Accelerated Deep Learning R&D

</div>

Catalyst is a PyTorch framework for Deep Learning Research and Development. It focuses on reproducibility, rapid experimentation, and codebase reuse so you can create something new rather than write yet another train loop. Break the cycle – use the Catalyst!

<details> <summary>Catalyst at PyTorch Ecosystem Day 2021</summary>

</details> <details> <summary>Catalyst at PyTorch Developer Day 2021</summary>

</details>

Getting started

pip install -U catalyst

import os
from torch import nn, optim
from torch.utils.data import DataLoader
from catalyst import dl, utils
from catalyst.contrib.datasets import MNIST

model = nn.Sequential(nn.Flatten(), nn.Linear(28 * 28, 10))
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.02)
loaders = {
    "train": DataLoader(MNIST(os.getcwd(), train=True), batch_size=32),
    "valid": DataLoader(MNIST(os.getcwd(), train=False), batch_size=32),
}

runner = dl.SupervisedRunner(
    input_key="features", output_key="logits", target_key="targets", loss_key="loss"
)

# model training
runner.train(
    model=model,
    criterion=criterion,
    optimizer=optimizer,
    loaders=loaders,
    num_epochs=1,
    callbacks=[
        dl.AccuracyCallback(input_key="logits", target_key="targets", topk=(1, 3, 5)),
        dl.PrecisionRecallF1SupportCallback(input_key="logits", target_key="targets"),
    ],
    logdir="./logs",
    valid_loader="valid",
    valid_metric="loss",
    minimize_valid_metric=True,
    verbose=True,
)

# model evaluation
metrics = runner.evaluate_loader(
    loader=loaders["valid"],
    callbacks=[dl.AccuracyCallback(input_key="logits", target_key="targets", topk=(1, 3, 5))],
)

# model inference
for prediction in runner.predict_loader(loader=loaders["valid"]):
    assert prediction["logits"].detach().cpu().numpy().shape[-1] == 10

# model post-processing
model = runner.model.cpu()
batch = next(iter(loaders["valid"]))[0]
utils.trace_model(model=model, batch=batch)
utils.quantize_model(model=model)
utils.prune_model(model=model, pruning_fn="l1_unstructured", amount=0.8)
utils.onnx_export(model=model, batch=batch, file="./logs/mnist.onnx", verbose=True)

Step-by-step Guide

Start with Catalyst — A PyTorch Framework for Accelerated Deep Learning R&D introduction.
Try notebook tutorials or check minimal examples for first deep dive.
Read blog posts with use-cases and guides.
Learn machine learning with our "Deep Learning with Catalyst" course.
And finally, join our slack if you want to chat with the team and contributors.

Getting started
- Step-by-step Guide
Table of Contents
Overview
Community

Overview

Catalyst helps you implement compact but full-featured Deep Learning pipelines with just a few lines of code. You get a training loop with metrics, early-stopping, model checkpointing, and other features without the boilerplate.

Installation

Generic installation:

pip install -U catalyst

<details> <summary>Specialized versions, extra requirements might apply</summary>

pip install catalyst[ml]         # installs ML-based Catalyst
pip install catalyst[cv]         # installs CV-based Catalyst
# master version installation
pip install git+https://github.com/catalyst-team/catalyst@master --upgrade
# all available extensions are listed here:
# https://github.com/catalyst-team/catalyst/blob/master/setup.py

</details>

Catalyst is compatible with: Python 3.7+. PyTorch 1.4+. Tested on Ubuntu 16.04/18.04/20.04, macOS 10.15, Windows 10, and Windows Subsystem for Linux.

Documentation

master
22.02
<details> <summary>2021 edition</summary> 
 </details>
<details> <summary>2020 edition</summary> 
- 20.12
- 20.11
- 20.10
- 20.09
- 20.08.2
- 20.07 (dev blog: 20.07 release)
- [20.06](https://catalyst-team.github.io/ca

Catalyst

Install / Use

README

Getting started

Step-by-step Guide

Table of Contents

Overview

Installation

Documentation