1# Copyright 2018 The TensorFlow Authors. All Rights Reserved. 2# 3# Licensed under the Apache License, Version 2.0 (the "License"); 4# you may not use this file except in compliance with the License. 5# You may obtain a copy of the License at 6# 7# http://www.apache.org/licenses/LICENSE-2.0 8# 9# Unless required by applicable law or agreed to in writing, software 10# distributed under the License is distributed on an "AS IS" BASIS, 11# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12# See the License for the specific language governing permissions and 13# limitations under the License. 14# ============================================================================== 15"""Ops to convert between RaggedTensors and other tensor types.""" 16 17from tensorflow.python.framework import dtypes 18from tensorflow.python.framework import indexed_slices 19from tensorflow.python.framework import ops 20from tensorflow.python.ops import array_ops 21from tensorflow.python.ops import gen_ragged_conversion_ops 22from tensorflow.python.ops import math_ops 23from tensorflow.python.ops.ragged import ragged_tensor 24 25 26def from_tensor(tensor, 27 lengths=None, 28 padding=None, 29 ragged_rank=1, 30 row_splits_dtype=dtypes.int64, 31 name=None): 32 if ragged_tensor.is_ragged(tensor): 33 return tensor 34 else: 35 return ragged_tensor.RaggedTensor.from_tensor( 36 tensor, 37 lengths=lengths, 38 padding=padding, 39 ragged_rank=ragged_rank, 40 row_splits_dtype=row_splits_dtype, 41 name=name) 42 43 44def to_tensor(rt_input, default_value=None, name=None): 45 if ragged_tensor.is_ragged(rt_input): 46 return rt_input.to_tensor(default_value, name) 47 else: 48 return rt_input 49 50 51def ragged_to_dense(rt_input, default_value=None, shape=None): 52 """Create a dense tensor from a ragged tensor.""" 53 return rt_input.to_tensor(default_value=default_value, shape=shape) 54 55 56@ops.RegisterGradient("RaggedTensorToTensor") 57def _ragged_tensor_to_tensor_grad(op, grad): 58 """Gradient for RaggedToTensor op.""" 59 # Extract inputs from the op. 60 flat_values = op.inputs[1] 61 default_value = op.inputs[2] 62 row_partition_tensors = op.inputs[3:] 63 row_partition_types = op.get_attr("row_partition_types") 64 flat_value_shape = array_ops.shape(flat_values) 65 ragged_rank = sum( 66 1 for typ in row_partition_types if typ != b"FIRST_DIM_SIZE") 67 68 # Create two tensors that correspond 1:1 with grad (and op.output): 69 # * indices[i1...iN] is the index in `flat_values` of the value used to 70 # populate output[i1...iN] (if the value came from `flat_values`) or 71 # -1 (if the value came from `default_value`). 72 # * mask[i1...iN] is true if output[i1...iN] came from `flat_values`, or 73 # false if it came from `default_value`. 74 indices = gen_ragged_conversion_ops.ragged_tensor_to_tensor( 75 shape=array_ops.shape(grad)[:1 + ragged_rank], 76 values=math_ops.range(flat_value_shape[0]), 77 default_value=-1, 78 row_partition_types=row_partition_types, 79 row_partition_tensors=row_partition_tensors) 80 mask = math_ops.not_equal(indices, -1) 81 82 # Select out the gradients & indices that came from `flat_values`, and use 83 # those to construct the gradient for `flat_values` (as an IndexedSlices). 84 values_grad = indexed_slices.IndexedSlices( 85 values=array_ops.boolean_mask(grad, mask), 86 indices=array_ops.boolean_mask(indices, mask), 87 dense_shape=flat_value_shape) 88 89 # Select out the gradients that came from `default_value`, and sum them to 90 # get the gradient for the default. Note that the default_value may have 91 # been broadcast as part of the RaggedTensorToTensor operation, so we also 92 # need to reduce any dimensions that might have been broadcast. 