當前位置: 首頁>>代碼示例>>Python>>正文


Python array_ops.invert_permutation方法代碼示例

本文整理匯總了Python中tensorflow.python.ops.array_ops.invert_permutation方法的典型用法代碼示例。如果您正苦於以下問題:Python array_ops.invert_permutation方法的具體用法?Python array_ops.invert_permutation怎麽用?Python array_ops.invert_permutation使用的例子?那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在tensorflow.python.ops.array_ops的用法示例。


在下文中一共展示了array_ops.invert_permutation方法的5個代碼示例,這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚,您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: _SparseReorderGrad

# 需要導入模塊: from tensorflow.python.ops import array_ops [as 別名]
# 或者: from tensorflow.python.ops.array_ops import invert_permutation [as 別名]
def _SparseReorderGrad(op, unused_output_indices_grad, output_values_grad):
  """Gradients for the SparseReorder op.

  Args:
    op: the SparseReorder op
    unused_output_indices_grad: the incoming gradients of the output indices
    output_values_grad: the incoming gradients of the output values

  Returns:
    Gradient for each of the 3 input tensors:
      (input_indices, input_values, input_shape)
    The gradients for input_indices and input_shape is None.
  """
  input_indices = op.inputs[0]
  input_shape = op.inputs[2]

  num_entries = array_ops.shape(input_indices)[0]
  entry_indices = math_ops.range(num_entries)
  sp_unordered = sparse_tensor.SparseTensor(
      input_indices, entry_indices, input_shape)
  sp_ordered = sparse_ops.sparse_reorder(sp_unordered)
  inverted_permutation = array_ops.invert_permutation(sp_ordered.values)

  return (None,
          array_ops.gather(output_values_grad, inverted_permutation),
          None) 
開發者ID:ryfeus,項目名稱:lambda-packs,代碼行數:28,代碼來源:sparse_grad.py

示例2: _TransposeGrad

# 需要導入模塊: from tensorflow.python.ops import array_ops [as 別名]
# 或者: from tensorflow.python.ops.array_ops import invert_permutation [as 別名]
def _TransposeGrad(op, grad):
  """Returns unshuffle(grad)."""
  p = op.inputs[1]
  return [array_ops.transpose(grad, array_ops.invert_permutation(p)), None] 
開發者ID:ryfeus,項目名稱:lambda-packs,代碼行數:6,代碼來源:array_grad.py

示例3: _ProdGrad

# 需要導入模塊: from tensorflow.python.ops import array_ops [as 別名]
# 或者: from tensorflow.python.ops.array_ops import invert_permutation [as 別名]
def _ProdGrad(op, grad):
  """Gradient for Prod."""
  # The gradient can be expressed by dividing the product by each entry of the
  # input tensor, but this approach can't deal with zeros in the input.
  # Here, we avoid this problem by composing the output as a product of two
  # cumprod operations.

  input_shape = array_ops.shape(op.inputs[0])
  # Reshape reduction indices for the case where the parameter is a scalar
  reduction_indices = array_ops.reshape(op.inputs[1], [-1])

  # Expand grad to full input shape
  output_shape_kept_dims = math_ops.reduced_shape(input_shape, op.inputs[1])
  tile_scaling = _safe_shape_div(input_shape, output_shape_kept_dims)
  grad = array_ops.reshape(grad, output_shape_kept_dims)
  grad = array_ops.tile(grad, tile_scaling)

  # Pack all reduced dimensions into a single one, so we can perform the
  # cumprod ops. If the reduction dims list is empty, it defaults to float32,
  # so we need to cast here.  We put all the shape-related ops on CPU to avoid
  # copying back and forth, and since listdiff is CPU only.
  with ops.device("/cpu:0"):
    reduced = math_ops.cast(reduction_indices, dtypes.int32)
    idx = math_ops.range(0, array_ops.rank(op.inputs[0]))
    other, _ = array_ops.setdiff1d(idx, reduced)
    perm = array_ops.concat([reduced, other], 0)
    reduced_num = math_ops.reduce_prod(array_ops.gather(input_shape, reduced))
    other_num = math_ops.reduce_prod(array_ops.gather(input_shape, other))
  permuted = array_ops.transpose(op.inputs[0], perm)
  permuted_shape = array_ops.shape(permuted)
  reshaped = array_ops.reshape(permuted, (reduced_num, other_num))

  # Calculate product, leaving out the current entry
  left = math_ops.cumprod(reshaped, axis=0, exclusive=True)
  right = math_ops.cumprod(reshaped, axis=0, exclusive=True, reverse=True)
  y = array_ops.reshape(left * right, permuted_shape)

  # Invert the transpose and reshape operations.
  # Make sure to set the statically known shape information through a reshape.
  out = grad * array_ops.transpose(y, array_ops.invert_permutation(perm))
  return array_ops.reshape(out, input_shape), None 
開發者ID:ryfeus,項目名稱:lambda-packs,代碼行數:43,代碼來源:math_grad.py

示例4: _ProdGrad

# 需要導入模塊: from tensorflow.python.ops import array_ops [as 別名]
# 或者: from tensorflow.python.ops.array_ops import invert_permutation [as 別名]
def _ProdGrad(op, grad):
  """Gradient for Prod."""
  # The gradient can be expressed by dividing the product by each entry of the
  # input tensor, but this approach can't deal with zeros in the input.
  # Here, we avoid this problem by composing the output as a product of two
  # cumprod operations.

