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!
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-0.5.1.tar.gz
(787.5 kB
view details)
File details
Details for the file pytorch_tools-0.5.1.tar.gz.
File metadata
- Download URL: pytorch_tools-0.5.1.tar.gz
- Upload date:
- Size: 787.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 7fe55d5f7ad5834fc49d8acb24aebbd0b0ac7a747dbd59c2ed51b476d635a1ce |
|
| MD5 | ec134edc8791a775bed8fec65214ae0c |
|
| BLAKE2b-256 | 776e4ff74c22ed8d54bf96c87f3ba51781594d7e2533941b66737cfd03399b84 |
