Making predictions with predictors.
Floating Point Values
Function value type | C/C++ type | Description |
---|---|---|
float16 | float16_t | IEEE 754 16-bit floating point number. |
float32 | float | IEEE 754 32-bit floating point number. |
float64 | double | IEEE 754 64-bit floating point number. |
float32
. Use a tensor constructor to explicitly specify the data type.float16
is planned for the future depending on language support.Tensor
instances—never plain vectors.Integer Values
Function value type | C/C++ type | Description |
---|---|---|
int8 | int8_t | Signed 8-bit integer. |
int16 | int16_t | Signed 16-bit integer. |
int32 | int32_t | Signed 32-bit integer. |
int64 | int64_t | Signed 64-bit integer. |
uint8 | uint8_t | Unsigned 8-bit integer. |
uint16 | uint16_t | Unsigned 16-bit integer. |
uint32 | uint32_t | Unsigned 32-bit integer. |
uint64 | uint64_t | Unsigned 64-bit integer. |
int32
. Use
a tensor constructor to explicitly specify the data type.Tensor
instances—never plain vectors.Boolean Values
Tensor
instances—never plain vectors.String Values
List Values
Dictionary Values
Image Values
Pixel format | Channels | Description |
---|---|---|
A8 | 1 | Single channel luminance or alpha image. |
RGB888 | 3 | Color image without alpha channel. |
RGBA8888 | 4 | Color image with alpha channel. |
Image
utility types for working with images:Binary Values
mmap
or your environment’s equivalent.