diff options
author | 2018-03-01 06:45:58 -0800 | |
---|---|---|
committer | 2018-03-01 06:49:20 -0800 | |
commit | bf048d60fbf68fd731df6b2f2ff36a5722b73bb8 (patch) | |
tree | f901b6ac0b97a557a447c11bdf1f240cc6a184ad /tensorflow/go | |
parent | 166980803009ec4577806b4437579159f5e9dd5a (diff) |
Go: Update generated wrapper functions for TensorFlow ops.
PiperOrigin-RevId: 187471483
Diffstat (limited to 'tensorflow/go')
-rw-r--r-- | tensorflow/go/op/wrappers.go | 1156 |
1 files changed, 578 insertions, 578 deletions
diff --git a/tensorflow/go/op/wrappers.go b/tensorflow/go/op/wrappers.go index d9e684a661..336df7c2f7 100644 --- a/tensorflow/go/op/wrappers.go +++ b/tensorflow/go/op/wrappers.go @@ -384,122 +384,6 @@ func FakeQuantWithMinMaxVarsGradient(scope *Scope, gradients tf.Output, inputs t return op.Output(0), op.Output(1), op.Output(2) } -// MutableHashTableOfTensorsV2Attr is an optional argument to MutableHashTableOfTensorsV2. -type MutableHashTableOfTensorsV2Attr func(optionalAttr) - -// MutableHashTableOfTensorsV2Container sets the optional container attribute to value. -// -// value: If non-empty, this table is placed in the given container. -// Otherwise, a default container is used. -// If not specified, defaults to "" -func MutableHashTableOfTensorsV2Container(value string) MutableHashTableOfTensorsV2Attr { - return func(m optionalAttr) { - m["container"] = value - } -} - -// MutableHashTableOfTensorsV2SharedName sets the optional shared_name attribute to value. -// -// value: If non-empty, this table is shared under the given name across -// multiple sessions. -// If not specified, defaults to "" -func MutableHashTableOfTensorsV2SharedName(value string) MutableHashTableOfTensorsV2Attr { - return func(m optionalAttr) { - m["shared_name"] = value - } -} - -// MutableHashTableOfTensorsV2UseNodeNameSharing sets the optional use_node_name_sharing attribute to value. -// If not specified, defaults to false -func MutableHashTableOfTensorsV2UseNodeNameSharing(value bool) MutableHashTableOfTensorsV2Attr { - return func(m optionalAttr) { - m["use_node_name_sharing"] = value - } -} - -// MutableHashTableOfTensorsV2ValueShape sets the optional value_shape attribute to value. -// If not specified, defaults to <> -func MutableHashTableOfTensorsV2ValueShape(value tf.Shape) MutableHashTableOfTensorsV2Attr { - return func(m optionalAttr) { - m["value_shape"] = value - } -} - -// Creates an empty hash table. -// -// This op creates a mutable hash table, specifying the type of its keys and -// values. Each value must be a vector. Data can be inserted into the table using -// the insert operations. It does not support the initialization operation. -// -// Arguments: -// key_dtype: Type of the table keys. -// value_dtype: Type of the table values. -// -// Returns Handle to a table. -func MutableHashTableOfTensorsV2(scope *Scope, key_dtype tf.DataType, value_dtype tf.DataType, optional ...MutableHashTableOfTensorsV2Attr) (table_handle tf.Output) { - if scope.Err() != nil { - return - } - attrs := map[string]interface{}{"key_dtype": key_dtype, "value_dtype": value_dtype} - for _, a := range optional { - a(attrs) - } - opspec := tf.OpSpec{ - Type: "MutableHashTableOfTensorsV2", - - Attrs: attrs, - } - op := scope.AddOperation(opspec) - return op.Output(0) -} - -// ResourceApplyProximalAdagradAttr is an optional argument to ResourceApplyProximalAdagrad. -type ResourceApplyProximalAdagradAttr func(optionalAttr) - -// ResourceApplyProximalAdagradUseLocking sets the optional use_locking attribute to value. -// -// value: If True, updating of the var and accum tensors will be protected by -// a lock; otherwise the behavior is undefined, but may exhibit less contention. -// If not specified, defaults to false -func ResourceApplyProximalAdagradUseLocking(value bool) ResourceApplyProximalAdagradAttr { - return func(m optionalAttr) { - m["use_locking"] = value - } -} - -// Update '*var' and '*accum' according to FOBOS with Adagrad learning rate. -// -// accum += grad * grad -// prox_v = var - lr * grad * (1 / sqrt(accum)) -// var = sign(prox_v)/(1+lr*l2) * max{|prox_v|-lr*l1,0} -// -// Arguments: -// var_: Should be from a Variable(). -// accum: Should be from a Variable(). -// lr: Scaling factor. Must be a scalar. -// l1: L1 regularization. Must be a scalar. -// l2: L2 regularization. Must be a scalar. -// grad: The gradient. -// -// Returns the created operation. -func ResourceApplyProximalAdagrad(scope *Scope, var_ tf.Output, accum tf.Output, lr tf.Output, l1 tf.Output, l2 tf.Output, grad tf.Output, optional ...ResourceApplyProximalAdagradAttr) (o *tf.Operation) { - if scope.Err() != nil { - return - } - attrs := map[string]interface{}{} - for _, a := range optional { - a(attrs) - } - opspec := tf.OpSpec{ - Type: "ResourceApplyProximalAdagrad", - Input: []tf.Input{ - var_, accum, lr, l1, l2, grad, - }, - Attrs: attrs, - } - return scope.AddOperation(opspec) -} - // MutableHashTableV2Attr