Binary Operations

As you may have seen in the tutorial, MaskedTensor also has binary operations implemented with the caveat that the masks in two masked tensors must match or else an error will be raised. As noted in the error, if you need support for a particular operator or have proposed semantics for how they should be behave instead, please open an issue on Github. For now, we have decided to go with the most conservative implementation to ensure that users know exactly what is going on and are being intentional about their decisions with masked semantics.

The available binary operators are:

add	Adds other, scaled by alpha, to input.
atan2	Element-wise arctangent of \(\text{input}_{i} / \text{other}_{i}\) with consideration of the quadrant.
arctan2	Alias for torch.atan2().
bitwise_and	Computes the bitwise AND of input and other.
bitwise_or	Computes the bitwise OR of input and other.
bitwise_xor	Computes the bitwise XOR of input and other.
bitwise_left_shift	Computes the left arithmetic shift of input by other bits.
bitwise_right_shift	Computes the right arithmetic shift of input by other bits.
div	Divides each element of the input input by the corresponding element of other.
divide	Alias for torch.div().
floor_divide
fmod	Applies C++'s std::fmod entrywise.
logaddexp	Logarithm of the sum of exponentiations of the inputs.
logaddexp2	Logarithm of the sum of exponentiations of the inputs in base-2.
mul	Multiplies input by other.
multiply	Alias for torch.mul().
nextafter	Return the next floating-point value after input towards other, elementwise.
remainder	Computes Python's modulus operation entrywise.
sub	Subtracts other, scaled by alpha, from input.
subtract	Alias for torch.sub().
true_divide	Alias for torch.div() with rounding_mode=None.
eq	Computes element-wise equality
ne	Computes \(\text{input} \neq \text{other}\) element-wise.
le	Computes \(\text{input} \leq \text{other}\) element-wise.
ge	Computes \(\text{input} \geq \text{other}\) element-wise.
greater	Alias for torch.gt().
greater_equal	Alias for torch.ge().
gt	Computes \(\text{input} > \text{other}\) element-wise.
less_equal	Alias for torch.le().
lt	Computes \(\text{input} < \text{other}\) element-wise.
less	Alias for torch.lt().
maximum	Computes the element-wise maximum of input and other.
minimum	Computes the element-wise minimum of input and other.
fmax	Computes the element-wise maximum of input and other.
fmin	Computes the element-wise minimum of input and other.
not_equal	Alias for torch.ne().

The available inplace binary operators are all of the above except:

logaddexp	Logarithm of the sum of exponentiations of the inputs.
logaddexp2	Logarithm of the sum of exponentiations of the inputs in base-2.
equal	True if two tensors have the same size and elements, False otherwise.
fmin	Computes the element-wise minimum of input and other.
minimum	Computes the element-wise minimum of input and other.
fmax	Computes the element-wise maximum of input and other.

As always, if you have any feature requests, please file an issue on Github.