Module: tf.keras.ops

DO NOT EDIT.

This file was autogenerated. Do not edit it by hand, since your modifications would be overwritten.

Modules

image module: DO NOT EDIT.

linalg module: DO NOT EDIT.

nn module: DO NOT EDIT.

numpy module: DO NOT EDIT.

Functions

abs(...): Shorthand for keras.ops.absolute.

absolute(...): Compute the absolute value element-wise.

add(...): Add arguments element-wise.

all(...): Test whether all array elements along a given axis evaluate to True.

amax(...): Returns the maximum of an array or maximum value along an axis.

amin(...): Returns the minimum of an array or minimum value along an axis.

any(...): Test whether any array element along a given axis evaluates to True.

append(...): Append tensor x2 to the end of tensor x1.

arange(...): Return evenly spaced values within a given interval.

arccos(...): Trigonometric inverse cosine, element-wise.

arccosh(...): Inverse hyperbolic cosine, element-wise.

arcsin(...): Inverse sine, element-wise.

arcsinh(...): Inverse hyperbolic sine, element-wise.

arctan(...): Trigonometric inverse tangent, element-wise.

arctan2(...): Element-wise arc tangent of x1/x2 choosing the quadrant correctly.

arctanh(...): Inverse hyperbolic tangent, element-wise.

argmax(...): Returns the indices of the maximum values along an axis.

argmin(...): Returns the indices of the minium values along an axis.

argsort(...): Returns the indices that would sort a tensor.

array(...): Create a tensor.

average(...): Compute the weighted average along the specified axis.

average_pool(...): Average pooling operation.

batch_normalization(...): Normalizes x by mean and variance.

binary_crossentropy(...): Computes binary cross-entropy loss between target and output tensor.

bincount(...): Count the number of occurrences of each value in a tensor of integers.

broadcast_to(...): Broadcast a tensor to a new shape.

cast(...): Cast a tensor to the desired dtype.

categorical_crossentropy(...): Computes categorical cross-entropy loss between target and output tensor.

ceil(...): Return the ceiling of the input, element-wise.

cholesky(...): Computes the Cholesky decomposition of a positive semi-definite matrix.

clip(...): Clip (limit) the values in a tensor.

concatenate(...): Join a sequence of tensors along an existing axis.

cond(...): Conditionally applies true_fn or false_fn.

conj(...): Shorthand for keras.ops.conjugate.

conjugate(...): Returns the complex conjugate, element-wise.

conv(...): General N-D convolution.

conv_transpose(...): General N-D convolution transpose.

convert_to_numpy(...): Convert a tensor to a NumPy array.

convert_to_tensor(...): Convert a NumPy array to a tensor.

copy(...): Returns a copy of x.

correlate(...): Compute the cross-correlation of two 1-dimensional tensors.

cos(...): Cosine, element-wise.

cosh(...): Hyperbolic cosine, element-wise.

count_nonzero(...): Counts the number of non-zero values in x along the given axis.

cross(...): Returns the cross product of two (arrays of) vectors.

ctc_decode(...): Decodes the output of a CTC model.

ctc_loss(...): CTC (Connectionist Temporal Classification) loss.

cumprod(...): Return the cumulative product of elements along a given axis.

cumsum(...): Returns the cumulative sum of elements along a given axis.

custom_gradient(...): Decorator to define a function with a custom gradient.

depthwise_conv(...): General N-D depthwise convolution.

det(...): Computes the determinant of a square tensor.

diag(...): Extract a diagonal or construct a diagonal array.

diagonal(...): Return specified diagonals.

diff(...): Calculate the n-th discrete difference along the given axis.

digitize(...): Returns the indices of the bins to which each value in x belongs.

divide(...): Divide arguments element-wise.

divide_no_nan(...): Safe element-wise division which returns 0 where the denominator is 0.

dot(...): Dot product of two tensors.

eig(...): Computes the eigenvalues and eigenvectors of a square matrix.

eigh(...): Computes the eigenvalues and eigenvectors of a complex Hermitian.

einsum(...): Evaluates the Einstein summation convention on the operands.

elu(...): Exponential Linear Unit activation function.

empty(...): Return a tensor of given shape and type filled with uninitialized data.

equal(...): Returns (x1 == x2) element-wise.

erf(...): Computes the error function of x, element-wise.

erfinv(...): Computes the inverse error function of x, element-wise.

exp(...): Calculate the exponential of all elements in the input tensor.

expand_dims(...): Expand the shape of a tensor.

expm1(...): Calculate exp(x) - 1 for all elements in the tensor.