is an optional argument to MutableHashTableV2. type MutableHashTableV2Attr func(optionalAttr) @@ -564,142 +448,6 @@ func MutableHashTableV2(scope *Scope, key_dtype tf.DataType, value_dtype tf.Data return op.Output(0) } -// MapUnstageNoKeyAttr is an optional argument to MapUnstageNoKey. -type MapUnstageNoKeyAttr func(optionalAttr) - -// MapUnstageNoKeyCapacity sets the optional capacity attribute to value. -// If not specified, defaults to 0 -// -// REQUIRES: value >= 0 -func MapUnstageNoKeyCapacity(value int64) MapUnstageNoKeyAttr { - return func(m optionalAttr) { - m["capacity"] = value - } -} - -// MapUnstageNoKeyMemoryLimit sets the optional memory_limit attribute to value. -// If not specified, defaults to 0 -// -// REQUIRES: value >= 0 -func MapUnstageNoKeyMemoryLimit(value int64) MapUnstageNoKeyAttr { - return func(m optionalAttr) { - m["memory_limit"] = value - } -} - -// MapUnstageNoKeyContainer sets the optional container attribute to value. -// If not specified, defaults to "" -func MapUnstageNoKeyContainer(value string) MapUnstageNoKeyAttr { - return func(m optionalAttr) { - m["container"] = value - } -} - -// MapUnstageNoKeySharedName sets the optional shared_name attribute to value. -// If not specified, defaults to "" -func MapUnstageNoKeySharedName(value string) MapUnstageNoKeyAttr { - return func(m optionalAttr) { - m["shared_name"] = value - } -} - -// Op removes and returns a random (key, value) -// -// from the underlying container. If the underlying container -// does not contain elements, the op will block until it does. -func MapUnstageNoKey(scope *Scope, indices tf.Output, dtypes []tf.DataType, optional ...MapUnstageNoKeyAttr) (key tf.Output, values []tf.Output) { - if scope.Err() != nil { - return - } - attrs := map[string]interface{}{"dtypes": dtypes} - for _, a := range optional { - a(attrs) - } - opspec := tf.OpSpec{ - Type: "MapUnstageNoKey", - Input: []tf.Input{ - indices, - }, - Attrs: attrs, - } - op := scope.AddOperation(opspec) - if scope.Err() != nil { - return - } - var idx int - var err error - key = op.Output(idx) - if values, idx, err = makeOutputList(op, idx, "values"); err != nil { - scope.UpdateErr("MapUnstageNoKey", err) - return - } - return key, values -} - -// HashTableV2Attr is an optional argument to HashTableV2. -type HashTableV2Attr func(optionalAttr) - -// HashTableV2Container sets the optional container attribute to value. -// -// value: If non-empty, this table is placed in the given container. -// Otherwise, a default container is used. -// If not specified, defaults to "" -func HashTableV2Container(value string) HashTableV2Attr { - return func(m optionalAttr) { - m["container"] = value - } -} - -// HashTableV2SharedName sets the optional shared_name attribute to value. -// -// value: If non-empty, this table is shared under the given name across -// multiple sessions. -// If not specified, defaults to "" -func HashTableV2SharedName(value string) HashTableV2Attr { - return func(m optionalAttr) { - m["shared_name"] = value - } -} - -// HashTableV2UseNodeNameSharing sets the optional use_node_name_sharing attribute to value. -// -// value: If true and shared_name is empty, the table is shared -// using the node name. -// If not specified, defaults to false -func HashTableV2UseNodeNameSharing(value bool) HashTableV2Attr { - return func(m optionalAttr) { - m["use_node_name_sharing"] = value - } -} - -// Creates a non-initialized hash table. -// -// This op creates a hash table, specifying the type of its keys and values. -// Before using the table you will have to initialize it. After initialization the -// table will be immutable. -// -// Arguments: -// key_dtype: Type of the table keys. -// value_dtype: Type of the table values. -// -// Returns Handle to a table. -func HashTableV2(scope *Scope, key_dtype tf.DataType, value_dtype tf.DataType, optional ...HashTableV2Attr) (table_handle tf.Output) { - if scope.Err() != nil { - return - } - attrs := map[string]interface{}{"key_dtype": key_dtype, "value_dtype": value_dtype} - for _, a := range optional { - a(attrs) - } - opspec := tf.OpSpec{ - Type: "HashTableV2", - - Attrs: attrs, - } - op := scope.AddOperation(opspec) - return op.Output(0) -} - // Replaces the contents of the table with the specified keys and values. // // The tensor `keys` must be of the same type as the keys of the table. @@ -5642,111 +5390,6 @@ func QuantizedReluX(scope *Scope, features tf.Output, max_value tf.Output, min_f return op.Output(0), op.Output(1), op.Output(2) } -// SummaryWriterAttr is an optional argument to SummaryWriter. -type SummaryWriterAttr func(optionalAttr) - -// SummaryWriterSharedName sets the optional shared_name attribute to value. -// If not specified, defaults to "" -func SummaryWriterSharedName(value string) SummaryWriterAttr { - return func(m optionalAttr) { - m["shared_name"] = value - } -} - -// SummaryWriterContainer sets the optional container attribute to