Tool box for PyTorch
Project description
Pytorch-Tools
Tool box for PyTorch for fast prototyping.
Overview
- FitWrapper - Keras like model trainer
- Losses - collection of different Loss functions.
- Metrics - collection of metrics.
- Models - classification model zoo.
- Optimizers
- Segmentation Models - segmentation models zoo
- TTA wrapper - wrapper for easy test-time augmentation
Installation
Requires GPU drivers and CUDA already installed.
pip install git+https://github.com/bonlime/pytorch-tools.git@master
It is also recommended to install NVIDIA Apex to allow usage of additional optimizers
pip install ---upgrade -v --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" git+https://github.com/NVIDIA/apex.git
Designed and maintained by @bonlime and @zakajd
Star the project if you like it!
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
pytorch_tools-0.5.6.tar.gz
(786.4 kB
view hashes)
Built Distribution
pytorch_tools-0.5.6-py3-none-any.whl
(168.2 kB
view hashes)
Close
Hashes for pytorch_tools-0.5.6-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2b36b05fac0c2ae8908b009de7b02ed8c78b19f012ad78e38189a50cbd64a721 |
|
MD5 | 9dd68e2f324e743ac062009285c14e40 |
|
BLAKE2b-256 | 9f6ea6c30fee53405062d5dc02e5267a10e5f4afc87cceb2bd4bb3de7fc15f68 |