mirror of
https://github.com/tensorflow/haskell.git
synced 2024-06-30 00:18:34 +02:00
379 lines
17 KiB
Plaintext
379 lines
17 KiB
Plaintext
-- Hoogle documentation, generated by Haddock
|
|
-- See Hoogle, http://www.haskell.org/hoogle/
|
|
|
|
|
|
-- | Friendly layer around TensorFlow bindings.
|
|
--
|
|
-- Please see README.md
|
|
@package tensorflow-ops
|
|
@version 0.1.0.0
|
|
|
|
|
|
-- | This module contains definitions for some built-in TensorFlow
|
|
-- operations.
|
|
--
|
|
-- Note that certain, "stateful" ops like <a>variable</a> and
|
|
-- <a>assign</a> return a <a>Build</a> action (e.g., <tt>Build (Tensor
|
|
-- Ref a)</tt> instead of a pure value; the returned <a>Tensor</a>s are
|
|
-- always rendered in the current <a>Build</a> context. This approach
|
|
-- helps us avoid problems with inlining or common subexpression
|
|
-- elimination, by writing
|
|
--
|
|
-- <pre>
|
|
-- do
|
|
-- v <- variable []
|
|
-- w <- assign v 3
|
|
-- render $ w * w
|
|
-- </pre>
|
|
--
|
|
-- instead of
|
|
--
|
|
-- <pre>
|
|
-- let
|
|
-- v = variable []
|
|
-- w = assign v 3
|
|
-- in w * w
|
|
-- </pre>
|
|
--
|
|
-- since the latter could be reasonably transformed by the compiler into
|
|
-- (or vice versa)
|
|
--
|
|
-- <pre>
|
|
-- let
|
|
-- v = variable []
|
|
-- w = assign v 3
|
|
-- w' = assign v 3
|
|
-- in w * w'
|
|
-- </pre>
|
|
--
|
|
-- Ops should return a <a>Build</a> action if their original
|
|
-- <tt>OpDef</tt> marks them as stateful, or if they take any Refs as
|
|
-- input. (This mirrors the rules that TensorFlow uses to avoid common
|
|
-- subexpression elimination.)
|
|
module TensorFlow.Ops
|
|
|
|
-- | Returns x + y element-wise.
|
|
--
|
|
-- <ul>
|
|
-- <li>NOTE*: <tt>Add</tt> supports broadcasting. <tt>AddN</tt> does not.
|
|
-- More about broadcasting <a>here</a></li>
|
|
-- </ul>
|
|
add :: (TensorType t, OneOf ((:) * (Complex Double) ((:) * (Complex Float) ((:) * ByteString ((:) * Int16 ((:) * Int32 ((:) * Int64 ((:) * Int8 ((:) * Word16 ((:) * Word8 ((:) * Double ((:) * Float ([] *)))))))))))) t) => Tensor v1 t -> Tensor v2 t -> Tensor Value t
|
|
|
|
-- | Computes the absolute value of a tensor.
|
|
--
|
|
-- Given a tensor <tt>x</tt>, this operation returns a tensor containing
|
|
-- the absolute value of each element in <tt>x</tt>. For example, if x is
|
|
-- an input element and y is an output element, this operation computes
|
|
-- \(y = |x|\).
|
|
abs :: (TensorType t, OneOf ((:) * Int32 ((:) * Int64 ((:) * Word16 ((:) * Double ((:) * Float ([] *)))))) t) => Tensor v1 t -> Tensor Value t
|
|
|
|
-- | Add all input tensors element wise.
|
|
addN :: (TensorType t, OneOf ((:) * (Complex Double) ((:) * (Complex Float) ((:) * Int16 ((:) * Int32 ((:) * Int64 ((:) * Int8 ((:) * Word16 ((:) * Word8 ((:) * Double ((:) * Float ([] *))))))))))) t) => [Tensor v1 t] -> Tensor Value t
|
|
|
|
-- | Returns the index with the largest value across dimensions of a
|
|
-- tensor.
|
|
argMax :: (TensorType t, OneOf ((:) * (Complex Double) ((:) * (Complex Float) ((:) * Int16 ((:) * Int32 ((:) * Int64 ((:) * Int8 ((:) * Word16 ((:) * Word8 ((:) * Double ((:) * Float ([] *))))))))))) t, TensorType tidx, OneOf ((:) * Int32 ((:) * Int64 ([] *))) tidx) => Tensor v1 t -> Tensor v2 tidx -> Tensor Value Int64
|
|
assign :: TensorType a => Tensor Ref a -> Tensor v a -> Build (Tensor Ref a)
|
|
|
|
-- | Return the reduction indices for computing gradients of s0 op s1 with
|
|
-- broadcast.
