Custom utils for PyTorch
Project description
pytorch-custom-utils
Custom utils for Pytorch.
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
orgit clone https://github.com/Harry24k/pytorch-custom-utils
from torchhk import *
Demos
-
RecordManager (code, markdown): RecordManager will help you to record loss or accuracy during iterations. It also provides some useful functions such as summary, plot, etc.
-
Datasets (code, markdown): Dataset utils for loading, split and label filtering.
Supported Datasets: CIFAR10, CIFAR100, STL10, MNIST, FashionMNIST, SVHN, MNISTM, ImageNet, USPS.
-
Vis (code, markdown): Visualization tools for torch tensors.
-
Transform (code): Transform will help you to construct a new model with certain layers changed.
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 Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distribution
torchhk-0.58-py3-none-any.whl
(12.6 kB
view hashes)