  input_shape = array_ops.shape(op.inputs[0])
  # Reshape reduction indices for the case where the parameter is a scalar
  reduction_indices = array_ops.reshape(op.inputs[1], [-1])

  # Expand grad to full input shape
  output_shape_kept_dims = math_ops.reduced_shape(input_shape, op.inputs[1])
  tile_scaling = _safe_shape_div(input_shape, output_shape_kept_dims)
  grad = array_ops.reshape(grad, output_shape_kept_dims)
  grad = array_ops.tile(grad, tile_scaling)

  # Pack all reduced dimensions into a single one, so we can perform the
  # cumprod ops. If the reduction dims list is empty, it defaults to float32,
  # so we need to cast here.  We put all the shape-related ops on CPU to avoid
  # copying back and forth, and since listdiff is CPU only.
  with ops.device("/cpu:0"):
    reduced = math_ops.cast(reduction_indices, dtypes.int32)
    idx = math_ops.range(0, array_ops.rank(op.inputs[0]))
    other, _ = array_ops.setdiff1d(idx, reduced)
    perm = array_ops.concat(0, [reduced, other])
    reduced_num = math_ops.reduce_prod(array_ops.gather(input_shape, reduced))
    other_num = math_ops.reduce_prod(array_ops.gather(input_shape, other))
  permuted = array_ops.transpose(op.inputs[0], perm)
  permuted_shape = array_ops.shape(permuted)
  reshaped = array_ops.reshape(permuted, (reduced_num, other_num))

  # Calculate product, leaving out the current entry
  left = math_ops.cumprod(reshaped, axis=0, exclusive=True)
  right = math_ops.cumprod(reshaped, axis=0, exclusive=True, reverse=True)
  y = array_ops.reshape(left * right, permuted_shape)

  # Invert the transpose and reshape operations.
  # Make sure to set the statically known shape information through a reshape.
  out = grad * array_ops.transpose(y, array_ops.invert_permutation(perm))
  return array_ops.reshape(out, input_shape), None 
開發者ID:tobegit3hub,項目名稱:deep_image_model,代碼行數:43,代碼來源:math_grad.py

示例5: _ProdGrad

# 需要導入模塊: from tensorflow.python.ops import array_ops [as 別名]
# 或者: from tensorflow.python.ops.array_ops import invert_permutation [as 別名]
def _ProdGrad(op, grad):
  """Gradient for Prod."""
  # The gradient can be expressed by dividing the product by each entry of the
  # input tensor, but this approach can't deal with zeros in the input.
  # Here, we avoid this problem by composing the output as a product of two
  # cumprod operations.

  input_shape = array_ops.shape(op.inputs[0])
  # Reshape reduction indices for the case where the parameter is a scalar
  reduction_indices = array_ops.reshape(op.inputs[1], [-1])

  # Expand grad to full input shape
  output_shape_kept_dims = math_ops.reduced_shape(input_shape, op.inputs[1])
  tile_scaling = _safe_shape_div(input_shape, output_shape_kept_dims)
  grad = array_ops.reshape(grad, output_shape_kept_dims)
  grad = array_ops.tile(grad, tile_scaling)

  # Pack all reduced dimensions into a single one, so we can perform the
  # cumprod ops. If the reduction dims list is empty, it defaults to float32,
  # so we need to cast here.  We put all the shape-related ops on CPU to avoid
  # copying back and forth, and since listdiff is CPU only.
  with ops.device("/cpu:0"):
    rank = array_ops.rank(op.inputs[0])
    reduction_indices = (reduction_indices + rank) % rank
    reduced = math_ops.cast(reduction_indices, dtypes.int32)
    idx = math_ops.range(0, rank)
    other, _ = array_ops.setdiff1d(idx, reduced)
    perm = array_ops.concat([reduced, other], 0)
    reduced_num = math_ops.reduce_prod(array_ops.gather(input_shape, reduced))
    other_num = math_ops.reduce_prod(array_ops.gather(input_shape, other))
  permuted = array_ops.transpose(op.inputs[0], perm)
  permuted_shape = array_ops.shape(permuted)
  reshaped = array_ops.reshape(permuted, (reduced_num, other_num))

  # Calculate product, leaving out the current entry
  left = math_ops.cumprod(reshaped, axis=0, exclusive=True)
  right = math_ops.cumprod(reshaped, axis=0, exclusive=True, reverse=True)
  y = array_ops.reshape(left * right, permuted_shape)

  # Invert the transpose and reshape operations.
  # Make sure to set the statically known shape information through a reshape.
  out = grad * array_ops.transpose(y, array_ops.invert_permutation(perm))
  return array_ops.reshape(out, input_shape), None 
開發者ID:PacktPublishing,項目名稱:Serverless-Deep-Learning-with-TensorFlow-and-AWS-Lambda,代碼行數:45,代碼來源:math_grad.py


注:本文中的tensorflow.python.ops.array_ops.invert_permutation方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台,相關代碼片段篩選自各路編程大神貢獻的開源項目,源碼版權歸原作者所有,傳播和使用請參考對應項目的License;未經允許,請勿轉載。