TensorFlow Dev Summit 2017: Integrating Keras and TensorFlow

I am briefly sharing a video from the last TensorFlow Dev Summit in February 2017. My choice has fallen to a presentation by François Chollet of the deep learning library API Keras and its integration with TensorFlow. As Dr. Chollet explains, Keras integrated with TensorFlow promises to streamline deep learning frameworks in ways that will be increasingly user-friendly, rendering the mass adoption of these software developments a more feasible reality:


Dr. François Chollet is the primary author of Keras, developing this tool while at Research at Google. The example workflows presented in this video are worth an attentive check up. For instance the way video with text data is processed with the Keras-TensorFlow integration is nicely described with the stack of CNNs, LSTMs and dense final layers with softmax being features explained by Dr. Chollet. The best practises advised by Dr. Chollet about the initialization of recurrent weighs of  the neural network is worth to listen, even if the experienced practitioner feels bored. With new software tools, every reminder of common practice is worth to note.

A final note to the confirmation by Dr. Chollet of the capacity of TensorFlow to streamline  a CloudML or a hyperparameter tuning process with just a few lines of code, enabling a distributed training platform able to enhance big data computes with productivity gains. And all democratically open and accessible to everyone…

featured image: Integrating Keras & TensorFlow: The Keras workflow, expanded (TensorFlow Dev Summit 2017)

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s