|
|
--
|
|
-- This is typically used by gradient computations for a broadcasting
|
|
-- operation.
|
|
broadcastGradientArgs :: (TensorType t, OneOf ((:) * Int32 ((:) * Int64 ([] *))) t) => Tensor v1 t -> Tensor v2 t -> (Tensor Value t, Tensor Value t)
|
|
|
|
-- | Cast x of type SrcT to y of DstT.
|
|
cast :: (TensorType dstT, TensorType srcT) => Tensor v1 srcT -> Tensor Value dstT
|
|
|
|
-- | Concatenates tensors along one dimension.
|
|
concat :: TensorType t => Tensor v1 Int32 -> [Tensor v2 t] -> Tensor Value t
|
|
|
|
-- | Create a constant tensor.
|
|
--
|
|
-- The values should be in row major order, e.g.,
|
|
--
|
|
-- element 0: index (0, ..., 0) element 1: index (0, ..., 1) ...
|
|
constant :: TensorType a => Shape -> [a] -> Tensor Value a
|
|
expandDims :: (TensorType t) => Tensor v1 t -> Tensor v2 Int32 -> Tensor Value t
|
|
|
|
-- | Creates a variable initialized to the given value. Initialization
|
|
-- happens next time session runs.
|
|
initializedVariable :: TensorType a => Tensor Value a -> Build (Tensor Ref a)
|
|
|
|
-- | Creates a zero-initialized variable with the given shape.
|
|
zeroInitializedVariable :: (TensorType a, Num a) => Shape -> Build (Tensor Ref a)
|
|
|
|
-- | Creates a tensor filled with a scalar value.
|
|
--
|
|
-- This operation creates a tensor of shape <tt>dims</tt> and fills it
|
|
-- with <a>value</a>.
|
|
--
|
|
-- For example:
|
|
--
|
|
-- ```prettyprint # Output tensor has shape [2, 3]. fill([2, 3], 9)
|
|
-- ==> [[9, 9, 9] [9, 9, 9]] ```
|
|
fill :: TensorType t => Tensor v1 Int32 -> Tensor v2 t -> Tensor Value t
|
|
|
|
-- | Multiply the matrix "a" by the matrix "b".
|
|
--
|
|
-- The inputs must be two-dimensional matrices and the inner dimension of
|
|
-- "a" (after being transposed if transpose_a is true) must match the
|
|
-- outer dimension of "b" (after being transposed if transposed_b is
|
|
-- true).
|
|
--
|
|
-- <ul>
|
|
-- <li>Note*: The default kernel implementation for MatMul on GPUs uses
|
|
-- cublas.</li>
|
|
-- </ul>
|
|
matMul :: (TensorType t, OneOf ((:) * (Complex Double) ((:) * (Complex Float) ((:) * Int32 ((:) * Word16 ((:) * Double ((:) * Float ([] *))))))) t) => Tensor v1 t -> Tensor v2 t -> Tensor Value t
|
|
matTranspose :: TensorType a => Tensor v a -> Tensor Value a
|
|
|
|
-- | Returns x * y element-wise.
|
|
--
|
|
-- <ul>
|
|
-- <li>NOTE*: <tt>Mul</tt> supports broadcasting. More about broadcasting
|
|
-- <a>here</a></li>
|
|
-- </ul>
|
|
mul :: (TensorType t, OneOf ((:) * (Complex Double) ((:) * (Complex Float) ((:) * Int16 ((:) * Int32 ((:) * Int64 ((:) * Int8 ((:) * Word16 ((:) * Word8 ((:) * Double ((:) * Float ([] *))))))))))) t) => Tensor v1 t -> Tensor v2 t -> Tensor Value t
|
|
|
|
-- | Computes numerical negative value element-wise.
|
|
--
|
|
-- I.e., \(y = -x\).
