# ktrain
*ktrain* is a lightweight wrapper for the deep learning library [Keras](https://keras.io/) to help build, train, and deploy neural networks. With only a few lines of code, ktrain allows you to easily and quickly:
- estimate an optimal learning rate for your model given your data using a Learning Rate Finder
- employ learning rate schedules such as the [triangular policy](https://arxiv.org/abs/1506.01186), the [1cycle policy](https://arxiv.org/abs/1803.09820), and [SGDR](https://arxiv.org/abs/1608.03983) to effectively minimize loss and improve generalization
- fast and easy-to-use pre-canned models for both text classification (e.g., NBSVM, fastText, logreg) and image classification (e.g., ResNet, Wide ResNet, Inception)
- methods to help you easily load and preprocess text and image data from a variety of formats
- easily inspect data points that were misclassified to help improve your model
- a simple prediction API for saving and deploying models and data-preprocessing steps to easily make predictions on new raw data
#### Tutorial Notebooks
Please see the following tutorial notebooks for a guide on how to use *ktrain* on your projects:
* Tutorial 1: [Introduction](https://github.com/amaiya/ktrain/blob/master/tutorial-01-introduction.ipynb)
* Tutorial 2: [Tuning Learning Rates](https://github.com/amaiya/ktrain/blob/master/tutorial-02-tuning-learning-rates.ipynb)
* Tutorial 3: [Image Classification](https://github.com/amaiya/ktrain/blob/master/tutorial-03-image-classification.ipynb)
* Tutorial 4: [Text Classification](https://github.com/amaiya/ktrain/blob/master/tutorial-04-text-classification.ipynb)
* Tutorial A1: [Additional tricks](https://github.com/amaiya/ktrain/blob/master/tutorial-A1-additional-tricks.ipynb), which covers topics such as examining misclassifications, inspecting intermediate output of Keras models for debugging, and built-in callbacks.
Tasks such as text classification and image classification can be accomplished easily with
only a few lines of codes.
#### Example: Classifying Images of [Dogs and Cats](https://www.kaggle.com/c/dogs-vs-cats) Using *ktrain*
```
import ktrain
from ktrain import vision as vis
(train_data, val_data, preproc) = vis.images_from_folder(
datadir='data/dogscats',
data_aug = vis.get_data_aug(horizontal_flip=True),
train_test_names=['train', 'valid'],
target_size=(224,224), color_mode='rgb')
model = vis.image_classifier('pretrained_resnet50', train_data, val_data, freeze_layers=80)
learner = ktrain.get_learner(model=model, train_data=train_data, val_data=val_data,
workers=8, use_multiprocessing=False, batch_size=64)
learner.lr_find() # briefly simulate training to find good learning rate
learner.lr_plot() # visually identify best learning rate
# implicitly employs triangular learning rate policy with ReduceLROnPlateau, ModelCheckpoint, and EarlyStopping
learner.autofit(1e-4, checkpoint_folder='/tmp')
```
### Requirements
The following software/libraries should be installed:
- [Python 3.6+](https://www.python.org/) (tested on 3.6.7)
- [Keras](https://keras.io/) (tested on 2.2.4)
- [TensorFlow](https://www.tensorflow.org/) (tested on 1.10.1)
- [scikit-learn](https://scikit-learn.org/stable/) (tested on 0.20.0)
- [matplotlib](https://matplotlib.org/) (tested on 3.0.0)
- [pandas](https://pandas.pydata.org/) (tested on 0.24.2)
<!--- [PIL](https://pillow.readthedocs.io/en/stable/) (tested on 5.1.0) -->
<!-- - [scipy](https://www.scipy.org/) (tested on 1.2.1) - insalled by scikit-learn-->
<!-- - [numpy](http://www.numpy.org/) (tested on 1.16.1) - installed by scikit-learn -->
This code was tested on Ubuntu 18.04 LTS using Keras 2.2.4 with a TensorFlow 1.10 backend.
There are a few portions of the code that may explicitly depend on TensorFlow, but
such dependencies are kept to a minimum.
