Neural Processes

A framework for composing Neural Processes in Python.

Installation

pip install neuralprocesses tensorflow tensorflow-probability  # For use with TensorFlow
pip install neuralprocesses torch                              # For use with PyTorch

If something is not working or unclear, please feel free to open an issue.

Documentation

See here.

TL;DR! Just Get me Started!

Here you go:

import torch

import neuralprocesses.torch as nps

# Construct a ConvCNP.
convcnp = nps.construct_convgnp(dim_x=1, dim_y=2, likelihood="het")

# Construct optimiser.
opt = torch.optim.Adam(convcnp.parameters(), 1e-3)

# Training: optimise the model for 32 batches.
for _ in range(32):
    # Sample a batch of new context and target sets. Replace this with your data. The
    # shapes are `(batch_size, dimensionality, num_data)`.
    xc = torch.randn(16, 1, 10)  # Context inputs
    yc = torch.randn(16, 2, 10)  # Context outputs
    xt = torch.randn(16, 1, 15)  # Target inputs
    yt = torch.randn(16, 2, 15)  # Target output

    # Compute the loss and update the model parameters.
    loss = -torch.mean(nps.loglik(convcnp, xc, yc, xt, yt, normalise=True))
    opt.zero_grad(set_to_none=True)
    loss.backward()
    opt.step()

# Testing: make some predictions.
mean, var, noiseless_samples, noisy_samples = nps.predict(
    convcnp,
    torch.randn(16, 1, 10),  # Context inputs
    torch.randn(16, 2, 10),  # Context outputs
    torch.randn(16, 1, 15),  # Target inputs
)

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

neuralprocesses-0.2.7.tar.gz (72.3 kB view details)

Uploaded Dec 17, 2024 Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

neuralprocesses-0.2.7-py3-none-any.whl (110.6 kB view details)

Uploaded Dec 17, 2024 Python 3

File details

Details for the file neuralprocesses-0.2.7.tar.gz.

File metadata

Download URL: neuralprocesses-0.2.7.tar.gz
Upload date: Dec 17, 2024
Size: 72.3 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/6.0.1 CPython/3.12.8

File hashes

Hashes for neuralprocesses-0.2.7.tar.gz
Algorithm	Hash digest
SHA256	`1eaa1f41cb6e6c42935714be71d2f453f72682c3fb9cc7b1aecf58d67dd8b0eb`
MD5	`9d619b6baab5e5e53915125f4b60bdf3`
BLAKE2b-256	`4c72310b21cb06e37944df32803606678dd7376db00d0b8189e2f5bc6150d510`

See more details on using hashes here.

File details

Details for the file neuralprocesses-0.2.7-py3-none-any.whl.

File metadata

Download URL: neuralprocesses-0.2.7-py3-none-any.whl
Upload date: Dec 17, 2024
Size: 110.6 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/6.0.1 CPython/3.12.8

File hashes

Hashes for neuralprocesses-0.2.7-py3-none-any.whl
Algorithm	Hash digest
SHA256	`1434ec42600e50812b4c935e416c27723e27b40b7f4ca3e7b5102f3f07cef946`
MD5	`8de140a3ffd22b517f6a1e14379db471`
BLAKE2b-256	`ce09d86315d1cd7db6647541a7d2d2cd54d0c37110b3d2e8483dc88336dede9d`