|
|
neg :: (TensorType t, OneOf ((:) * (Complex Double) ((:) * (Complex Float) ((:) * Int32 ((:) * Int64 ((:) * Word16 ((:) * Double ((:) * Float ([] *)))))))) t) => Tensor v1 t -> Tensor Value t
|
|
|
|
-- | Packs a list of <tt>N</tt> rank-<tt>R</tt> tensors into one
|
|
-- rank-`(R+1)` tensor.
|
|
--
|
|
-- Packs the <tt>N</tt> tensors in <tt>values</tt> into a tensor with
|
|
-- rank one higher than each tensor in <tt>values</tt>, by packing them
|
|
-- along the <tt>axis</tt> dimension. Given a list of tensors of shape
|
|
-- `(A, B, C)`;
|
|
--
|
|
-- if `axis == 0` then the <tt>output</tt> tensor will have the shape
|
|
-- `(N, A, B, C)`. if `axis == 1` then the <tt>output</tt> tensor will
|
|
-- have the shape `(A, N, B, C)`. Etc.
|
|
--
|
|
-- For example:
|
|
--
|
|
-- ```prettyprint # <tt>x</tt> is [1, 4] # <tt>y</tt> is [2, 5] #
|
|
-- <tt>z</tt> is [3, 6] pack([x, y, z]) => [[1, 4], [2, 5], [3, 6]] #
|
|
-- Pack along first dim. pack([x, y, z], axis=1) => [[1, 2, 3], [4, 5,
|
|
-- 6]] ```
|
|
--
|
|
-- This is the opposite of <a>unpack</a>.
|
|
pack :: TensorType t => [Tensor v1 t] -> Tensor Value t
|
|
placeholder :: TensorType a => Shape -> Build (Tensor Value a)
|
|
|
|
-- | Creates a sequence of integers.
|
|
--
|
|
-- This operation creates a sequence of integers that begins at
|
|
-- <tt>start</tt> and extends by increments of <tt>delta</tt> up to but
|
|
-- not including <tt>limit</tt>.
|
|
--
|
|
-- For example:
|
|
--
|
|
-- ``` # <tt>start</tt> is 3 # <tt>limit</tt> is 18 # <tt>delta</tt> is 3
|
|
-- tf.range(start, limit, delta) ==> [3, 6, 9, 12, 15] ```
|
|
range :: (TensorType tidx, OneOf ((:) * Int32 ((:) * Int64 ([] *))) tidx) => Tensor v1 tidx -> Tensor v2 tidx -> Tensor v3 tidx -> Tensor Value tidx
|
|
|
|
-- | Helper function for reduction ops (translation of
|
|
-- math_ops.reduced_shape).
|
|
reducedShape :: (OneOf '[Int32, Int64] t1, OneOf '[Int32, Int64] t2) => Tensor v1 t1 -> Tensor v2 t2 -> Tensor Value Int32
|
|
|
|
-- | Computes rectified linear: `max(features, 0)`.
|
|
relu :: (TensorType t, OneOf ((:) * Int16 ((:) * Int32 ((:) * Int64 ((:) * Int8 ((:) * Word16 ((:) * Word8 ((:) * Double ((:) * Float ([] *))))))))) t) => Tensor v1 t -> Tensor Value t
|
|
|
|
-- | Computes rectified linear gradients for a Relu operation.
|
|
reluGrad :: (TensorType t, OneOf ((:) * Int16 ((:) * Int32 ((:) * Int64 ((:) * Int8 ((:) * Word16 ((:) * Word8 ((:) * Double ((:) * Float ([] *))))))))) t) => Tensor v1 t -> Tensor v2 t -> Tensor Value t
|
|
|
|
-- | Reshapes a tensor.
|
|
--
|
|
-- Given <tt>tensor</tt>, this operation returns a tensor that has the
|
|
-- same values as <tt>tensor</tt> with shape <a>shape</a>.
|
|
--
|
|
-- If one component of <a>shape</a> is the special value -1, the size of
|
|
-- that dimension is computed so that the total size remains constant. In
|
|
-- particular, a <a>shape</a> of `[-1]` flattens into 1-D. At most one
|
|
-- component of <a>shape</a> can be -1.
|
|
--
|
|
-- If <a>shape</a> is 1-D or higher, then the operation returns a tensor
|
|
-- with shape <a>shape</a> filled with the values of <tt>tensor</tt>. In
|
|
-- this case, the number of elements implied by <a>shape</a> must be the
|
|
-- same as the number of elements in <tt>tensor</tt>.
