Metadata-Version: 2.1
Name: sitorchtools
Version: 0.0.1
Summary: A small package
Home-page: https://pypi.org/project/sitorchtools
Author: ulwan
Author-email: ulwan.nashihun@tiket.com
License: MIT
Keywords: pytorchtools,pytorch-early-stopping,image-dataloader,pytorch-imbalanced,data-scientist,deep-learning
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Intended Audience :: Developers
Classifier: Topic :: Software Development :: Build Tools
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Image Processing
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: matplotlib (>=3.3.3)
Requires-Dist: numpy (>=1.19.4)
Requires-Dist: scikit-learn (>=0.24.0)

# sitorchtools
Support function for train dataset using Pytorch

## Features
```
Early Stopping based on validation loss
Folder loader based on pytorch DataLoader
Imblanaced image data handling
Spliting Image on Folder to train and test dataset
```
## Usage
1. EarlyStopping
```
from sitorchtools import EarlyStopping, folder_loader, img_folder_split
    early_stopping = EarlyStopping(
        patience=7,
        verbose=True,
        delta=0,
        path="best_model.pth",
        trace_func=print,
        model_class=None
        )

    early_stopping(model, train_loss, valid_loss, y_true, y_pred, plot=False)
```

2. Data Loader
```
train_set, train_loader = folder_loader.loader(
    your_train_path,
    transform=your_train_transform,
    batch_size=your_bs,
    imbalance=True)
```

3. image folder split
```
img_folder_split.split_folder(path_to_train_data, path_to_test_data, train_ratio)
```


