Turning SymPy expressions into PyTorch modules.

Patrick Kidger

Last update: Dec 13, 2022

Related tags

Deep Learning sympytorch

Overview

sympytorch

A micro-library as a convenience for turning SymPy expressions into PyTorch Modules.

All SymPy floats become trainable parameters. All SymPy symbols are inputs to the Module.

Installation

pip install git+https://github.com/patrick-kidger/sympytorch.git

Example

import sympy, torch, sympytorch

x = sympy.symbols('x_name')
cosx = 1.0 * sympy.cos(x)
sinx = 2.0 * sympy.sin(x)
mod = sympytorch.SymPyModule(expressions=[cosx, sinx])

x_ = torch.rand(3)
out = mod(x_name=x_)  # out has shape (3, 2)

assert torch.equal(out[:, 0], x_.cos())
assert torch.equal(out[:, 1], 2 * x_.sin())
assert out.requires_grad  # from the two Parameters initialised as 1.0 and 2.0
assert {x.item() for x in mod.parameters()} == {1.0, 2.0}

API

The API consists of a single object, SymPyModule.

It is initialised as SymPyModule(*, expressions), where expressions is a list of SymPy expressions.
It can be called, passing the values of the symbols as in the above example.
It has a method .sympy(), which returns the corresponding list of SymPy expressions. (Which may not be the same as the expressions it was initialised with, if the values of its Parameters have been changed, i.e. have been learnt.)

Extensions

Not every PyTorch or SymPy operation is supported -- just the ones that I found I've needed! There's a dictionary here that lists the supported operations. Feel free to submit PRs for any extra operations you need.

Comments

add sympy rational

I got a key error of "sympy.core.Rational". so I suggest to add this code temporarily. but Rational Class implement is necessary by PyTorch.

opened by yeoun9 1
Fix hide_floats to work with `sympy.Min` and `sympy.Max`

Because sympy.Min and sympy.Max check whether their arguments are of a comparably type, they fail with the sympy.UnevaluatedExpr wrappers added by hide_floats unless explicitly told not to evaluate. This fixes that problem by preventing their evaluation when hiding floats, and by explicitly evaluating the hidden arguments when actually evaluating the expressions.

opened by fpollock 1

A library of extension and helper modules for Python's data analysis and machine learning libraries.

Mlxtend (machine learning extensions) is a Python library of useful tools for the day-to-day data science tasks. Sebastian Raschka 2014-2020 Links Doc

4.2k Jan 2, 2023

Implementation of self-attention mechanisms for general purpose. Focused on computer vision modules. Ongoing repository.

Self-attention building blocks for computer vision applications in PyTorch Implementation of self attention mechanisms for computer vision in PyTorch

962 Dec 23, 2022

Implementation of Bidirectional Recurrent Independent Mechanisms (Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules)

BRIMs Bidirectional Recurrent Independent Mechanisms Implementation of the paper Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neura

26 May 26, 2022

This is a Machine Learning Based Hand Detector Project, It Uses Machine Learning Models and Modules Like Mediapipe, Developed By Google!

Machine Learning Hand Detector This is a Machine Learning Based Hand Detector Project, It Uses Machine Learning Models and Modules Like Mediapipe, Dev

3 Feb 25, 2022

Stacs-ci - A set of modules to enable integration of STACS with commonly used CI / CD systems

Static Token And Credential Scanner CI Integrations What is it? STACS is a YARA

18 Aug 4, 2022

Turning SymPy expressions into PyTorch modules.

Related tags

Overview

sympytorch

Installation

Example

API

Extensions

You might also like...

A library of extension and helper modules for Python's data analysis and machine learning libraries.

Implementation of self-attention mechanisms for general purpose. Focused on computer vision modules. Ongoing repository.

Implementation of Bidirectional Recurrent Independent Mechanisms (Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules)

DI-HPC is an acceleration operator component for general algorithm modules in reinforcement learning algorithms

Implementation for our ICCV 2021 paper: Dual-Camera Super-Resolution with Aligned Attention Modules

Implementation for our ICCV 2021 paper: Dual-Camera Super-Resolution with Aligned Attention Modules

Nest - A flexible tool for building and sharing deep learning modules

This is a Machine Learning Based Hand Detector Project, It Uses Machine Learning Models and Modules Like Mediapipe, Developed By Google!

Stacs-ci - A set of modules to enable integration of STACS with commonly used CI / CD systems

Comments

add sympy rational

Fix hide_floats to work with `sympy.Min` and `sympy.Max`

Owner

Patrick Kidger

This solves the autonomous driving issue which is supported by deep learning technology. Given a video, it splits into images and predicts the angle of turning for each frame.

SymPy-powered, Wolfram|Alpha-like answer engine totally in your browser, without backend computation

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.

MacroTools provides a library of tools for working with Julia code and expressions.

Weight initialization schemes for PyTorch nn.Modules

Pytorch modules for paralel models with same architecture. Ideal for multi agent-based systems

Torch-mutable-modules - Use in-place and assignment operations on PyTorch module parameters with support for autograd

Convert scikit-learn models to PyTorch modules