pytorch-custom-utils

This is a lightweight repository to help PyTorch users.

Usage

📋 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

🔨 Installation

pip install torchhk or
git clone https://github.com/Harry24k/pytorch-custom-utils

from torchhk import *

🚀 Demos

RecordManager (code, markdown): RecordManager will help you to keep tracking training records.
Datasets (code, markdown): Dataset will help you to use torch datasets including split and label-filtering.

Supported datasets

# 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, markdown): Vis will help you to visualize torch tensors.
Transform (code): Transform will help you to change specific layers.

Contribution

Contribution is always welcome! Use pull requests 😊

Metadata

Release files for torchhk 0.86.14

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for torchhk 0.86.14
File	Interpreter	ABI	Platform	Reset
torchhk-0.86.14-py3-none-any.whl 21.1 kB Nov 20, 2022	Python 3	none	any	Details

Release files / torchhk-0.86.14-py3-none-any.whl

Download URL	torchhk-0.86.14-py3-none-any.whl
Size	21.1 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`0e9d4b36b638dbee72ccb98c65b1b3c5a5378e0c008f70da2fd021404037467a`
BLAKE2b-256 checksum How to use checksums	`42381cf7979f3a1ba807749699fa7930a2633524663bbc6a033c556bdf744126`
Upload date	Nov 20, 2022
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/3.4.1 importlib_metadata/4.12.0 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.8.8`