awslabs/autogluon
AutoGluon: AutoML Toolkit for Deep Learning
| repo name | awslabs/autogluon |
| repo link | https://github.com/awslabs/autogluon |
| homepage | https://autogluon.mxnet.io |
| language | Python |
| size (curr.) | 4964 kB |
| stars (curr.) | 2037 |
| created | 2019-07-29 |
| license | Apache License 2.0 |
AutoGluon: AutoML Toolkit for Deep Learning
AutoGluon automates machine learning tasks enabling you to easily achieve strong predictive performance in your applications. With just a few lines of code, you can train and deploy high-accuracy deep learning models on tabular, image, and text data. Get started with:
# First install package from terminal: pip install mxnet autogluon
from autogluon import TabularPrediction as task
train_data = task.Dataset(file_path='https://autogluon.s3.amazonaws.com/datasets/Inc/train.csv')
test_data = task.Dataset(file_path='https://autogluon.s3.amazonaws.com/datasets/Inc/test.csv')
predictor = task.fit(train_data=train_data, label='class')
performance = predictor.evaluate(test_data)
See the AutoGluon Website for instructions on:
- Installing AutoGluon
- Learning with tabular data
- Learning with image data
- Learning with text data
- More advanced topics such as Neural Architecture Search
License
This library is licensed under the Apache 2.0 License.
