Skip to content
/ ktrain Public

ktrain is a Python library that makes deep learning and AI more accessible and easier to apply


Notifications You must be signed in to change notification settings


Repository files navigation

PyPI Status ktrain python compatibility license Downloads

Welcome to ktrain

a "Swiss Army knife" for machine learning

News and Announcements

  • 2024-02-20
    • ktrain 0.41.x is released and removes the module. Our OnPrem.LLM package should be used for Generative Question-Answering tasks. See example notebook.


ktrain is a lightweight wrapper for the deep learning library TensorFlow Keras (and other libraries) to help build, train, and deploy neural networks and other machine learning models. Inspired by ML framework extensions like fastai and ludwig, ktrain is designed to make deep learning and AI more accessible and easier to apply for both newcomers and experienced practitioners. With only a few lines of code, ktrain allows you to easily and quickly:

  • employ fast, accurate, and easy-to-use pre-canned models for text, vision, graph, and tabular data:

  • estimate an optimal learning rate for your model given your data using a Learning Rate Finder

  • utilize learning rate schedules such as the triangular policy, the 1cycle policy, and SGDR to effectively minimize loss and improve generalization

  • build text classifiers for any language (e.g., Arabic Sentiment Analysis with BERT, Chinese Sentiment Analysis with NBSVM)

  • easily train NER models for any language (e.g., Dutch NER )

  • load and preprocess text and image data from a variety of formats

  • inspect data points that were misclassified and provide explanations to help improve your model

  • leverage a simple prediction API for saving and deploying both models and data-preprocessing steps to make predictions on new raw data

  • built-in support for exporting models to ONNX and TensorFlow Lite (see example notebook for more information)


Please see the following tutorial notebooks for a guide on how to use ktrain on your projects:

Some blog tutorials and other guides about ktrain are shown below:

ktrain: A Lightweight Wrapper for Keras to Help Train Neural Networks

BERT Text Classification in 3 Lines of Code

Text Classification with Hugging Face Transformers in TensorFlow 2 (Without Tears)

Build an Open-Domain Question-Answering System With BERT in 3 Lines of Code

Finetuning BERT using ktrain for Disaster Tweets Classification by Hamiz Ahmed

Indonesian NLP Examples with ktrain by Sandy Khosasi


Using ktrain on Google Colab? See these Colab examples:

Tasks such as text classification and image classification can be accomplished easily with only a few lines of code.

Example: Text Classification of IMDb Movie Reviews Using BERT [see notebook]

import ktrain
from ktrain import text as txt

# load data
(x_train, y_train), (x_test, y_test), preproc = txt.texts_from_folder('data/aclImdb', maxlen=500,
                                                                     train_test_names=['train', 'test'],
                                                                     classes=['pos', 'neg'])

# load model
model = txt.text_classifier('bert', (x_train, y_train), preproc=preproc)

# wrap model and data in ktrain.Learner object
learner = ktrain.get_learner(model,
                             train_data=(x_train, y_train),
                             val_data=(x_test, y_test),

# find good learning rate
learner.lr_find()             # briefly simulate training to find good learning rate
learner.lr_plot()             # visually identify best learning rate

# train using 1cycle learning rate schedule for 3 epochs
learner.fit_onecycle(2e-5, 3)

Example: Classifying Images of Dogs and Cats Using a Pretrained ResNet50 model [see notebook]

import ktrain
from ktrain import vision as vis

# load data
(train_data, val_data, preproc) = vis.images_from_folder(
                                              data_aug = vis.get_data_aug(horizontal_flip=True),
                                              train_test_names=['train', 'valid'],
                                              target_size=(224,224), color_mode='rgb')

# load model
model = vis.image_classifier('pretrained_resnet50', train_data, val_data, freeze_layers=80)

# wrap model and data in ktrain.Learner object
learner = ktrain.get_learner(model=model, train_data=train_data, val_data=val_data,
                             workers=8, use_multiprocessing=False, batch_size=64)

# find good learning rate
learner.lr_find()             # briefly simulate training to find good learning rate
learner.lr_plot()             # visually identify best learning rate

# train using triangular policy with ModelCheckpoint and implicit ReduceLROnPlateau and EarlyStopping
learner.autofit(1e-4, checkpoint_folder='/tmp/saved_weights')

Example: Sequence Labeling for Named Entity Recognition using a randomly initialized Bidirectional LSTM CRF model [see notebook]

import ktrain
from ktrain import text as txt

# load data
(trn, val, preproc) = txt.entities_from_txt('data/ner_dataset.csv',
                                            sentence_column='Sentence #',
                                            use_char=True) # enable character embeddings

# load model
model = txt.sequence_tagger('bilstm-crf', preproc)

# wrap model and data in ktrain.Learner object
learner = ktrain.get_learner(model, train_data=trn, val_data=val)

# conventional training for 1 epoch using a learning rate of 0.001 (Keras default for Adam optmizer), 1)

Example: Node Classification on Cora Citation Graph using a GraphSAGE model [see notbook]

import ktrain
from ktrain import graph as gr

# load data with supervision ratio of 10%
(trn, val, preproc)  = gr.graph_nodes_from_csv(
                                               'cora.content', # node attributes/labels
                                               'cora.cites',   # edge list
                                              train_pct=0.1, sep='\t')

# load model
model=gr.graph_node_classifier('graphsage', trn)

# wrap model and data in ktrain.Learner object
learner = ktrain.get_learner(model, train_data=trn, val_data=val, batch_size=64)

# find good learning rate
learner.lr_find(max_epochs=100) # briefly simulate training to find good learning rate
learner.lr_plot()               # visually identify best learning rate

# train using triangular policy with ModelCheckpoint and implicit ReduceLROnPlateau and EarlyStopping
learner.autofit(0.01, checkpoint_folder='/tmp/saved_weights')

Example: Text Classification with Hugging Face Transformers on 20 Newsgroups Dataset Using DistilBERT [see notebook]

# load text data
categories = ['alt.atheism', 'soc.religion.christian','', '']
from sklearn.datasets import fetch_20newsgroups
train_b = fetch_20newsgroups(subset='train', categories=categories, shuffle=True)
test_b = fetch_20newsgroups(subset='test',categories=categories, shuffle=True)
(x_train, y_train) = (,
(x_test, y_test) = (,

# build, train, and validate model (Transformer is wrapper around transformers library)
import ktrain
from ktrain import text
MODEL_NAME = 'distilbert-base-uncased'
t = text.Transformer(MODEL_NAME, maxlen=500, class_names=train_b.target_names)
trn = t.preprocess_train(x_train, y_train)
val = t.preprocess_test(x_test, y_test)
model = t.get_classifier()
learner = ktrain.get_learner(model, train_data=trn, val_data=val, batch_size=6)
learner.fit_onecycle(5e-5, 4)
learner.validate(class_names=t.get_classes()) # class_names must be string values

# Output from learner.validate()
#                        precision    recall  f1-score   support
#           alt.atheism       0.92      0.93      0.93       319
#       0.97      0.97      0.97       389
#            0.97      0.95      0.96       396
#soc.religion.christian       0.96      0.96      0.96       398
#              accuracy                           0.96      1502
#             macro avg       0.95      0.96      0.95      1502
#          weighted avg       0.96      0.96      0.96      1502

Example: Tabular Classification for Titanic Survival Prediction Using an MLP [see notebook]

import ktrain
from ktrain import tabular
import pandas as pd
train_df = pd.read_csv('train.csv', index_col=0)
train_df = train_df.drop(['Name', 'Ticket', 'Cabin'], 1)
trn, val, preproc = tabular.tabular_from_df(train_df, label_columns=['Survived'], random_state=42)
learner = ktrain.get_learner(tabular.tabular_classifier('mlp', trn), train_data=trn, val_data=val)
learner.lr_find(show_plot=True, max_epochs=5) # estimate learning rate
learner.fit_onecycle(5e-3, 10)

# evaluate held-out labeled test set
tst = preproc.preprocess_test(pd.read_csv('heldout.csv', index_col=0))
learner.evaluate(tst, class_names=preproc.get_classes())

Additional examples can be found here.


