end=4846,
 )
 
 _ATTRIBUTEPROTO_SEQINFOPROTO.fields_by_name['tuple_elem_item'].message_type = _ATTRIBUTEPROTO