extract_sequences(...): Expands the dimension of last axis into sequences of sequence_length.

eye(...): Return a 2-D tensor with ones on the diagonal and zeros elsewhere.

fft(...): Computes the Fast Fourier Transform along last axis of input.

fft2(...): Computes the 2D Fast Fourier Transform along the last two axes of input.

flip(...): Reverse the order of elements in the tensor along the given axis.

floor(...): Return the floor of the input, element-wise.

floor_divide(...): Returns the largest integer smaller or equal to the division of inputs.

fori_loop(...): For loop implementation.

full(...): Return a new tensor of given shape and type, filled with fill_value.

full_like(...): Return a full tensor with the same shape and type as the given tensor.

gelu(...): Gaussian Error Linear Unit (GELU) activation function.

get_item(...): Return x[key].

greater(...): Return the truth value of x1 > x2 element-wise.

greater_equal(...): Return the truth value of x1 >= x2 element-wise.

hard_sigmoid(...): Hard sigmoid activation function.

hard_silu(...): Hard SiLU activation function, also known as Hard Swish.

hard_swish(...): Hard SiLU activation function, also known as Hard Swish.

hstack(...): Stack tensors in sequence horizontally (column wise).

identity(...): Return the identity tensor.

imag(...): Return the imaginary part of the complex argument.

in_top_k(...): Checks if the targets are in the top-k predictions.

inv(...): Computes the inverse of a square tensor.

irfft(...): Inverse real-valued Fast Fourier transform along the last axis.

is_tensor(...): Check whether the given object is a tensor.

isclose(...): Return whether two tensors are element-wise almost equal.

isfinite(...): Return whether a tensor is finite, element-wise.

isinf(...): Test element-wise for positive or negative infinity.

isnan(...): Test element-wise for NaN and return result as a boolean tensor.

istft(...): Inverse Short-Time Fourier Transform along the last axis of the input.

leaky_relu(...): Leaky version of a Rectified Linear Unit activation function.

less(...): Return the truth value of x1 < x2 element-wise.

less_equal(...): Return the truth value of x1 <= x2 element-wise.

linspace(...): Return evenly spaced numbers over a specified interval.

log(...): Natural logarithm, element-wise.

log10(...): Return the base 10 logarithm of the input tensor, element-wise.

log1p(...): Returns the natural logarithm of one plus the x, element-wise.

log2(...): Base-2 logarithm of x, element-wise.

log_sigmoid(...): Logarithm of the sigmoid activation function.

log_softmax(...): Log-softmax activation function.

logaddexp(...): Logarithm of the sum of exponentiations of the inputs.

logical_and(...): Computes the element-wise logical AND of the given input tensors.

logical_not(...): Computes the element-wise NOT of the given input tensor.

logical_or(...): Computes the element-wise logical OR of the given input tensors.

logical_xor(...): Compute the truth value of x1 XOR x2, element-wise.

logspace(...): Returns numbers spaced evenly on a log scale.

logsumexp(...): Computes the logarithm of sum of exponentials of elements in a tensor.

lu_factor(...): Computes the lower-upper decomposition of a square matrix.

matmul(...): Matrix product of two tensors.

max(...): Return the maximum of a tensor or maximum along an axis.

max_pool(...): Max pooling operation.

maximum(...): Element-wise maximum of x1 and x2.

mean(...): Compute the arithmetic mean along the specified axes.

median(...): Compute the median along the specified axis.

meshgrid(...): Creates grids of coordinates from coordinate vectors.

min(...): Return the minimum of a tensor or minimum along an axis.

minimum(...): Element-wise minimum of x1 and x2.

mod(...): Returns the element-wise remainder of division.

moments(...): Calculates the mean and variance of x.

moveaxis(...): Move axes of a tensor to new positions.

multi_hot(...): Encodes integer labels as multi-hot vectors.

multiply(...): Multiply arguments element-wise.

nan_to_num(...): Replace NaN with zero and infinity with large finite numbers.

ndim(...): Return the number of dimensions of a tensor.

negative(...): Numerical negative, element-wise.

nonzero(...): Return the indices of the elements that are non-zero.

norm(...): Matrix or vector norm.

normalize(...): Normalizes x over the specified axis.

not_equal(...): Return (x1 != x2) element-wise.

one_hot(...): Converts integer tensor x into a one-hot tensor.

ones(...): Return a new tensor of given shape and type, filled with ones.

ones_like(...): Return a tensor of ones with the same shape and type of x.

outer(...): Compute the outer product of two vectors.