  1. Make sure pip is up-to-date with: pip install -U pip

  2. Install TensorFlow 2 if it is not already installed (e.g., pip install tensorflow).

  3. Install ktrain: pip install ktrain

  4. If using tensorflow>=2.16:

    • Install tf_keras: pip install tf_keras
    • Set the environment variable TF_USE_LEGACY_KERAS to true before importing ktrain

The above should be all you need on Linux systems and cloud computing environments like Google Colab and AWS EC2. If you are using ktrain on a Windows computer, you can follow these more detailed instructions that include some extra steps.

Notes about TensorFlow Versions

  • As of tensorflow>=2.11, you must only use legacy optimizers such as tf.keras.optimizers.legacy.Adam. The newer tf.keras.optimizers.Optimizer base class is not supported at this time. For instance, when using TensorFlow 2.11 and above, please use tf.keras.optimzers.legacy.Adam() instead of the string "adam" in model.compile. ktrain does this automatically when using out-of-the-box models (e.g., models from the transformers library).
  • As mentioned above, due to breaking changes in TensorFlow 2.16, you will need to install the tf_keras package and also set the environment variable TF_USE_LEGACY_KERAS=True before importing ktrain (e.g., add export TF_USE_LEGACY_KERAS=1 in .bashrc or add os.environ['TF_USE_LEGACY_KERAS']="1" at top of your code, etc.).

Additional Notes About Installation

  • Some optional, extra libraries used for some operations can be installed as needed. (Notice that ktrain is using forked versions of the eli5 and stellargraph libraries in order to support TensorFlow2.)
# for graph module:
pip install
# for text.TextPredictor.explain and vision.ImagePredictor.explain:
pip install
# for tabular.TabularPredictor.explain:
pip install shap
# for text.zsl (ZeroShotClassifier), text.summarization, text.translation, text.speech:
pip install torch
# for text.speech:
pip install librosa
# for tabular.causal_inference_model:
pip install causalnlp
# for text.summarization.core.LexRankSummarizer:
pip install sumy
# for
pip install textblob
# for text.generative_ai
pip install onprem
  • ktrain purposely pins to a lower version of transformers to include support for older versions of TensorFlow. If you need a newer version of transformers, it is usually safe for you to upgrade transformers, as long as you do it after installing ktrain.

  • As of v0.30.x, TensorFlow installation is optional and only required if training neural networks. Although ktrain uses TensorFlow for neural network training, it also includes a variety of useful pretrained PyTorch models and sklearn models, which can be used out-of-the-box without having TensorFlow installed, as summarized in this table:

Feature TensorFlow PyTorch Sklearn
training any neural network (e.g., text or image classification)
End-to-End Question-Answering (pretrained)
QA-Based Information Extraction (pretrained)
Zero-Shot Classification (pretrained)
Language Translation (pretrained)
Summarization (pretrained)
Speech Transcription (pretrained)
Image Captioning (pretrained)
Object Detection (pretrained)
Sentiment Analysis (pretrained)
GenerativeAI (sentence-transformers)
Topic Modeling (sklearn)
Keyphrase Extraction (textblob/nltk/sklearn)

As noted above, end-to-end question-answering and information extraction in ktrain can be used with either TensorFlow (using framework='tf') or PyTorch (using framework='pt').

How to Cite

Please cite the following paper when using ktrain:

    title={ktrain: A Low-Code Library for Augmented Machine Learning},
    author={Arun S. Maiya},
    journal={arXiv preprint arXiv:2004.10703},

Creator: Arun S. Maiya

Email: arun [at] maiya [dot] net