|
|
--
|
|
-- For example:
|
|
--
|
|
-- ```prettyprint # tensor <tt>t</tt> is [1, 2, 3, 4, 5, 6, 7, 8, 9] #
|
|
-- tensor <tt>t</tt> has shape [9] reshape(t, [3, 3]) ==> [[1, 2, 3],
|
|
-- [4, 5, 6], [7, 8, 9]]
|
|
--
|
|
-- # tensor <tt>t</tt> is [[[1, 1], [2, 2]], # [[3, 3], [4, 4]]] # tensor
|
|
-- <tt>t</tt> has shape [2, 2, 2] reshape(t, [2, 4]) ==> [[1, 1, 2,
|
|
-- 2], [3, 3, 4, 4]]
|
|
--
|
|
-- # tensor <tt>t</tt> is [[[1, 1, 1], # [2, 2, 2]], # [[3, 3, 3], # [4,
|
|
-- 4, 4]], # [[5, 5, 5], # [6, 6, 6]]] # tensor <tt>t</tt> has shape [3,
|
|
-- 2, 3] # pass '[-1]' to flatten <tt>t</tt> reshape(t, [-1]) ==> [1,
|
|
-- 1, 1, 2, 2, 2, 3, 3, 3, 4, 4, 4, 5, 5, 5, 6, 6, 6]
|
|
--
|
|
-- # -1 can also be used to infer the shape
|
|
--
|
|
-- # -1 is inferred to be 9: reshape(t, [2, -1]) ==> [[1, 1, 1, 2, 2,
|
|
-- 2, 3, 3, 3], [4, 4, 4, 5, 5, 5, 6, 6, 6]] # -1 is inferred to be 2:
|
|
-- reshape(t, [-1, 9]) ==> [[1, 1, 1, 2, 2, 2, 3, 3, 3], [4, 4, 4, 5,
|
|
-- 5, 5, 6, 6, 6]] # -1 is inferred to be 3: reshape(t, [ 2, -1, 3])
|
|
-- ==> [[[1, 1, 1], [2, 2, 2], [3, 3, 3]], [[4, 4, 4], [5, 5, 5], [6,
|
|
-- 6, 6]]]
|
|
--
|
|
-- # tensor <tt>t</tt> is [7] # shape `[]` reshapes to a scalar
|
|
-- reshape(t, []) ==> 7 ```
|
|
reshape :: (TensorType t, TensorType tshape, OneOf ((:) * Int32 ((:) * Int64 ([] *))) tshape) => Tensor v1 t -> Tensor v2 tshape -> Tensor Value t
|
|
|
|
-- | Restore a tensor's value from a checkpoint file.
|
|
restore :: TensorType a => ByteString -> Tensor Ref a -> Build ControlNode
|
|
|
|
-- | Restore a tensor's value from a checkpoint file.
|
|
--
|
|
-- This version allows restoring from a checkpoint file that uses a
|
|
-- different tensor name than the variable.
|
|
restoreFromName :: TensorType a => ByteString -> ByteString -> Tensor Ref a -> Build ControlNode
|
|
save :: TensorType a => ByteString -> [Tensor v a] -> Build ControlNode
|
|
|
|
-- | Create a constant scalar.
|
|
scalar :: TensorType a => a -> Tensor Value a
|
|
shape :: (TensorType t) => Tensor v1 t -> Tensor Value Int32
|
|
|
|
-- | Returns an element-wise indication of the sign of a number.
|
|
--
|
|
-- `y = sign(x) = -1` if `x <a>0 if `x == 0`; 1 if `x</a> 0`.
|
|
--
|
|
-- For complex numbers, `y = sign(x) = x / |x|` if `x != 0`, otherwise `y
|
|
-- = 0`.
|
|
sign :: (TensorType t, OneOf ((:) * (Complex Double) ((:) * (Complex Float) ((:) * Int32 ((:) * Int64 ((:) * Word16 ((:) * Double ((:) * Float ([] *)))))))) t) => Tensor v1 t -> Tensor Value t
|
|
|
|
-- | Returns the size of a tensor.
|
|
--
|
|
-- This operation returns an integer representing the number of elements
|
|
-- in <tt>input</tt>.