93 default_grads = array_ops.boolean_mask(grad, ~mask) 94 dims_to_reduce = math_ops.range( 95 array_ops.rank(default_grads) - 96 _rank_ignoring_leading_dims_with_size_1(default_value)) 97 default_grad = math_ops.reduce_sum(default_grads, axis=dims_to_reduce) 98 99 # Restore any leading dims with size one. 100 default_grad = array_ops.reshape(default_grad, array_ops.shape(default_value)) 101 102 return ([None, values_grad, default_grad] + 103 [None for _ in row_partition_tensors]) 104 105 106def _rank_ignoring_leading_dims_with_size_1(value): 107 """Returns `rank(value)`, ignoring any leading dimensions with size 1.""" 108 # Compute the result using static shape, if possible. 109 if value.shape.rank is not None: 110 ndims = value.shape.rank 111 for dim in value.shape.dims: 112 if dim.value == 1: 113 ndims -= 1 114 elif dim.value is None: 115 ndims = None # Can't compute the result using static shape. 116 break 117 else: 118 break 119 if ndims is not None: 120 return ndims 121 122 # Otherwise, we need to compute the result dynamically. The math we use to 123 # do this is a bit round-about, so here's an example to illustrate: 124 # shape = [1, 1, 3, 5, 1, 4] # shape(value) 125 # dim_is_one = [1, 1, 0, 0, 1, 0] # equal(shape, 1) 126 # leading_ones = [1, 1, 0, 0, 0, 0] # cumprod(dim_is_one) 127 # num_leading_ones = 2 # reduce_sum(leading_ones) 128 # result = 4 # rank(value) - num_leading_ones 129 shape = array_ops.shape(value) 130 dim_is_one = math_ops.cast(math_ops.equal(shape, 1), dtypes.int32) 131 leading_ones = math_ops.cumprod(dim_is_one) 132 num_leading_ones = math_ops.reduce_sum(leading_ones) 133 return array_ops.rank(value) - num_leading_ones 134 135 136def to_sparse(rt_input, name=None): 137 return rt_input.to_sparse(name) 138 139 140def from_sparse(st_input, name=None): 141 return ragged_tensor.RaggedTensor.from_sparse(st_input, name) 142 143 144@ops.RegisterGradient("RaggedTensorFromVariant") 145def _ragged_tensor_from_variant_grad(op, *grads): 146 """Gradient for RaggedTensorFromVariant op.""" 147 148 variant_rank = op.inputs[0].shape.rank 149 if variant_rank == 0: 150 batched_input = False 151 elif variant_rank == 1: 152 batched_input = True 153 elif variant_rank is None: 154 batched_input = (op.get_attr("output_ragged_rank") > 0) 155 else: 156 # TODO(edloper): Add a batch_dims argument to RaggedTensorToVariant, so 157 # we can support this. 158 raise ValueError("Unable to compute gradient: RaggedTensorToVariant " 159 "can currently only generate 0D or 1D output.") 160 return [ 161 gen_ragged_conversion_ops.ragged_tensor_to_variant( 162 rt_nested_splits=op.outputs[:-1], 163 rt_dense_values=grads[-1], 164 batched_input=batched_input) 165 ] 166 167 168@ops.RegisterGradient("RaggedTensorToVariant") 169def _ragged_tensor_to_variant_grad(op, encoded_ragged_grad): 170 """Gradient for RaggedTensorToVariant op.""" 171 dense_values = op.inputs[-1] 172 ragged_rank = len(op.inputs) - 1 173 row_splits = 0 if ragged_rank == 0 else op.inputs[0] 174 values_grad = gen_ragged_conversion_ops.ragged_tensor_to_variant_gradient( 175 encoded_ragged_grad=encoded_ragged_grad, 176 row_splits=row_splits, 177 dense_values_shape=array_ops.shape(dense_values), 178 Tvalues=op.inputs[-1].dtype) 179 result = [None] * ragged_rank + [values_grad] 180 return result 181