----
**Creator: [Arun S. Maiya](http://arun.maiya.net)**
**Email:** arun [at] maiya [dot] net
*ktrain* is a lightweight wrapper for the deep learning library [Keras](https://keras.io/) to help build, train, and deploy neural networks. With only a few lines of code, ktrain allows you to easily and quickly:
- estimate an optimal learning rate for your model given your data using a Learning Rate Finder
- employ learning rate schedules such as the [triangular policy](https://arxiv.org/abs/1506.01186), the [1cycle policy](https://arxiv.org/abs/1803.09820), and [SGDR](https://arxiv.org/abs/1608.03983) to effectively minimize loss and improve generalization
- fast and easy-to-use pre-canned models for both text classification (e.g., NBSVM, fastText, logreg) and image classification (e.g., ResNet, Wide ResNet, Inception)
- methods to help you easily load and preprocess text and image data from a variety of formats
- easily inspect data points that were misclassified to help improve your model
- a simple prediction API for saving and deploying models and data-preprocessing steps to easily make predictions on new raw data
#### Tutorial Notebooks
Please see the following tutorial notebooks for a guide on how to use *ktrain* on your projects:
* Tutorial 1: [Introduction](https://github.com/amaiya/ktrain/blob/master/tutorial-01-introduction.ipynb)
* Tutorial 2: [Tuning Learning Rates](https://github.com/amaiya/ktrain/blob/master/tutorial-02-tuning-learning-rates.ipynb)
* Tutorial 3: [Image Classification](https://github.com/amaiya/ktrain/blob/master/tutorial-03-image-classification.ipynb)
* Tutorial 4: [Text Classification](https://github.com/amaiya/ktrain/blob/master/tutorial-04-text-classification.ipynb)
* Tutorial A1: [Additional tricks](https://github.com/amaiya/ktrain/blob/master/tutorial-A1-additional-tricks.ipynb), which covers topics such as examining misclassifications, inspecting intermediate output of Keras models for debugging, and built-in callbacks.
Tasks such as text classification and image classification can be accomplished easily with
only a few lines of codes.
#### Example: Classifying Images of [Dogs and Cats](https://www.kaggle.com/c/dogs-vs-cats) Using *ktrain*
```
import ktrain
from ktrain import vision as vis
(train_data, val_data, preproc) = vis.images_from_folder(
datadir='data/dogscats',
data_aug = vis.get_data_aug(horizontal_flip=True),
train_test_names=['train', 'valid'],
target_size=(224,224), color_mode='rgb')
model = vis.image_classifier('pretrained_resnet50', train_data, val_data, freeze_layers=80)
learner = ktrain.get_learner(model=model, train_data=train_data, val_data=val_data,
workers=8, use_multiprocessing=False, batch_size=64)
learner.lr_find() # briefly simulate training to find good learning rate
learner.lr_plot() # visually identify best learning rate
# implicitly employs triangular learning rate policy with ReduceLROnPlateau, ModelCheckpoint, and EarlyStopping
learner.autofit(1e-4, checkpoint_folder='/tmp')
```
### Requirements
The following software/libraries should be installed:
- [Python 3.6+](https://www.python.org/) (tested on 3.6.7)
- [Keras](https://keras.io/) (tested on 2.2.4)
- [TensorFlow](https://www.tensorflow.org/) (tested on 1.10.1)
- [scikit-learn](https://scikit-learn.org/stable/) (tested on 0.20.0)
- [matplotlib](https://matplotlib.org/) (tested on 3.0.0)
- [pandas](https://pandas.pydata.org/) (tested on 0.24.2)
<!--- [PIL](https://pillow.readthedocs.io/en/stable/) (tested on 5.1.0) -->
<!-- - [scipy](https://www.scipy.org/) (tested on 1.2.1) - insalled by scikit-learn-->
<!-- - [numpy](http://www.numpy.org/) (tested on 1.16.1) - installed by scikit-learn -->
This code was tested on Ubuntu 18.04 LTS using Keras 2.2.4 with a TensorFlow 1.10 backend.
There are a few portions of the code that may explicitly depend on TensorFlow, but
such dependencies are kept to a minimum.
----
**Creator: [Arun S. Maiya](http://arun.maiya.net)**
**Email:** arun [at] maiya [dot] net
1 maintainer
Metadata
1 maintainer
Release files for ktrain 0.1.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| ktrain-0.1.2.tar.gz | 37.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| ktrain-0.1.2-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 84.2 kB
Release files / ktrain-0.1.2.tar.gz
| Download URL | ktrain-0.1.2.tar.gz |
|---|---|
| Size | 37.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
cee4f5b7dab535c5c62e9c3ed59698cf907eae000fc00379f83df86f32194ea8
|
|
BLAKE2b-256 checksum How to use checksums |
4c9028cf5d0f2aad2cebd63e74d292be22b5a16ff9f915671bf3a38b8998eabf
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/1.13.0 pkginfo/1.5.0.1 requests/2.18.4 setuptools/39.0.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.6.7
|
Release files / ktrain-0.1.2-py3-none-any.whl
| Download URL | ktrain-0.1.2-py3-none-any.whl |
|---|---|
| Size | 47.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c6fde9586964e63c7e31a93396a4b3a948d0ead46691e818ed5a64afff03751a
|
|
BLAKE2b-256 checksum How to use checksums |
1c36aa1f76377b87ca55d847f8287ee0c38f7060ffa6637533372562e783ba9e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/1.13.0 pkginfo/1.5.0.1 requests/2.18.4 setuptools/39.0.1 requests-toolbelt/0.9.1 tqdm/4.31.1 CPython/3.6.7
|
