本文整理汇总了Python中tensorflow.python.ops.sparse_ops.sparse_dense_cwise_add方法的典型用法代码示例。如果您正苦于以下问题：Python sparse_ops.sparse_dense_cwise_add方法的具体用法？Python sparse_ops.sparse_dense_cwise_add怎么用？Python sparse_ops.sparse_dense_cwise_add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tensorflow.python.ops.sparse_ops的用法示例。
在下文中一共展示了sparse_ops.sparse_dense_cwise_add方法的2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: testCwiseAdd
# 需要导入模块: from tensorflow.python.ops import sparse_ops [as 别名]
# 或者: from tensorflow.python.ops.sparse_ops import sparse_dense_cwise_add [as 别名]
def testCwiseAdd(self):
with self.test_session(use_gpu=False):
# Identity(2) + AllOnes(2,2). Should be equal to 2 * Identity(2).
indices = [[0, 0], [1, 1]]
vals = [1, 1]
shape = (2, 2)
sp_t = tf.SparseTensor(indices, vals, shape)
dense_t = tf.ones(shape, dtype=dtypes.int32)
self._check(sparse_ops.sparse_dense_cwise_add(sp_t, dense_t),
np.identity(2) * 2, sp_t)
# Variant of above, but broadcasts the dense side.
dense_t = tf.ones([1], dtype=dtypes.int32)
self._check(sparse_ops.sparse_dense_cwise_add(sp_t, dense_t),
np.identity(2) * 2, sp_t) 示例2: _SparseSoftmaxGrad
# 需要导入模块: from tensorflow.python.ops import sparse_ops [as 别名]
# 或者: from tensorflow.python.ops.sparse_ops import sparse_dense_cwise_add [as 别名]
def _SparseSoftmaxGrad(op, grad):
"""Gradients for SparseSoftmax.
The calculation is the same as SoftmaxGrad:
grad_x = grad_softmax * softmax - sum(grad_softmax * softmax) * softmax
where we now only operate on the non-zero values present in the SparseTensors.
Args:
op: the SparseSoftmax op.
grad: the upstream gradient w.r.t. the non-zero SparseSoftmax output values.
Returns:
Gradients w.r.t. the input (sp_indices, sp_values, sp_shape).
"""
indices, shape = op.inputs[0], op.inputs[2]
out_vals = op.outputs[0]
sp_output = sparse_tensor.SparseTensor(indices, out_vals, shape)
sp_grad = sparse_tensor.SparseTensor(indices, grad, shape)
sp_product = sparse_tensor.SparseTensor(
indices, sp_output.values * sp_grad.values, shape)
# [..., B, 1], dense.
sum_reduced = -sparse_ops.sparse_reduce_sum(sp_product, [-1], keep_dims=True)
# sparse [..., B, C] + dense [..., B, 1] with broadcast; outputs sparse.
sp_sum = sparse_ops.sparse_dense_cwise_add(sp_grad, sum_reduced)
grad_x = sp_sum.values * sp_output.values
return [None, grad_x, None]