pytorch-toolbelt

(★ 1,574)

PyTorch extensions for fast R&D prototyping and Kaggle farming

File Explorer

Download Latest Version (.zip)

- - bug-report.md
- - ci.yml
  - codeql.yml
  - upload_to_pypi.yml
- demo_losses.py
- 480px-Flag_of_Ukraine.jpg
- SegmentationModelsTutorial.ipynb
- tiled_inference.ipynb
- - __init__.py
  - common.py
  - mean_std.py
  - segmentation.py
  - wrappers.py
- - __init__.py
  - ensembling.py
  - functional.py
  - tiles.py
  - tiles_3d.py
  - tta.py
- - __init__.py
  - balanced_bce.py
  - bitempered_loss.py
  - dice.py
  - focal.py
  - focal_cosine.py
  - functional.py
  - jaccard.py
  - logcosh.py
  - lovasz.py
  - quality_focal_loss.py
  - soft_bce.py
  - soft_ce.py
  - soft_f1.py
  - wing_loss.py
- - __init__.py
  - activations.py
  - coord_conv.py
  - drop_path.py
  - dropblock.py
  - dsconv.py
  - fpn.py
  - identity.py
  - initialization.py
  - interfaces.py
  - normalization.py
  - ocnet.py
  - pooling.py
  - scse.py
  - simple.py
  - spp.py
  - srm.py
  - unet.py
  - upsample.py
- - __init__.py
  - functional.py
  - lr_schedules.py
- - __init__.py
  - bboxes_utils.py
  - bucket_assignment.py
  - distributed.py
  - fs.py
  - namesgenerator.py
  - python_utils.py
  - random_utils.py
  - rle.py
  - support.py
  - torch_utils.py
  - visualization.py
- __init__.py
- lena.png
- test_activations.py
- test_ddp_utils.py
- test_decoders.py
- test_encoders.py
- test_filesystem_utils.py
- test_init.py
- test_losses.py
- test_model_export.py
- test_modules.py
- test_optimizer.py
- test_tiles.py
- test_tta.py
- test_utils_functional.py
- test_visualization.py
.gitattributes
.gitignore
CREDITS.md
LICENSE
makefile
MANIFEST.in
pyproject.toml
README.md
setup.cfg
setup.py

# Installation Guide

1. Get the code

git clone https://github.com/BloodAxe/pytorch-toolbelt

Downloads the entire project code from GitHub to your computer.

cd pytorch-toolbelt

Moves into the project folder you just downloaded.

2. Python

Easy Recommended

Prerequisites

Git Needed to download the project code from GitHub.
Python 3 On Windows, be sure to check 'Add Python to PATH' during installation.

pip install .

Installs the package published on PyPI directly — no need to clone the source.

jupyter notebook

Launches Jupyter in your browser so you can open and run the notebook (.ipynb) files.

✅ If it runs without errors and prints output in the terminal, it worked.

3. Make

Medium

Prerequisites

Git Needed to download the project code from GitHub.
Make Usually pre-installed on Linux/macOS. On Windows, install separately (e.g. via MSYS2 or WSL).

make

Compiles the code based on the generated build configuration to produce an executable.

✅ If it finishes without errors, it worked. Try running the generated executable directly.