Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/harry24k/pytorch-custom-utils
Custom utils for Pytorch
https://github.com/harry24k/pytorch-custom-utils
deep-learning pytorch utils
Last synced: about 2 months ago
JSON representation
Custom utils for Pytorch
- Host: GitHub
- URL: https://github.com/harry24k/pytorch-custom-utils
- Owner: Harry24k
- License: mit
- Created: 2019-04-21T11:17:06.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2022-11-20T05:38:05.000Z (about 2 years ago)
- Last Synced: 2024-10-12T21:12:00.412Z (2 months ago)
- Topics: deep-learning, pytorch, utils
- Language: Python
- Homepage:
- Size: 5.25 MB
- Stars: 9
- Watchers: 1
- Forks: 2
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# pytorch-custom-utils
[](https://img.shields.io/github/license/Harry24k/pytorch-custom-utils)
[](https://img.shields.io/pypi/v/torchhk)
This is a lightweight repository to help PyTorch users.
## Usage
### :clipboard: Dependencies
- torch 1.4.0
- torchvision 0.5.0
- python 3.6
- matplotlib 2.2.2
- numpy 1.14.3
- seaborn 0.9.0
- sklearn
- plotly
### :hammer: Installation
- `pip install torchhk` or
- `git clone https://github.com/Harry24k/pytorch-custom-utils`
```python
from torchhk import *
```
### :rocket: Demos
- **RecordManager** ([code](https://github.com/Harry24k/pytorch-custom-utils/blob/master/demo/RecordManager.ipynb), [markdown](https://github.com/Harry24k/pytorch-custom-utils/blob/master/docs/RecordManager.md)):
RecordManager will help you to keep tracking training records.
- **Datasets** ([code](https://github.com/Harry24k/pytorch-custom-utils/blob/master/demo/Datasets.ipynb), [markdown](https://github.com/Harry24k/pytorch-custom-utils/blob/master/docs/Datasets.md)):
Dataset will help you to use torch datasets including split and label-filtering.
Supported datasets
```python
# CIFAR10
datasets = Datasets("CIFAR10", root='./data')
# CIFAR100
datasets = Datasets("CIFAR100", root='./data')
# STL10
datasets = Datasets("STL10", root='./data')
# MNIST
datasets = Datasets("MNIST", root='./data')
# FashionMNIST
datasets = Datasets("FashionMNIST", root='./data')
# SVHN
datasets = Datasets("SVHN", root='./data')
# MNISTM
datasets = Datasets("MNISTM", root='./data')
# ImageNet
datasets = Datasets("ImageNet", root='./data')
# USPS
datasets = Datasets("USPS", root='./data')
# TinyImageNet
datasets = Datasets("TinyImageNet", root='./data')
# CIFAR with Unsupervised
datasets = Datasets("CIFAR10U", root='./data')
datasets = Datasets("CIFAR100U", root='./data')
# Corrupted CIFAR (Only test data will be corrupted)
# CORRUPTIONS = [
# 'gaussian_noise', 'shot_noise', 'impulse_noise', 'defocus_blur',
# 'glass_blur', 'motion_blur', 'zoom_blur', 'snow', 'frost', 'fog',
# 'brightness', 'contrast', 'elastic_transform', 'pixelate',
# 'jpeg_compression'
#]
datasets = Datasets("CIFAR10", root='./data',corruption='gaussian_noise')
```
- **Vis** ([code](https://github.com/Harry24k/pytorch-custom-utils/blob/master/demo/Vis.ipynb), [markdown](https://github.com/Harry24k/pytorch-custom-utils/blob/master/docs/Vis.md)):
Vis will help you to visualize torch tensors.
- **Transform** ([code](https://github.com/Harry24k/pytorch-custom-utils/blob/master/demo/Transform.ipynb)):
Transform will help you to change specific layers.
## Contribution
Contribution is always welcome! Use [pull requests](https://github.com/Harry24k/adversarial-attacks-pytorch/pulls) :blush: