torch — PyTorch 2.5 documentation (original) (raw)
Computes the absolute value of each element in input.
Alias for torch.abs()
Computes the inverse cosine of each element in input.
Alias for torch.acos().
Returns a new tensor with the inverse hyperbolic cosine of the elements of input.
Alias for torch.acosh().
Adds other, scaled by alpha, to input.
Performs the element-wise division of tensor1 by tensor2, multiplies the result by the scalar value and adds it to input.
Performs the element-wise multiplication of tensor1 by tensor2, multiplies the result by the scalar value and adds it to input.
Computes the element-wise angle (in radians) of the given input tensor.
Returns a new tensor with the arcsine of the elements of input.
Alias for torch.asin().
Returns a new tensor with the inverse hyperbolic sine of the elements of input.
Alias for torch.asinh().
Returns a new tensor with the arctangent of the elements of input.
Alias for torch.atan().
Returns a new tensor with the inverse hyperbolic tangent of the elements of input.
Alias for torch.atanh().
Element-wise arctangent of inputi/otheri\text{input}_{i} / \text{other}_{i} with consideration of the quadrant.
Alias for torch.atan2().
Computes the bitwise NOT of the given input tensor.
Computes the bitwise AND of input and other.
Computes the bitwise OR of input and other.
Computes the bitwise XOR of input and other.
Computes the left arithmetic shift of input by other bits.
Computes the right arithmetic shift of input by other bits.
Returns a new tensor with the ceil of the elements of input, the smallest integer greater than or equal to each element.
Clamps all elements in input into the range [ min, max ].
Alias for torch.clamp().
Computes the element-wise conjugate of the given input tensor.
Create a new floating-point tensor with the magnitude of input and the sign of other, elementwise.
Returns a new tensor with the cosine of the elements of input.
Returns a new tensor with the hyperbolic cosine of the elements of input.
Returns a new tensor with each of the elements of input converted from angles in degrees to radians.
Divides each element of the input input by the corresponding element of other.
Alias for torch.div().
Alias for torch.special.digamma().
Alias for torch.special.erf().
Alias for torch.special.erfc().
Alias for torch.special.erfinv().
Returns a new tensor with the exponential of the elements of the input tensor input.
Alias for torch.special.exp2().
Alias for torch.special.expm1().
fake_quantize_per_channel_affine
Returns a new tensor with the data in input fake quantized per channel using scale, zero_point, quant_min and quant_max, across the channel specified by axis.
fake_quantize_per_tensor_affine
Returns a new tensor with the data in input fake quantized using scale, zero_point, quant_min and quant_max.
Alias for torch.trunc()
Raises input to the power of exponent, elementwise, in double precision.
Returns a new tensor with the floor of the elements of input, the largest integer less than or equal to each element.
Applies C++'s std::fmod entrywise.
Computes the fractional portion of each element in input.
Decomposes input into mantissa and exponent tensors such that input=mantissa×2exponent\text{input} = \text{mantissa} \times 2^{\text{exponent}}.
Estimates the gradient of a function g:Rn→Rg : \mathbb{R}^n \rightarrow \mathbb{R} in one or more dimensions using the second-order accurate central differences method and either first or second order estimates at the boundaries.
Returns a new tensor containing imaginary values of the self tensor.
Multiplies input by 2 ** other.
Does a linear interpolation of two tensors start (given by input) and end based on a scalar or tensor weight and returns the resulting out tensor.
Computes the natural logarithm of the absolute value of the gamma function on input.
Returns a new tensor with the natural logarithm of the elements of input.
Returns a new tensor with the logarithm to the base 10 of the elements of input.
Returns a new tensor with the natural logarithm of (1 + input).
Returns a new tensor with the logarithm to the base 2 of the elements of input.
Logarithm of the sum of exponentiations of the inputs.
Logarithm of the sum of exponentiations of the inputs in base-2.
Computes the element-wise logical AND of the given input tensors.
Computes the element-wise logical NOT of the given input tensor.
Computes the element-wise logical OR of the given input tensors.
Computes the element-wise logical XOR of the given input tensors.
Alias for torch.special.logit().
Given the legs of a right triangle, return its hypotenuse.
Alias for torch.special.i0().
Alias for torch.special.gammainc().
Alias for torch.special.gammaincc().
Multiplies input by other.
Alias for torch.mul().
Alias for torch.special.multigammaln().
Replaces NaN, positive infinity, and negative infinity values in input with the values specified by nan, posinf, and neginf, respectively.
Returns a new tensor with the negative of the elements of input.
Alias for torch.neg()
Return the next floating-point value after input towards other, elementwise.
Alias for torch.special.polygamma().
Returns input.
Takes the power of each element in input with exponent and returns a tensor with the result.
Applies batch normalization on a 4D (NCHW) quantized tensor.
Applies a 1D max pooling over an input quantized tensor composed of several input planes.
Applies a 2D max pooling over an input quantized tensor composed of several input planes.
Returns a new tensor with each of the elements of input converted from angles in radians to degrees.
Returns a new tensor containing real values of the self tensor.
Returns a new tensor with the reciprocal of the elements of input
Computes Python's modulus operation entrywise.
Rounds elements of input to the nearest integer.
Returns a new tensor with the reciprocal of the square-root of each of the elements of input.
Alias for torch.special.expit().
Returns a new tensor with the signs of the elements of input.
This function is an extension of torch.sign() to complex tensors.
Tests if each element of input has its sign bit set or not.
Returns a new tensor with the sine of the elements of input.
Alias for torch.special.sinc().
Returns a new tensor with the hyperbolic sine of the elements of input.
Alias for torch.nn.functional.softmax().
Returns a new tensor with the square-root of the elements of input.
Returns a new tensor with the square of the elements of input.
Subtracts other, scaled by alpha, from input.
Alias for torch.sub().
Returns a new tensor with the tangent of the elements of input.
Returns a new tensor with the hyperbolic tangent of the elements of input.
Alias for torch.div() with rounding_mode=None.
Returns a new tensor with the truncated integer values of the elements of input.
Alias for torch.special.xlogy().