Jupyter Notebook
Need help with RotNet?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.
177 Stars 87 Forks MIT License 31 Commits 5 Opened issues

Services available

Need anything else?


This repository contains the code necessary to train and test convolutional neural networks (CNNs) for predicting the rotation angle of an image to correct its orientation. There are scripts to train two models, one on MNIST and another one on the Google Street View dataset. Since the data for this application is generated on-the-fly, you can also train using your own images in a similar way. A detailed explanation of the code and motivation for this project can be found in my blog.


The code mainly relies on Keras to train and test the CNN models, and OpenCV for image manipulation.

You can install all the required packages using pip:

pip install -r requirements.txt

The recommended way to use Keras is with the TensorFlow backend. If you want to use it with the Theano backend you will need to make some minor modifications to the code to make it work.


Run either

python train/train_mnist.py
to train on MNIST or
python train/train_street_view.py
to train on the Google Street View dataset. Note that the first time you run the scripts will take longer since the datasets will be automatically downloaded. Also, you will need a decent GPU to train the ResNet50 model that is used in
, otherwise it will take quite long to finish.

If you only want to test the models, you can download pre-trained versions here.

Note also that the regression models (

) don't provide a good accuracy and are only included for illustration purposes.


You can evaluate the models and display examples using the provided Jupyter notebooks. Simply run

jupyter notebook
from the root directory and navigate to

Finally, you can use the

script to correct the orientation of your own images. You can run it as follows:

python correct_rotation.py  

You can also specify the following command line arguments: -

-o, --output
to specify the output image or directory. -
-b, --batch_size
to specify the batch size used to run the model. -
-c, --crop
to crop out the black borders after rotating the images.

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.