Module autograd::ops

Modules

dummy_op

Functions

_hessian_vector_product	(Experimental) Computes hessian vector product
acos	Elementwise arccos
acosh	Elementwise hyperbolic arccos
add	Element-wise addition
add_inplace	Inplace addition
add_n	Adds all input tensors inplace.
argmax	Takes argmax along specified axis.
asin	Elementwise arcsin
asinh	Elementwise hyperbolic arcsin
atan	Elementwise arctan
atanh	Elementwise hyperbolic arctan
batch_matmul	Batched matrix multiplication.
bernoulli	Outputs values sampled from the bernoulli distribution.
clip	Limits all elements so as to be within [min, max]
concat	Concatenates (stacks) input tensors along specified axis.
cos	Elementwise cosine
cosh	Elementwise hyperbolic cosine
div	Element-wise division
elu	Elementwise exponential linear unit function.
equals	Compares two tensors and returns a binary tensor.
exp	Elementwise exponential
expand_dims	Expands dims.
flatten	Flattens input tensor into 1-ranked (vector)
gamma	Outputs values sampled from the gamma distribution.
gather	Gathers slices.
gradients	Returns gradient tensors wrt variables.
greater	Returns binary tensor.
greater_equal	Returns binary tensor.
identity	Identity function
jacobians	Computes jacobians for variables.
lesser	Returns binary tensor.
lesser_equal	Returns binary tensor.
log	Elementwise log
log_normal	Outputs values sampled from the log-normal distribution.
log_softmax	Log softmax function.
logsumexp	Computes log(sum(exp(x))) along specified axis.
matmul	Matrix multiplication.
matmul_t	Matrix multiplication.
mul	Element-wise multiplication
ones	Returns ones with given shape
pow	Elementwise pow
random_exp	Outputs values sampled from the exponential distribution.
random_normal	Outputs values sampled from the normal distribution.
random_uniform	Outputs values sampled from the uniform distribution.
range	Returns range
rank	Returns the (symbolic) rank of input tensor
reduce_max	Takes max along specified axis.
reduce_mean	Takes mean along specified axis.
reduce_min	Takes min along specified axis.
reduce_prod	Takes product along specified axis.
reduce_sum	Takes sum along specified axis.
relu	Elementwise rectified linear unit function.
reshape	Reshapes input tensor.
reverse_axes	Reverses axes of the input tensor.
rnn_step	Applies recurrent net unit to the input.
scalar	Creates a constant tensor.
setdiff1d	Takes diff between two tensor
shape	Returns symbolic shape of input tensor
sigmoid	Elementwise logistic sigmoid function.
sigmoid_cross_entropy	Computes binary_cross_entropy(sigmoid(y), t).
sin	Elementwise sine
sinh	Elementwise hyperbolic sine
size	Returns the (symbolic) length of input tensor
slice	Slices input tensor with indices.
softmax	Takes softmax along specified axis
softmax_cross_entropy	Computes categorical_cross_entropy(softmax(y), t).
sparse_softmax_cross_entropy	A variant of softmax_cross_entropy.
split	Splits input tensors into parts.
sqrt	Elementwise sqrt
squeeze	Squeezes dims.
standard_normal	Outputs values sampled from the standard normal distribution.
standard_uniform	Outputs values sampled from the standard uniform distribution.
stop_gradients	Stops gradients
sub	Element-wise subtraction
sub_inplace	Inplace subtraction
tan	Elementwise tangent
tanh	Elementwise hyperbolic tangent
tensordot	Computes tensor dot product (tensor contraction) along specified axes.
tile	Tiles input tensor along specified axis.
transpose	Permutes dimensions.
zeros	Returns zeros with given shape