Float16
Related Docs:
object Float16
| package onnx
Whether this Float16 value is finite or not.
Whether this Float16 value is finite or not.
For the purposes of this method, infinities and NaNs are considered non-finite. For those values it returns false and for all other values it returns true.
Returns if this is a zero value (positive or negative).
Return the sign of a Float16 value as a Float.
Return the sign of a Float16 value as a Float.
There are five possible return values:
* NaN: the value is Float16.NaN (and has no sign) * -1F: the value is a non-zero negative number * -0F: the value is Float16.NegativeZero * 0F: the value is Float16.Zero * 1F: the value is a non-zero positive number
PositiveInfinity and NegativeInfinity return their expected signs.
Convert this Float16 value to the nearest Float.
Convert this Float16 value to the nearest Float.
Non-finite values and zero values will be mapped to the corresponding Float value.
All other finite values will be handled depending on whether they are normal or subnormal. The relevant formulas are:
* normal: (sign*2-1) * 2(exponent-15) * (1 + mantissa/1024) * subnormal: (sign*2-1) * 2-14 * (mantissa/1024)
Given any (x: Float16), Float16.fromFloat(x.toFloat) = x
The reverse is not necessarily true, since there are many Float values which are not precisely representable as Float16 values.
String representation of this Float16 value.
String representation of this Float16 value.
Reverse the sign of this Float16 value.
Reverse the sign of this Float16 value.
This just involves toggling the sign bit with XOR.
-Float16.NaN has no meaningful effect. -Float16.Zero returns Float16.NegativeZero.
Float16 represents 16-bit floating-point values.
This type does not actually support arithmetic directly. The expected use case is to convert to Float to perform any actual arithmetic, then convert back to a Float16 if needed.
Binary representation:
sign (1 bit) | | exponent (5 bits) | | | | mantissa (10 bits) | | | x xxxxx xxxxxxxxxx
Value interpretation (in order of precedence, with _ wild):
0 00000 0000000000 (positive) zero 1 00000 0000000000 negative zero _ 00000 subnormal number _ 11111 0000000000 +/- infinity _ 11111 not-a-number _ _ normal number
For non-zero exponents, the mantissa has an implied leading 1 bit, so 10 bits of data provide 11 bits of precision for normal numbers.