Remove API: mean_iou (#47971)

remove mean_iou which is not used in paddle 2.0

python/paddle/fluid/layers/nn.py

@@ -114,7 +114,6 @@ __all__ = [
     'gather_nd',
     'scatter',
     'random_crop',
-    'mean_iou',
     'relu',
     'log',
     'crop_tensor',
@@ -7626,73 +7625,6 @@ def relu(x, name=None):
     return out
 
 
-def mean_iou(input, label, num_classes):
-    r"""
-    Mean Intersection-Over-Union is a common evaluation metric for
-    semantic image segmentation, which first computes the IOU for each
-    semantic class and then computes the average over classes.
-    IOU is defined as follows:
-
-    .. math::
-
-        IOU = \\frac{true\_positive}{(true\_positive + false\_positive + false\_negative)}.
-
-    The predictions are accumulated in a confusion matrix and mean-IOU
-    is then calculated from it.
-
-
-    Parameters:
-        input (Tensor): A n-D Tensor of prediction results for semantic labels with type int32 or int64.
-        label (Tensor): A Tensor of ground truth labels with type int32 or int64.
-                           Its shape should be the same as input.
-        num_classes (int32): The possible number of labels.
-
-    Returns:
-	Three Tensors.
-
-        - mean_iou(Tensor) : A 1-D Tensor representing the mean intersection-over-union with shape [1]. \
-			    Data type is float32.
-        - out_wrong(Tensor) : A 1-D Tensor with shape [num_classes]. Data type is int32. \
-			     The wrong numbers of each class.
-        - out_correct(Tensor): A 1-D  Tensor with shape [num_classes]. Data type is int32. The correct numbers of each class.
-
-
-    Examples:
-
-        .. code-block:: python
-
-            import paddle
-
-            iou_shape = [64, 32, 32]
-            num_classes = 5
-            predict = paddle.randint(low=0, high=255, shape=iou_shape, dtype='int64')
-            label = paddle.randint(low=0, high=255, shape=iou_shape, dtype='int64')
-            mean_iou, out_wrong, out_correct = paddle.metric.mean_iou(predict, label, num_classes)
-    """
-    if _non_static_mode():
-        return _legacy_C_ops.mean_iou(input, label, 'num_classes', num_classes)
-
-    helper = LayerHelper('mean_iou', **locals())
-    check_variable_and_dtype(
-        input, 'Predictions', ['int32', 'int64'], 'mean_iou'
-    )
-    check_variable_and_dtype(label, 'Labels', ['int32', 'int64'], 'mean_iou')
-    out_mean_iou = helper.create_variable_for_type_inference(dtype='float32')
-    out_wrong = helper.create_variable_for_type_inference(dtype='int32')
-    out_correct = helper.create_variable_for_type_inference(dtype='int32')
-    helper.append_op(
-        type="mean_iou",
-        inputs={"Predictions": input, "Labels": label},
-        outputs={
-            "OutMeanIou": out_mean_iou,
-            "OutWrong": out_wrong,
-            "OutCorrect": out_correct,
-        },
-        attrs={"num_classes": num_classes},
-    )
-    return out_mean_iou, out_wrong, out_correct
-
-
 def crop_tensor(x, shape=None, offsets=None, name=None):
     """
     Crop input into output, as specified by offsets and shape.

python/paddle/fluid/tests/unittests/test_layers.py

@@ -3476,13 +3476,6 @@ class TestBook(LayerTest):
             output = layers.l2_normalize(x, axis=1)
             return output
 
-    def make_mean_iou(self):
-        with fluid.framework._dygraph_place_guard(place=fluid.CPUPlace()):
-            x = self._get_data(name='x', shape=[16], dtype='int32')
-            y = self._get_data(name='label', shape=[16], dtype='int32')
-            iou = layers.mean_iou(x, y, self._high_data_bound)
-            return iou
-
     def make_argsort(self):
         with program_guard(
             fluid.default_main_program(), fluid.default_startup_program()

python/paddle/fluid/tests/unittests/test_mean_iou.py

@@ -15,7 +15,6 @@
 import unittest
 import numpy as np
 from op_test import OpTest
-import paddle.fluid as fluid
 
 
 def compute_mean_iou(
@@ -140,22 +139,5 @@ class TestCase1(TestMeanIOUOp):
         self.check_output(check_dygraph=False, check_eager=False)
 
 
-class TestMeanIOUOpError(unittest.TestCase):
-    def test_errors(self):
-        with fluid.program_guard(fluid.Program(), fluid.Program()):
-            # The input type of accuracy_op must be Variable.
-            x1 = fluid.create_lod_tensor(
-                np.array([[-1]]), [[1]], fluid.CPUPlace()
-            )
-            y1 = fluid.create_lod_tensor(
-                np.array([[-1]]), [[1]], fluid.CPUPlace()
-            )
-            self.assertRaises(TypeError, fluid.layers.mean_iou, x1, y1)
-            # The input dtype of accuracy_op must be float32 or float64.
-            x2 = fluid.layers.data(name='x2', shape=[4], dtype="float32")
-            y2 = fluid.layers.data(name='x2', shape=[4], dtype="float32")
-            self.assertRaises(TypeError, fluid.layers.mean_iou, x2, y2)
-
-
 if __name__ == '__main__':
     unittest.main()