pad(...): Pad a tensor.

power(...): First tensor elements raised to powers from second tensor, element-wise.

prod(...): Return the product of tensor elements over a given axis.

psnr(...): Peak Signal-to-Noise Ratio (PSNR) function.

qr(...): Computes the QR decomposition of a tensor.

quantile(...): Compute the q-th quantile(s) of the data along the specified axis.

ravel(...): Return a contiguous flattened tensor.

real(...): Return the real part of the complex argument.

reciprocal(...): Return the reciprocal of the argument, element-wise.

relu(...): Rectified linear unit activation function.

relu6(...): Rectified linear unit activation function with upper bound of 6.

repeat(...): Repeat each element of a tensor after themselves.

reshape(...): Gives a new shape to a tensor without changing its data.

rfft(...): Real-valued Fast Fourier Transform along the last axis of the input.

roll(...): Roll tensor elements along a given axis.

round(...): Evenly round to the given number of decimals.

rsqrt(...): Computes reciprocal of square root of x element-wise.

scatter(...): Returns a tensor of shape shape where indices are set to values.

scatter_update(...): Update inputs via updates at scattered (sparse) indices.

segment_max(...): Computes the max of segments in a tensor.

segment_sum(...): Computes the sum of segments in a tensor.

select(...): Return elements from choicelist, based on conditions in condlist.

selu(...): Scaled Exponential Linear Unit (SELU) activation function.

separable_conv(...): General N-D separable convolution.

shape(...): Gets the shape of the tensor input.

sigmoid(...): Sigmoid activation function.

sign(...): Returns a tensor with the signs of the elements of x.

silu(...): Sigmoid Linear Unit (SiLU) activation function, also known as Swish.

sin(...): Trigonometric sine, element-wise.

sinh(...): Hyperbolic sine, element-wise.

size(...): Return the number of elements in a tensor.

slice(...): Return a slice of an input tensor.

slice_update(...): Update an input by slicing in a tensor of updated values.

slogdet(...): Compute the sign and natural logarithm of the determinant of a matrix.

softmax(...): Softmax activation function.

softplus(...): Softplus activation function.

softsign(...): Softsign activation function.

solve(...): Solves a linear system of equations given by a x = b.

solve_triangular(...): Solves a linear system of equations given by a x = b.

sort(...): Sorts the elements of x along a given axis in ascending order.

sparse_categorical_crossentropy(...): Computes sparse categorical cross-entropy loss.

split(...): Split a tensor into chunks.

sqrt(...): Return the non-negative square root of a tensor, element-wise.

square(...): Return the element-wise square of the input.

squeeze(...): Remove axes of length one from x.

stack(...): Join a sequence of tensors along a new axis.

std(...): Compute the standard deviation along the specified axis.

stft(...): Short-Time Fourier Transform along the last axis of the input.

stop_gradient(...): Stops gradient computation.

subtract(...): Subtract arguments element-wise.

sum(...): Sum of a tensor over the given axes.

svd(...): Computes the singular value decomposition of a matrix.

swapaxes(...): Interchange two axes of a tensor.

swish(...): Sigmoid Linear Unit (SiLU) activation function, also known as Swish.

take(...): Take elements from a tensor along an axis.

take_along_axis(...): Select values from x at the 1-D indices along the given axis.

tan(...): Compute tangent, element-wise.

tanh(...): Hyperbolic tangent, element-wise.

tensordot(...): Compute the tensor dot product along specified axes.

tile(...): Repeat x the number of times given by repeats.

top_k(...): Finds the top-k values and their indices in a tensor.

trace(...): Return the sum along diagonals of the tensor.

transpose(...): Returns a tensor with axes transposed.

tri(...): Return a tensor with ones at and below a diagonal and zeros elsewhere.

tril(...): Return lower triangle of a tensor.

triu(...): Return upper triangle of a tensor.

true_divide(...): Alias for keras.ops.divide.

unstack(...): Unpacks the given dimension of a rank-R tensor into rank-(R-1) tensors.

var(...): Compute the variance along the specified axes.

vdot(...): Return the dot product of two vectors.

vectorize(...): Turn a function into a vectorized function.

vectorized_map(...): Parallel map of function on axis 0 of tensor(s) elements.

vstack(...): Stack tensors in sequence vertically (row wise).

where(...): Return elements chosen from x1 or x2 depending on condition.

while_loop(...): While loop implementation.

zeros(...): Return a new tensor of given shape and type, filled with zeros.

zeros_like(...): Return a tensor of zeros with the same shape and type as x.