|
|
--
|
|
-- For example:
|
|
--
|
|
-- ```prettyprint # <tt>t</tt> is [[[1, 1,, 1], [2, 2, 2]], [[3, 3, 3],
|
|
-- [4, 4, 4]]]] size(t) ==> 12 ```
|
|
size :: (TensorType t, TensorType out_type, OneOf ((:) * Int32 ((:) * Int64 ([] *))) out_type) => Tensor v1 t -> Tensor Value out_type
|
|
|
|
-- | Computes softmax activations.
|
|
--
|
|
-- For each batch <tt>i</tt> and class <tt>j</tt> we have
|
|
--
|
|
-- softmax[i, j] = exp(logits[i, j]) / sum_j(exp(logits[i, j]))
|
|
softmax :: (TensorType t, OneOf ((:) * Word16 ((:) * Double ((:) * Float ([] *)))) t) => Tensor v1 t -> Tensor Value t
|
|
|
|
-- | Computes softmax cross entropy cost and gradients to backpropagate.
|
|
--
|
|
-- Inputs are the logits, not probabilities.
|
|
softmaxCrossEntropyWithLogits :: (TensorType t, OneOf ((:) * Word16 ((:) * Double ((:) * Float ([] *)))) t) => Tensor v1 t -> Tensor v2 t -> (Tensor Value t, Tensor Value t)
|
|
|
|
-- | Converts a sparse representation into a dense tensor.
|
|
--
|
|
-- Builds an array <tt>dense</tt> with shape <tt>output_shape</tt> such
|
|
-- that
|
|
--
|
|
-- ```prettyprint # If sparse_indices is scalar dense[i] = (i ==
|
|
-- sparse_indices ? sparse_values : default_value)
|
|
--
|
|
-- # If sparse_indices is a vector, then for each i
|
|
-- dense[sparse_indices[i]] = sparse_values[i]
|
|
--
|
|
-- # If sparse_indices is an n by d matrix, then for each i in [0, n)
|
|
-- dense[sparse_indices[i][0], ..., sparse_indices[i][d-1]] =
|
|
-- sparse_values[i] ```
|
|
--
|
|
-- All other values in <tt>dense</tt> are set to <tt>default_value</tt>.
|
|
-- If <tt>sparse_values</tt> is a scalar, all sparse indices are set to
|
|
-- this single value.
|
|
--
|
|
-- Indices should be sorted in lexicographic order, and indices must not
|
|
-- contain any repeats. If <tt>validate_indices</tt> is true, these
|
|
-- properties are checked during execution.
|
|
sparseToDense :: (TensorType t, TensorType tindices, OneOf ((:) * Int32 ((:) * Int64 ([] *))) tindices) => Tensor v1 tindices -> Tensor v2 tindices -> Tensor v3 t -> Tensor v4 t -> Tensor Value t
|
|
|
|
-- | Returns x - y element-wise.
|
|
--
|
|
-- <ul>
|
|
-- <li>NOTE*: <tt>Sub</tt> supports broadcasting. More about broadcasting
|
|
-- <a>here</a></li>
|
|
-- </ul>
|
|
sub :: (TensorType t, OneOf ((:) * (Complex Double) ((:) * (Complex Float) ((:) * Int32 ((:) * Int64 ((:) * Word16 ((:) * Double ((:) * Float ([] *)))))))) t) => Tensor v1 t -> Tensor v2 t -> Tensor Value t
|
|
|
|
-- | Computes the sum of elements across dimensions of a tensor.
|
|
--
|
|
-- Reduces <tt>input</tt> along the dimensions given in
|
|
-- <tt>reduction_indices</tt>. Unless <tt>keep_dims</tt> is true, the
|
|
-- rank of the tensor is reduced by 1 for each entry in
|
|
-- <tt>reduction_indices</tt>. If <tt>keep_dims</tt> is true, the reduced
|
|
-- dimensions are retained with length 1.
|
|
sum :: (TensorType t, OneOf ((:) * (Complex Double) ((:) * (Complex Float) ((:) * Int16 ((:) * Int32 ((:) * Int64 ((:) * Int8 ((:) * Word16 ((:) * Word8 ((:) * Double ((:) * Float ([] *))))))))))) t, TensorType tidx, OneOf ((:) * Int32 ((:) * Int64 ([] *))) tidx) => Tensor v1 t -> Tensor v2 tidx -> Tensor Value t
|
|
|
|
-- | Finds values and indices of the <tt>k</tt> largest elements for the
|
|
-- last dimension.
