pytorch-symbolic 1.2.1

Symbolic API for model creation in PyTorch.

Pytorch Symbolic

Pytorch Symbolic is MIT licensed library that adds symbolic API for model creation to PyTorch.

Pytorch Symbolic makes it easier and faster to define complex models. It spares you writing boilerplate code. It aims to be PyTorch equivalent for Keras Functional API.

Features:

• Small extension of PyTorch
• No dependencies besides PyTorch
• Produces models entirely compatible with PyTorch
• Works with torch.compile and torch.export
• Overhead free as tested in benchmarks
• Reduces the amount of boilerplate code
• Works well with complex architectures
• Code and documentation is automatically tested

Example

To create a symbolic model, you need Symbolic Tensors and torch.nn.Module. Register layers and operations in your model by calling layer(inputs) or equivalently inputs(layer). Layers will be automagically added to your model and all operations will be replayed on the real data. That's all!

Using Pytorch Symbolic, we can define a working classifier in a few lines of code:

from torch import nn
from pytorch_symbolic import Input, SymbolicModel

inputs = Input(shape=(1, 28, 28))
x = nn.Flatten()(inputs)
x = nn.Linear(x.shape[1], 10)(x)(nn.Softmax(1))
model = SymbolicModel(inputs=inputs, outputs=x)
model.summary()

_______________________________________________________
     Layer       Output shape        Params   Parent   
=======================================================
1    Input_1     (None, 1, 28, 28)   0                 
2    Flatten_1   (None, 784)         0        1        
3    Linear_1    (None, 10)          7850     2        
4*   Softmax_1   (None, 10)          0        3        
=======================================================
Total params: 7850
Trainable params: 7850
Non-trainable params: 0
_______________________________________________________

See more examples in Documentation Quick Start.

Symbolic models are plain torch.nn.Module objects, so they work with modern PyTorch tooling:

model = SymbolicModel(inputs=inputs, outputs=x)
compiled_model = torch.compile(model)
exported_program = torch.export.export(model, (example_input,))
# ...

How to start

See Jupyter Notebook showing the basic usage of Pytorch Symbolic:

• Learn Pytorch Symbolic in an interactive way.
• Try the package before installing it on your computer.
• See visualizations of graphs that are created under the hood.

Open in Colab:

Installation

Install Pytorch Symbolic easily with pip:

pip install pytorch-symbolic

Troubleshooting

Please create an issue if you notice a problem!

Links

• See Documentation
• See on GitHub
• See on PyPI