value. -// If not specified, defaults to "" -func SummaryWriterContainer(value string) SummaryWriterAttr { - return func(m optionalAttr) { - m["container"] = value - } -} - -// Returns a handle to be used to access a summary writer. -// -// The summary writer is an in-graph resource which can be used by ops to write -// summaries to event files. -// -// Returns the summary writer resource. Scalar handle. -func SummaryWriter(scope *Scope, optional ...SummaryWriterAttr) (writer tf.Output) { - if scope.Err() != nil { - return - } - attrs := map[string]interface{}{} - for _, a := range optional { - a(attrs) - } - opspec := tf.OpSpec{ - Type: "SummaryWriter", - - Attrs: attrs, - } - op := scope.AddOperation(opspec) - return op.Output(0) -} - -// Computes gradients for SparseSegmentMean. -// -// Returns tensor "output" with same shape as grad, except for dimension 0 whose -// value is output_dim0. -// -// Arguments: -// grad: gradient propagated to the SparseSegmentMean op. -// indices: indices passed to the corresponding SparseSegmentMean op. -// segment_ids: segment_ids passed to the corresponding SparseSegmentMean op. -// output_dim0: dimension 0 of "data" passed to SparseSegmentMean op. -func SparseSegmentMeanGrad(scope *Scope, grad tf.Output, indices tf.Output, segment_ids tf.Output, output_dim0 tf.Output) (output tf.Output) { - if scope.Err() != nil { - return - } - opspec := tf.OpSpec{ - Type: "SparseSegmentMeanGrad", - Input: []tf.Input{ - grad, indices, segment_ids, output_dim0, - }, - } - op := scope.AddOperation(opspec) - return op.Output(0) -} - -// Applies softmax to a batched N-D `SparseTensor`. -// -// The inputs represent an N-D SparseTensor with logical shape `[..., B, C]` -// (where `N >= 2`), and with indices sorted in the canonical lexicographic order. -// -// This op is equivalent to applying the normal `tf.nn.softmax()` to each innermost -// logical submatrix with shape `[B, C]`, but with the catch that *the implicitly -// zero elements do not participate*. Specifically, the algorithm is equivalent -// to the following: -// -// (1) Applies `tf.nn.softmax()` to a densified view of each innermost submatrix -// with shape `[B, C]`, along the size-C dimension; -// (2) Masks out the original implicitly-zero locations; -// (3) Renormalizes the remaining elements. -// -// Hence, the `SparseTensor` result has exactly the same non-zero indices and -// shape. -// -// Arguments: -// sp_indices: 2-D. `NNZ x R` matrix with the indices of non-empty values in a -// SparseTensor, in canonical ordering. -// sp_values: 1-D. `NNZ` non-empty values corresponding to `sp_indices`. -// sp_shape: 1-D. Shape of the input SparseTensor. -// -// Returns 1-D. The `NNZ` values for the result `SparseTensor`. -func SparseSoftmax(scope *Scope, sp_indices tf.Output, sp_values tf.Output, sp_shape tf.Output) (output tf.Output) { - if scope.Err() != nil { - return - } - opspec := tf.OpSpec{ - Type: "SparseSoftmax", - Input: []tf.Input{ - sp_indices, sp_values, sp_shape, - }, - } - op := scope.AddOperation(opspec) - return op.Output(0) -} - // RandomPoissonAttr is an optional argument to RandomPoisson. type RandomPoissonAttr func(optionalAttr) @@ -7025,6 +6668,225 @@ func DestroyResourceOp(scope *Scope, resource tf.Output, optional ...DestroyReso return scope.AddOperation(opspec) } +// SummaryWriterAttr is an optional argument to SummaryWriter. +type SummaryWriterAttr func(optionalAttr) + +// SummaryWriterSharedName sets the optional shared_name attribute to value. +// If not specified, defaults to "" +func SummaryWriterSharedName(value string) SummaryWriterAttr { + return func(m optionalAttr) { + m["shared_name"] = value + } +} + +// SummaryWriterContainer sets the optional container attribute to value. +// If not specified, defaults to "" +func SummaryWriterContainer(value string) SummaryWriterAttr { + return func(m optionalAttr) { + m["container"] = value + } +} + +// Returns a handle to be used to access a summary writer. +// +// The summary writer is an in-graph resource which can be used by ops to write +// summaries to event files. +// +// Returns the summary writer resource. Scalar handle. +func SummaryWriter(scope *Scope, optional ...SummaryWriterAttr) (writer tf.Output) { + if scope.Err() != nil { + return + } + attrs := map[string]interface{}{} + for _, a := range optional { + a(attrs) + } + opspec := tf.OpSpec{ + Type: "SummaryWriter", + + Attrs: attrs, + } + op := scope.AddOperation(opspec) + return op.Output(0) +} + +// Computes gradients for SparseSegmentMean. +// +// Returns tensor "output" with same shape as grad, except for dimension 0 whose +// value is output_dim0. +// +// Arguments: +// grad: gradient propagated to the SparseSegmentMean op. +// indices: indices passed to the corresponding SparseSegmentMean op. +// segment_ids: segment_ids passed to the corresponding SparseSegmentMean op. +// output_dim0: dimension 0 of "data" passed to SparseSegmentMean op. +func SparseSegmentMeanGrad(scope *Scope, grad tf.Output, indices tf.Output, segment_ids tf.Output, output_dim0 tf.Output) (output tf.Output) { + if scope.Err() != nil { + return + } + opspec := tf.OpSpec{ + Type: "SparseSegmentMeanGrad", + Input: []tf.Input{ + grad, indices, segment_ids, output_dim0, + }, + } + op := scope.AddOperation(opspec) + return op.Output(0) +} + +// Applies softmax to a batched N-D `SparseTensor`. +// +// The inputs represent an N-D SparseTensor with logical shape `[..., B, C]` +// (where `N >= 2`), and with indices sorted in the canonical lexicographic order. +// +// This op is equivalent to applying the normal `tf.nn.softmax()` to each innermost +// logical submatrix with shape `[B, C]`, but with the catch that *the implicitly +// zero elements do not participate*. Specifically, the algorithm is equivalent +// to the following: +// +// (1) Applies `tf.nn.softmax()` to a densified view of each innermost submatrix +// with shape `[B, C]`, along the size-C dimension; +// (2) Masks out the original implicitly-zero locations; +// (3) Renormalizes the remaining elements. +// +// Hence, the `SparseTensor` result has exactly the same non-zero indices and +// shape. +// +// Arguments: +// sp_indices: 2-D. `NNZ x R` matrix with the indices of non-empty values in a +// SparseTensor, in canonical ordering. +// sp_values: 1-D. `NNZ` non-empty values corresponding to `sp_indices`. +// sp_shape: 1-D. Shape of the input SparseTensor. +// +// Returns 1-D. The `NNZ` values for the result `SparseTensor`. +func SparseSoftmax(scope *Scope, sp_indices tf.Output, sp_values tf.Output, sp_shape tf.Output) (output tf.Output) { + if scope.Err() != nil { + return + } + opspec := tf.OpSpec{ + Type: "SparseSoftmax", + Input: []tf.Input{ + sp_indices, sp_values, sp_shape, + }, + } + op := scope.AddOperation(opspec) + return op.Output(0) +} + +// Partitions `data` into `num_partitions` tensors using indices from `partitions`. +// +// For each index tuple `js` of size `partitions.ndim`, the slice `data[js, ...]` +// becomes part of `outputs[partitions[js]]`. The slices with `partitions[js] = i` +// are placed in `outputs[i]` in lexicographic order of `js`, and the first +// dimension of `outputs[i]` is the number of entries in `partitions` equal to `i`. +// In detail, +// +// ```python +// outputs[i].shape = [sum(partitions == i)] + data.shape[partitions.ndim:] +// +// outputs[i] = pack([data[js, ...] for js if partitions[js] == i]) +// ``` +// +// `data.shape` must start with `partitions.shape`. +// +// For example: +// +// ```python +// # Scalar partitions. +// partitions = 1 +// num_partitions = 2 +// data = [10, 20] +// outputs[0] = [] # Empty with shape [0, 2] +// outputs[1] = [[10, 20]] +// +// # Vector partitions. +// partitions = [0, 0, 1, 1, 0] +// num_partitions = 2 +// data = [10, 20, 30, 40, 50] +// outputs[0] = [10, 20, 50] +// outputs[1] = [30, 40] +// ``` +// +// See `dynamic_stitch` for an example on how to merge partitions back. +// +// <div style="width:70%; margin:auto; margin-bottom:10px; margin-top:20px;"> +// <img style="width:100%" src="https://www.tensorflow.org/images/DynamicPartition.png" alt> +// </div> +// +// Arguments: +// +// partitions: Any shape. Indices in the range `[0, num_partitions)`. +// num_partitions: The number of partitions to output. +func DynamicPartition(scope *Scope, data tf.Output, partitions tf.Output, num_partitions int64) (outputs []tf.Output) { + if scope.Err() != nil { + return + } + attrs := map[string]interface{}{"num_partitions": num_partitions} + opspec := tf.OpSpec{ + Type: "DynamicPartition", + Input: []tf.Input{ + data, partitions, + }, + Attrs: attrs, + } + op := scope.AddOperation(opspec) + if scope.Err() != nil { + return + } + var idx int + var err error + if outputs, idx, err = makeOutputList(op, idx, "outputs"); err != nil { + scope.UpdateErr("DynamicPartition", err) + return + } + return outputs +} + +// ResourceApplyAdagradAttr is an optional argument to ResourceApplyAdagrad. +type ResourceApplyAdagradAttr func(optionalAttr) + +// ResourceApplyAdagradUseLocking sets the optional use_locking attribute to value. +// +// value: If `True`, updating of the var and accum tensors will be protected +// by a lock; otherwise the behavior is undefined, but may exhibit less +// contention. +// If not specified, defaults to false +func ResourceApplyAdagradUseLocking(value bool) ResourceApplyAdagradAttr { + return func(m optionalAttr) { + m["use_locking"] = value + } +} + +// Update '*var' according to the adagrad scheme. +// +// accum += grad * grad +// var -= lr * grad * (1 / sqrt(accum)) +// +// Arguments: +// var_: Should be from a Variable(). +// accum: Should be from a Variable(). +// lr: Scaling factor. Must be a scalar. +// grad: The gradient. +// +// Returns the created operation. +func ResourceApplyAdagrad(scope *Scope, var_ tf.Output, accum tf.Output, lr tf.Output, grad tf.Output, optional ...ResourceApplyAdagradAttr) (o *tf.Operation) { + if scope.Err() != nil { + return + } + attrs := map[string]interface{}{} + for _, a := range optional { + a(attrs) + } + opspec := tf.OpSpec{ + Type: "ResourceApplyAdagrad", + Input: []tf.Input{ + var_, accum, lr, grad, + }, + Attrs: attrs, + } + return scope.AddOperation(opspec) +} + // CumprodAttr is an optional argument to Cumprod. type CumprodAttr func(optionalAttr) @@ -7909,63 +7771,6 @@ func ResourceScatterNdUpdate(scope *Scope, ref tf.Output, indices tf.Output, upd return scope.AddOperation(opspec) } -// StageSizeAttr is an optional argument to StageSize. -type StageSizeAttr func(optionalAttr) - -// StageSizeCapacity sets the optional capacity attribute to value. -// If not specified, defaults to 0 -// -// REQUIRES: value >= 0 -func StageSizeCapacity(value int64) StageSizeAttr { - return func(m optionalAttr) { - m["capacity"] = value - } -} - -// StageSizeMemoryLimit sets the optional memory_limit attribute to value. -// If not specified, defaults to 0 -// -// REQUIRES: value >= 0 -func StageSizeMemoryLimit(value int64) StageSizeAttr { - return func(m optionalAttr) { - m["memory_limit"] = value - } -} - -// StageSizeContainer sets the optional container attribute to value. -// If not specified, defaults to "" -func StageSizeContainer(value string) StageSizeAttr { - return func(m optionalAttr) { - m["container"] = value - } -} - -// StageSizeSharedName sets the optional shared_name attribute to value. -// If not specified, defaults to "" -func StageSizeSharedName(value string) StageSizeAttr { - return func(m optionalAttr) { - m["shared_name"] = value - } -} - -// Op returns the number of elements in the underlying container. -func StageSize(scope *Scope, dtypes []tf.DataType, optional ...StageSizeAttr) (size tf.Output) { - if scope.Err() != nil { - return - } - attrs := map[string]interface{}{"dtypes": dtypes} - for _, a := range optional { - a(attrs) - } - opspec := tf.OpSpec{ - Type: "StageSize", - - Attrs: attrs, - } - op := scope.AddOperation(opspec) - return op.Output(0) -} - // NonMaxSuppressionAttr is an optional argument to NonMaxSuppression. type NonMaxSuppressionAttr func(optionalAttr) @@ -8705,120 +8510,6 @@ func SparseReduceSum(scope *Scope, input_indices tf.Output, input_values tf.Outp return op.Output(0) } -// Partitions `data` into `num_partitions` tensors using indices from `partitions`. -// -// For each index tuple `js` of size `partitions.ndim`, the slice `data[js, ...]` -// becomes part of `outputs[partitions[js]]`. The slices with `partitions[js] = i` -// are placed in `outputs[i]` in lexicographic order of `js`, and the first -// dimension of `outputs[i]` is the number of entries in `partitions` equal to `i`. -// In detail, -// -// ```python -// outputs[i].shape = [sum(partitions == i)] + data.shape[partitions.ndim:] -// -// outputs[i] = pack([data[js, ...] for js if partitions[js] == i]) -// ``` -// -// `data.shape` must start with `partitions.shape`. -// -// For example: -// -// ```python -// # Scalar partitions. -// partitions = 1 -// num_partitions = 2 -// data = [10, 20] -// outputs[0] = [] # Empty with shape [0, 2] -// outputs[1] = [[10, 20]] -// -// # Vector partitions. -// partitions = [0, 0, 1, 1, 0] -// num_partitions = 2 -// data = [10, 20, 30, 40, 50] -// outputs[0] = [10, 20, 50] -// outputs[1] = [30, 40] -// ``` -// -// See `dynamic_stitch` for an example on how to merge partitions back. -// -// <div style="width:70%; margin:auto; margin-bottom:10px; margin-top:20px;"> -// <img style="width:100%" src="https://www.tensorflow.org/images/DynamicPartition.png" alt> -// </div> -// -// Arguments: -// -// partitions: Any shape. Indices in the range `[0, num_partitions)`. -// num_partitions: The number of partitions to output. -func DynamicPartition(scope *Scope, data tf.Output, partitions tf.Output, num_partitions int64) (outputs []tf.Output) { - if scope.Err() != nil { - return - } - attrs := map[string]interface{}{"num_partitions": num_partitions} - opspec := tf.OpSpec{ - Type: "DynamicPartition", - Input: []tf.Input{ - data, partitions, - }, - Attrs: attrs, - } - op := scope.AddOperation(opspec) - if scope.Err() != nil { - return - } - var idx int - var err error - if outputs, idx, err = makeOutputList(op, idx, "outputs"); err != nil { - scope.UpdateErr("DynamicPartition", err) - return - } - return outputs -} - -// ResourceApplyAdagradAttr is an optional argument to ResourceApplyAdagrad. -type ResourceApplyAdagradAttr func(optionalAttr) - -// ResourceApplyAdagradUseLocking sets the optional use_locking attribute to value. -// -// value: If `True`, updating of the var and accum tensors will be protected -// by a lock; otherwise the behavior is undefined, but may exhibit less -// contention. -// If not specified, defaults to false -func ResourceApplyAdagradUseLocking(value bool) ResourceApplyAdagradAttr { - return func(m optionalAttr) { - m["use_locking"] = value - } -} - -// Update '*var' according to