https://yokekeong.com/blog/keras/Recent content in Keras on Yoke KeongHugoenMon, 05 Aug 2019 12:00:00 +0000https://yokekeong.com/serving-rock-paper-scissors-image-classifier-app-built-with-tensorflow-2-keras-and-flask/Mon, 05 Aug 2019 12:00:00 +0000https://yokekeong.com/serving-rock-paper-scissors-image-classifier-app-built-with-tensorflow-2-keras-and-flask/<p><em>Picture Credits:</em> <a href="https://pixabay.com/vectors/interface-internet-program-browser-3614766/"><em>Pixabay</em></a></p> <p>In this post, we shall be looking at serving a Tensorflow 2 Keras image classification model with a Flask app.</p> <p>We shall be leveraging on the <a href="https://github.com/lmoroney/io19/blob/master/Zero%20to%20Hero/Rock-Paper-Scissors.ipynb">Rock Paper Scissors Tensorflow 2 Notebook</a> created by <a href="http://laurencemoroney.com/">Laurence Moroney</a> and built on the Image Classifier App template provided by <a href="https://github.com/mtobeiyf">Fing</a> on the Github repository <a href="https://github.com/mtobeiyf/keras-flask-deploy-webapp">here</a>.</p> <h3 id="training-and-saving-the-model-in-google-colab">Training and saving the Model in Google Colab</h3> <p>To train the model, we can run the aforementioned Jupyter Notebook on <a href="https://colab.research.google.com/">Google Colab</a>. To train the model successfully, we will need to ensure that Tensorflow 2 beta is installed with the following command:</p>