-- 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 variable and -- assign return a Build action (e.g., Build (Tensor -- Ref a) instead of a pure value; the returned Tensors are -- always rendered in the current Build context. This approach -- helps us avoid problems with inlining or common subexpression -- elimination, by writing -- -- 
--   do
--       v <- variable []
--       w <- assign v 3
--       render $ w * w
--
-- -- instead of -- -- 
--   let
--      v = variable []
--      w = assign v 3
--   in w * w
--
-- -- since the latter could be reasonably transformed by the compiler into -- (or vice versa) -- -- 
--   let
--      v = variable []
--      w = assign v 3
--      w' = assign v 3
--   in w * w'
--
-- -- Ops should return a Build action if their original -- OpDef 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. -- -- 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 x, this operation returns a tensor containing -- the absolute value of each element in x. 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 -- | Returns the truth value of (x == y) element-wise. -- -- equal :: (TensorType t, OneOf ((:) * (Complex Double) ((:) * (Complex Float) ((:) * Bool ((:) * ByteString ((:) * Int16 ((:) * Int32 ((:) * Int64 ((:) * Int8 ((:) * Word16 ((:) * Word8 ((:) * Double ((:) * Float ([] *))))))))))))) t) => Tensor v1 t -> Tensor v2 t -> Tensor Value Bool 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 dims and fills it -- with value. -- -- 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 -- | Returns a one-hot tensor. -- -- The locations represented by indices in indices take value -- on_value, while all other locations take value -- off_value. -- -- If the input indices is rank N, the output will have -- rank `N+1`, The new axis is created at dimension axis -- (default: the new axis is appended at the end). -- -- If indices is a scalar the output shape will be a vector of -- length depth. -- -- If indices is a vector of length features, the -- output shape will be: ``` features x depth if axis == -1 depth x -- features if axis == 0 ``` -- -- If indices is a matrix (batch) with shape `[batch, -- features]`, the output shape will be: ``` batch x features x depth if -- axis == -1 batch x depth x features if axis == 1 depth x batch x -- features if axis == 0 ``` -- -- Examples ========= -- -- Suppose that -- -- ``` indices = [0, 2, -1, 1] depth = 3 on_value = 5.0 off_value = 0.0 -- axis = -1 ``` -- -- Then output is `[4 x 3]`: -- -- ```output = [5.0 0.0 0.0] // one_hot(0) [0.0 0.0 5.0] // one_hot(2) -- [0.0 0.0 0.0] // one_hot(-1) [0.0 5.0 0.0] // one_hot(1) ``` -- -- Suppose that -- -- ``` indices = [0, 2, -1, 1] depth = 3 on_value = 0.0 off_value = 3.0 -- axis = 0 ``` -- -- Then output is `[3 x 4]`: -- -- ```output = [0.0 3.0 3.0 3.0] [3.0 3.0 3.0 0.0] [3.0 3.0 3.0 3.0] [3.0 -- 0.0 3.0 3.0] // ^ one_hot(0) // ^ one_hot(2) // ^ one_hot(-1) // ^ -- one_hot(1) ``` Suppose that -- -- ``` indices = [[0, 2], [1, -1]] depth = 3 on_value = 1.0 off_value = -- 0.0 axis = -1 ``` -- -- Then output is `[2 x 2 x 3]`: -- -- ```output = [ [1.0, 0.0, 0.0] // one_hot(0) [0.0, 0.0, 1.0] // -- one_hot(2) ][ [0.0, 1.0, 0.0] // one_hot(1) [0.0, 0.0, 0.0] // -- one_hot(-1) ]``` oneHot :: (TensorType t, TensorType tI, OneOf ((:) * Int32 ((:) * Int64 ((:) * Word8 ([] *)))) tI) => Tensor v1 tI -> Tensor v2 Int32 -> Tensor v3 t -> Tensor v4 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). -- -- 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 -- | Computes the mean of elements across dimensions of a tensor. -- -- Reduces input along the dimensions given in -- reduction_indices. Unless keep_dims is true, the -- rank of the tensor is reduced by 1 for each entry in -- reduction_indices. If keep_dims is true, the reduced -- dimensions are retained with length 1. mean :: (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 -- | Returns x * y element-wise. -- -- 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 N rank-R tensors into one -- rank-`(R+1)` tensor. -- -- Packs the N tensors in values into a tensor with -- rank one higher than each tensor in values, by packing them -- along the axis dimension. Given a list of tensors of shape -- `(A, B, C)`; -- -- if `axis == 0` then the output tensor will have the shape -- `(N, A, B, C)`. if `axis == 1` then the output tensor will -- have the shape `(A, N, B, C)`. Etc. -- -- For example: -- -- ```prettyprint # x is [1, 4] # y is [2, 5] # -- z 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 unpack. 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 -- start and extends by increments of delta up to but -- not including limit. -- -- For example: -- -- ``` # start is 3 # limit is 18 # delta 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 tensor, this operation returns a tensor that has the -- same values as tensor with shape shape. -- -- If one component of shape is the special value -1, the size of -- that dimension is computed so that the total size remains constant. In -- particular, a shape of `[-1]` flattens into 1-D. At most one -- component of shape can be -1. -- -- If shape is 1-D or higher, then the operation returns a tensor -- with shape shape filled with the values of tensor. In -- this case, the number of elements implied by shape must be the -- same as the number of elements in tensor. -- -- For example: -- -- ```prettyprint # tensor t is [1, 2, 3, 4, 5, 6, 7, 8, 9] # -- tensor t has shape [9] reshape(t, [3, 3]) ==> [[1, 2, 3], -- [4, 5, 6], [7, 8, 9]] -- -- # tensor t is [[[1, 1], [2, 2]], # [[3, 3], [4, 4]]] # tensor -- t has shape [2, 2, 2] reshape(t, [2, 4]) ==> [[1, 1, 2, -- 2], [3, 3, 4, 4]] -- -- # tensor t is [[[1, 1, 1], # [2, 2, 2]], # [[3, 3, 3], # [4, -- 4, 4]], # [[5, 5, 5], # [6, 6, 6]]] # tensor t has shape [3, -- 2, 3] # pass '[-1]' to flatten t 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 t 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 0 if `x == 0`; 1 if `x 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 input. -- -- For example: -- -- ```prettyprint # t 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 i and class j 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 dense with shape output_shape 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 dense are set to default_value. -- If sparse_values 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 validate_indices 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. -- -- 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 input along the dimensions given in -- reduction_indices. Unless keep_dims is true, the -- rank of the tensor is reduced by 1 for each entry in -- reduction_indices. If keep_dims 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 k largest elements for the -- last dimension. -- -- If the input is a vector (rank-1), finds the k largest -- entries in the vector and outputs their values and indices as vectors. -- Thus `values[j]` is the j-th largest entry in input, -- and its index is `indices[j]`. -- -- For matrices (resp. higher rank input), computes the top k -- 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 k varies dynamically, use TopKV2 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 y has the same rank as x. The shapes of -- x and y 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 ids in a list of embedding tensors. -- -- This function is used to perform parallel lookups on the list of -- tensors in params. It is a generalization of gather, -- where params 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 y w.r.t. each element of xs. gradients :: (Num (Tensor v1 a), v1 ~ Value, GradientCompatible a) => Tensor v1 a -> [Tensor v2 a] -> Build [Tensor Value a]