the adagrad scheme. -// -// accum += grad * grad -// var -= lr * grad * (1 / sqrt(accum)) -// -// Arguments: -// var_: Should be from a Variable(). -// accum: Should be from a Variable(). -// lr: Scaling factor. Must be a scalar. -// grad: The gradient. -// -// Returns the created operation. -func ResourceApplyAdagrad(scope *Scope, var_ tf.Output, accum tf.Output, lr tf.Output, grad tf.Output, optional ...ResourceApplyAdagradAttr) (o *tf.Operation) { - if scope.Err() != nil { - return - } - attrs := map[string]interface{}{} - for _, a := range optional { - a(attrs) - } - opspec := tf.OpSpec{ - Type: "ResourceApplyAdagrad", - Input: []tf.Input{ - var_, accum, lr, grad, - }, - Attrs: attrs, - } - return scope.AddOperation(opspec) -} - // Returns element-wise remainder of division. This emulates C semantics in that // // the result here is consistent with a truncating divide. E.g. `truncate(x / y) * @@ -9561,6 +9252,258 @@ func Conv3DBackpropInput(scope *Scope, input tf.Output, filter tf.Output, out_ba return op.Output(0) } +// ResourceApplyProximalAdagradAttr is an optional argument to ResourceApplyProximalAdagrad. +type ResourceApplyProximalAdagradAttr func(optionalAttr) + +// ResourceApplyProximalAdagradUseLocking sets the optional use_locking attribute to value. +// +// value: If True, updating of the var and accum tensors will be protected by +// a lock; otherwise the behavior is undefined, but may exhibit less contention. +// If not specified, defaults to false +func ResourceApplyProximalAdagradUseLocking(value bool) ResourceApplyProximalAdagradAttr { + return func(m optionalAttr) { + m["use_locking"] = value + } +} + +// Update '*var' and '*accum' according to FOBOS with Adagrad learning rate. +// +// accum += grad * grad +// prox_v = var - lr * grad * (1 / sqrt(accum)) +// var = sign(prox_v)/(1+lr*l2) * max{|prox_v|-lr*l1,0} +// +// Arguments: +// var_: Should be from a Variable(). +// accum: Should be from a Variable(). +// lr: Scaling factor. Must be a scalar. +// l1: L1 regularization. Must be a scalar. +// l2: L2 regularization. Must be a scalar. +// grad: The gradient. +// +// Returns the created operation. +func ResourceApplyProximalAdagrad(scope *Scope, var_ tf.Output, accum tf.Output, lr tf.Output, l1 tf.Output, l2 tf.Output, grad tf.Output, optional ...ResourceApplyProximalAdagradAttr) (o *tf.Operation) { + if scope.Err() != nil { + return + } + attrs := map[string]interface{}{} + for _, a := range optional { + a(attrs) + } + opspec := tf.OpSpec{ + Type: "ResourceApplyProximalAdagrad", + Input: []tf.Input{ + var_, accum, lr, l1, l2, grad, + }, + Attrs: attrs, + } + return scope.AddOperation(opspec) +} + +// MutableHashTableOfTensorsV2Attr is an optional argument to MutableHashTableOfTensorsV2. +type MutableHashTableOfTensorsV2Attr func(optionalAttr) + +// MutableHashTableOfTensorsV2Container sets the optional container attribute to value. +// +// value: If non-empty, this table is placed in the given container. +// Otherwise, a default container is used. +// If not specified, defaults to "" +func MutableHashTableOfTensorsV2Container(value string) MutableHashTableOfTensorsV2Attr { + return func(m optionalAttr) { + m["container"] = value + } +} + +// MutableHashTableOfTensorsV2SharedName sets the optional shared_name attribute to value. +// +// value: If non-empty, this table is shared under the given name across +// multiple sessions. +// If not specified, defaults to "" +func MutableHashTableOfTensorsV2SharedName(value string) MutableHashTableOfTensorsV2Attr { + return func(m optionalAttr) { + m["shared_name"] = value + } +} + +// MutableHashTableOfTensorsV2UseNodeNameSharing sets the optional use_node_name_sharing attribute to value. +// If not specified, defaults to false +func MutableHashTableOfTensorsV2UseNodeNameSharing(value bool) MutableHashTableOfTensorsV2Attr { + return func(m optionalAttr) { + m["use_node_name_sharing"] = value + } +} + +// MutableHashTableOfTensorsV2ValueShape sets the optional value_shape attribute to value. +// If not specified, defaults to <> +func MutableHashTableOfTensorsV2ValueShape(value tf.Shape) MutableHashTableOfTensorsV2Attr { + return func(m optionalAttr) { + m["value_shape"] = value + } +} + +// Creates an empty hash table. +// +// This op creates a mutable hash table, specifying the type of its keys and +// values. Each value must be a vector. Data can be inserted into the table using +// the insert operations. It does not support the initialization operation. +// +// Arguments: +// key_dtype: Type of the table keys. +// value_dtype: Type of the table values. +// +// Returns Handle to a table. +func MutableHashTableOfTensorsV2(scope *Scope, key_dtype tf.DataType, value_dtype tf.DataType, optional ...MutableHashTableOfTensorsV2Attr) (table_handle tf.Output) { + if scope.Err() != nil { + return + } + attrs := map[string]interface{}{"key_dtype": key_dtype, "value_dtype": value_dtype} + for _, a := range optional { + a(attrs) + } + opspec := tf.OpSpec{ + Type: "MutableHashTableOfTensorsV2", + + Attrs: attrs, + } + op := scope.AddOperation(opspec) + return op.Output(0) +} + +// HashTableV2Attr is an optional argument to HashTableV2. +type HashTableV2Attr func(optionalAttr) + +// HashTableV2Container sets the optional container attribute to value. +// +// value: If non-empty, this table is placed in the given container. +// Otherwise, a default container is used. +// If not specified, defaults to "" +func HashTableV2Container(value string) HashTableV2Attr { + return func(m optionalAttr) { + m["container"] = value + } +} + +// HashTableV2SharedName sets the optional shared_name attribute to value. +// +// value: If non-empty, this table is shared under the given name across +// multiple sessions. +// If not specified, defaults to "" +func HashTableV2SharedName(value string) HashTableV2Attr { + return func(m optionalAttr) { + m["shared_name"] = value + } +} + +// HashTableV2UseNodeNameSharing sets the optional use_node_name_sharing attribute to value. +// +// value: If true and shared_name is empty, the table is shared +// using the node name. +// If not specified, defaults to false +func HashTableV2UseNodeNameSharing(value bool) HashTableV2Attr { + return func(m optionalAttr) { + m["use_node_name_sharing"] = value + } +} + +// Creates a non-initialized hash table. +// +// This op creates a hash table, specifying the type of its keys and values. +// Before using the table you will have to initialize it. After initialization the +// table will be immutable. +// +// Arguments: +// key_dtype: Type of the table keys. +// value_dtype: Type of the table values. +// +// Returns Handle to a table. +func HashTableV2(scope *Scope, key_dtype tf.DataType, value_dtype tf.DataType, optional ...HashTableV2Attr) (table_handle tf.Output) { + if scope.Err() != nil { + return + } + attrs := map[string]interface{}{"key_dtype": key_dtype, "value_dtype": value_dtype} + for _, a := range optional { + a(attrs) + } + opspec := tf.OpSpec{ + Type: "HashTableV2", + + Attrs: attrs, + } + op := scope.AddOperation(opspec) + return op.Output(0) +} + +// MapUnstageNoKeyAttr is an optional argument to MapUnstageNoKey. +type MapUnstageNoKeyAttr func(optionalAttr) + +// MapUnstageNoKeyCapacity sets the optional capacity attribute to value. +// If not specified, defaults to 0 +// +// REQUIRES: value >= 0 +func MapUnstageNoKeyCapacity(value int64) MapUnstageNoKeyAttr { + return func(m optionalAttr) { + m["capacity"] = value + } +} + +// MapUnstageNoKeyMemoryLimit sets the optional memory_limit attribute to value. +// If not specified, defaults to 0 +// +// REQUIRES: value >= 0 +func MapUnstageNoKeyMemoryLimit(value int64) MapUnstageNoKeyAttr { + return func(m optionalAttr) { + m["memory_limit"] = value + } +} + +// MapUnstageNoKeyContainer sets the optional container attribute to value. +// If not specified, defaults to "" +func MapUnstageNoKeyContainer(value string) MapUnstageNoKeyAttr { + return func(m optionalAttr) { + m["container"] = value + } +} + +// MapUnstageNoKeySharedName sets the optional shared_name attribute to value. +// If not specified, defaults to "" +func MapUnstageNoKeySharedName(value string) MapUnstageNoKeyAttr { + return func(m optionalAttr) { + m["shared_name"] = value + } +} + +// Op removes and returns a random (key, value) +// +// from the underlying container. If the underlying container +// does not contain elements, the op will block until it does. +func MapUnstageNoKey(scope *Scope, indices tf.Output, dtypes []tf.DataType, optional ...MapUnstageNoKeyAttr) (key tf.Output, values []tf.Output) { + if scope.Err() != nil { + return + } + attrs := map[string]interface{}{"dtypes": dtypes} + for _, a := range optional { + a(attrs) + } + opspec := tf.OpSpec{ + Type: "MapUnstageNoKey", + Input: []tf.Input{ + indices, + }, + Attrs: attrs, + } + op := scope.AddOperation(opspec) + if scope.Err() != nil { + return + } + var idx int + var err error + key = op.Output(idx) + if values, idx, err = makeOutputList(op, idx, "values"); err != nil { + scope.UpdateErr("MapUnstageNoKey", err) + return + } + return key, values +} + // Inverse 2D fast Fourier transform. // // Computes the inverse 2-dimensional discrete Fourier transform over the @@ -12257,6 +12200,63 @@ func MutableDenseHashTableV2(scope *Scope, empty_key tf.Output, value_dtype tf.D return op.Output(0) } +// StageSizeAttr is an optional argument to StageSize. +type StageSizeAttr func(optionalAttr) + +// StageSizeCapacity sets the optional capacity attribute to value. +// If not specified, defaults to 0 +// +// REQUIRES: value >= 0 +func StageSizeCapacity(value int64) StageSizeAttr { + return func(m optionalAttr) { + m["capacity"] = value + } +} + +// StageSizeMemoryLimit sets the optional memory_limit attribute to value. +// If not specified, defaults to 0 +// +// REQUIRES: value >= 0 +func StageSizeMemoryLimit(value int64) StageSizeAttr { + return func(m optionalAttr) { + m["memory_limit"] = value + } +} + +// StageSizeContainer sets the optional container attribute to value. +// If not specified, defaults to "" +func StageSizeContainer(value string) StageSizeAttr { + return func(m optionalAttr) { + m["container"] = value + } +} + +// StageSizeSharedName sets the optional shared_name attribute to value. +// If not specified, defaults to "" +func StageSizeSharedName(value string) StageSizeAttr { + return func(m optionalAttr) { + m["shared_name"] = value + } +} + +// Op returns the number of elements in the underlying container. +func StageSize(scope *Scope, dtypes []tf.DataType, optional ...StageSizeAttr) (size tf.Output) { + if scope.Err() != nil { + return + } + attrs := map[string]interface{}{"dtypes": dtypes} + for _, a := range optional { + a(attrs) + } + opspec := tf.OpSpec{ + Type: "StageSize", + + Attrs: attrs, + } + op := scope.AddOperation(opspec) + return op.Output(0) +} + // Produces the max pool of the input tensor for quantized types. // // Arguments: @@ -12999,6 +12999,56 @@ func Neg(scope *Scope, x tf.Output) (y tf.Output) { return op.Output(0) } +// FakeQuantWithMinMaxVarsAttr is an optional argument to FakeQuantWithMinMaxVars. +type FakeQuantWithMinMaxVarsAttr func(optionalAttr) + +// FakeQuantWithMinMaxVarsNumBits sets the optional num_bits attribute to value. +// If not specified, defaults to 8 +func FakeQuantWithMinMaxVarsNumBits(value int64) FakeQuantWithMinMaxVarsAttr { + return func(m optionalAttr) { + m["num_bits"] = value + } +} + +// FakeQuantWithMinMaxVarsNarrowRange sets the optional narrow_range attribute to value. +// If not specified, defaults to false +func FakeQuantWithMinMaxVarsNarrowRange(value bool) FakeQuantWithMinMaxVarsAttr { + return func(m optionalAttr) { + m["narrow_range"] = value + } +} + +// Fake-quantize the 'inputs' tensor of type float via global float scalars `min` +// +// and `max` to 'outputs' tensor of same shape as `inputs`. +// +// `[min; max]` define the clamping range for the `inputs` data. +// `inputs` values are quantized into the quantization range (`[0; 2^num_bits - 1]` +// when `narrow_range` is false and `[1; 2^num_bits - 1]` when it is true) and +// then de-quantized and output as floats in `[min; max]` interval. +// `num_bits` is the bitwidth of the quantization; between 2 and 8, inclusive. +// +// This operation has a gradient and thus allows for training `min` and `max` +// values. +func FakeQuantWithMinMaxVars(scope *Scope, inputs tf.Output, min tf.Output, max tf.Output, optional ...FakeQuantWithMinMaxVarsAttr) (outputs tf.Output) { + if scope.Err() != nil { + return + } + attrs := map[string]interface{}{} + for _, a := range optional { + a(attrs) + } + opspec := tf.OpSpec{ + Type: "FakeQuantWithMinMaxVars", + Input: []tf.Input{ + inputs, min, max, + }, + Attrs: attrs, + } + op := scope.AddOperation(opspec) + return op.Output(0) +} + // Writes a `Summary` protocol buffer with a histogram. // // The generated @@ -28230,53 +28280,3 @@ func QuantizedInstanceNorm(scope *Scope, x tf.Output, x_min tf.Output, x_max tf. op := scope.AddOperation(opspec) return op.Output(0), op.Output(1), op.Output(2) } - -// FakeQuantWithMinMaxVarsAttr is an optional argument to FakeQuantWithMinMaxVars. -type FakeQuantWithMinMaxVarsAttr func(optionalAttr) - -// FakeQuantWithMinMaxVarsNumBits sets the optional num_bits attribute to value. -// If not specified, defaults to 8 -func FakeQuantWithMinMaxVarsNumBits(value int64) FakeQuantWithMinMaxVarsAttr { - return func(m optionalAttr) { - m["num_bits"] = value - } -} - -// FakeQuantWithMinMaxVarsNarrowRange sets the optional narrow_range attribute to value. -// If not specified, defaults to false -func FakeQuantWithMinMaxVarsNarrowRange(value bool) FakeQuantWithMinMaxVarsAttr { - return func(m optionalAttr) { - m["narrow_range"] = value - } -} - -// Fake-quantize the 'inputs' tensor of type float via global float scalars `min` -// -// and `max` to 'outputs' tensor of same shape as `inputs`. -// -// `[min; max]` define the clamping range for the `inputs` data. -// `inputs` values are quantized into the quantization range (`[0; 2^num_bits - 1]` -// when `narrow_range` is false and `[1; 2^num_bits - 1]` when it is true) and -// then de-quantized and output as floats in `[min; max]` interval. -// `num_bits` is the bitwidth of the quantization; between 2 and 8, inclusive. -// -// This operation has a gradient and thus allows for training `min` and `max` -// values. -func FakeQuantWithMinMaxVars(scope *Scope, inputs tf.Output, min tf.Output, max tf.Output, optional ...FakeQuantWithMinMaxVarsAttr) (outputs tf.Output) { - if scope.Err() != nil { - return - } - attrs := map[string]interface{}{} - for _, a := range optional { - a(attrs) - } - opspec := tf.OpSpec{ - Type: "FakeQuantWithMinMaxVars", - Input: []tf.Input{ - inputs, min, max, - }, - Attrs: attrs, - } - op := scope.AddOperation(opspec) - return op.Output(0) -} |