Making Predictions

The very first step in making predictions is finding a prediction function to use:

Explore Predictors on Function

Explore public predictors on Function. These predictors can be used by any user on the Function platform.

Join our waitlist to bring your custom Python functions and run them on-device.

Making predictions with Function can be done in as little as two lines of code.

Using Prediction Values

Function supports a fixed set of value types for prediction input and output values:

Function supports float32 and float64 floating point scalars:

In languages that don’t support fixed-size floating point scalars, the data type for floating point values defaults to float32. Use a tensor constructor to explicitly specify the data type.

Support for half-precision floating point scalars float16 is planned for the future depending on language support.

Function supports floating point vectors (i.e. one-dimensional floating point tensors):

Although Function supports input vectors, predictors will always output either scalars or Tensor instances—never plain vectors.

Function supports floating point tensors:

Function supports several signed or unsigned integer scalars: int8, int16, int32, int64, uint8, uint16, uint32, and uint64.

When integer scalars are passed to predictors, the data type defaults to int32. Use a tensor constructor to explicitly specify the data type.

Function supports integer vectors (i.e. one-dimensional integer tensors):

Although Function supports input vectors, predictors will always output either scalars or Tensor instances—never plain vectors.

Function supports integer tensors:

Unsigned integer tensors are not supported in our Android client because of missing language support in Java.

Function supports boolean scalars:

Function supports boolean vectors (i.e. one-dimensional boolean tensors):

Although Function supports input vectors, predictors will always output either scalars or Tensor instances—never plain vectors.

Function supports boolean tensors:

Function supports string values:

Function supports lists of values, each with potentially different types:

Input list values must be JSON-serializable.

Function supports dictionary values:

Input dictionary values must be JSON-serializable.

Function supports images, represented as raw pixel buffers with 8 bytes per pixel and interleaved by channel. Function supports three pixel buffer formats:

R8: Single channel luminance image.
RGB888: Color image without alpha channel.
RGBA8888: Color image with alpha channel.

Some client SDKs provide Image utility types for working with images:

Function supports binary blobs:

Because Function’s security model prohibits file system access, binary input values are always fully read into memory before being passed to the predictor.

To make predictions on large files, consider mapping the file into memory using mmap or environment’s equivalent.

Get Started

Workflows

Insiders

Making Predictions

Explore Predictors on Function