本文整理汇总了Python中object_detection.utils.ops.reduce_sum_trailing_dimensions方法的典型用法代码示例。如果您正苦于以下问题:Python ops.reduce_sum_trailing_dimensions方法的具体用法?Python ops.reduce_sum_trailing_dimensions怎么用?Python ops.reduce_sum_trailing_dimensions使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类object_detection.utils.ops
的用法示例。
在下文中一共展示了ops.reduce_sum_trailing_dimensions方法的3个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: test_reduce_sum_trailing_dimensions
# 需要导入模块: from object_detection.utils import ops [as 别名]
# 或者: from object_detection.utils.ops import reduce_sum_trailing_dimensions [as 别名]
def test_reduce_sum_trailing_dimensions(self):
input_tensor = tf.placeholder(tf.float32, shape=[None, None, None])
reduced_tensor = ops.reduce_sum_trailing_dimensions(input_tensor, ndims=2)
with self.test_session() as sess:
reduced_np = sess.run(reduced_tensor,
feed_dict={input_tensor: np.ones((2, 2, 2),
np.float32)})
self.assertAllClose(reduced_np, 2 * np.ones((2, 2), np.float32))
示例2: test_reduce_sum_trailing_dimensions
# 需要导入模块: from object_detection.utils import ops [as 别名]
# 或者: from object_detection.utils.ops import reduce_sum_trailing_dimensions [as 别名]
def test_reduce_sum_trailing_dimensions(self):
input_tensor = tf.placeholder(tf.float32, shape=[None, None, None])
reduced_tensor = ops.reduce_sum_trailing_dimensions(input_tensor, ndims=2)
with self.test_session() as sess:
reduced_np = sess.run(reduced_tensor,
feed_dict={input_tensor: np.ones((2, 2, 2),
np.float32)})
self.assertAllClose(reduced_np, 2 * np.ones((2, 2), np.float32))
示例3: test_reduce_sum_trailing_dimensions
# 需要导入模块: from object_detection.utils import ops [as 别名]
# 或者: from object_detection.utils.ops import reduce_sum_trailing_dimensions [as 别名]
def test_reduce_sum_trailing_dimensions(self):
def graph_fn(input_tensor):
reduced_tensor = ops.reduce_sum_trailing_dimensions(input_tensor, ndims=2)
return reduced_tensor
reduced_np = self.execute(graph_fn, [np.ones((2, 2, 2), np.float32)])
self.assertAllClose(reduced_np, 2 * np.ones((2, 2), np.float32))