|
|
--
|
|
-- If the input is a vector (rank-1), finds the <tt>k</tt> largest
|
|
-- entries in the vector and outputs their values and indices as vectors.
|
|
-- Thus `values[j]` is the <tt>j</tt>-th largest entry in <tt>input</tt>,
|
|
-- and its index is `indices[j]`.
|
|
--
|
|
-- For matrices (resp. higher rank input), computes the top <tt>k</tt>
|
|
-- entries in each row (resp. vector along the last dimension). Thus,
|
|
--
|
|
-- values.shape = indices.shape = input.shape[:-1] + [k]
|
|
--
|
|
-- If two elements are equal, the lower-index element appears first.
|
|
--
|
|
-- If <tt>k</tt> varies dynamically, use <tt>TopKV2</tt> below.
|
|
topK :: (TensorType t, OneOf ((:) * Int16 ((:) * Int32 ((:) * Int64 ((:) * Int8 ((:) * Word16 ((:) * Word8 ((:) * Double ((:) * Float ([] *))))))))) t) => Int64 -> Tensor v1 t -> (Tensor Value t, Tensor Value Int32)
|
|
|
|
-- | Shuffle dimensions of x according to a permutation.
|
|
--
|
|
-- The output <tt>y</tt> has the same rank as <tt>x</tt>. The shapes of
|
|
-- <tt>x</tt> and <tt>y</tt> satisfy: `y.shape[i] == x.shape[perm[i]] for
|
|
-- i in [0, 1, ..., rank(x) - 1]`
|
|
transpose :: (TensorType t, TensorType tperm, OneOf ((:) * Int32 ((:) * Int64 ([] *))) tperm) => Tensor v1 t -> Tensor v2 tperm -> Tensor Value t
|
|
truncatedNormal :: TensorType a => Tensor v Int64 -> Build (Tensor Value a)
|
|
|
|
-- | Create a new, uninitialized stateful Tensor of the given shape.
|
|
variable :: TensorType a => Shape -> Build (Tensor Ref a)
|
|
|
|
-- | Create a constant vector.
|
|
vector :: TensorType a => [a] -> Tensor Value a
|
|
zeros :: (Num a, TensorType a) => Shape -> Tensor Value a
|
|
|
|
-- | Returns a tensor of zeros with the same shape and type as x.
|
|
zerosLike :: TensorType t => Tensor v1 t -> Tensor Value t
|
|
instance (TensorFlow.Types.TensorType a, GHC.Num.Num a, v ~ TensorFlow.Tensor.Value, TensorFlow.Types.OneOf '[GHC.Types.Double, GHC.Types.Float, GHC.Int.Int32, GHC.Int.Int64, Data.Complex.Complex GHC.Types.Float, Data.Complex.Complex GHC.Types.Double] a) => GHC.Num.Num (TensorFlow.Tensor.Tensor v a)
|
|
|
|
|
|
-- | Parallel lookups on the list of tensors.
|
|
module TensorFlow.EmbeddingOps
|
|
|
|
-- | Looks up <tt>ids</tt> in a list of embedding tensors.
|
|
--
|
|
-- This function is used to perform parallel lookups on the list of
|
|
-- tensors in <tt>params</tt>. It is a generalization of <a>gather</a>,
|
|
-- where <tt>params</tt> is interpreted as a partition of a larger
|
|
-- embedding tensor.
|
|
--
|
|
-- The partition_strategy is "mod", we assign each id to partition `p =
|
|
-- id % len(params)`. For instance, 13 ids are split across 5 partitions
|
|
-- as: `[[0, 5, 10], [1, 6, 11], [2, 7, 12], [3, 8], [4, 9]]`
|
|
--
|
|
-- The results of the lookup are concatenated into a dense tensor. The
|
|
-- returned tensor has shape `shape(ids) + shape(params)[1:]`.
|
|
embeddingLookup :: (TensorType a, OneOf '[Int64, Int32] b, Num b) => [Tensor v a] -> Tensor Value b -> Build (Tensor Value a)
|
|
|
|
module TensorFlow.Gradient
|
|
|
|
-- | Gradient of <tt>y</tt> w.r.t. each element of <tt>xs</tt>.
|
|
gradients :: (Num (Tensor v1 a), v1 ~ Value, GradientCompatible a) => Tensor v1 a -> [Tensor v2 a] -> Build [Tensor Value a]
|