#CNTK – The Microsoft Cognitive Toolkit

Hola !

Hoy Microsoft ha liberado una nueva versión de Microsoft Cognitive Toolkit (link), al que ya conocíamos por CNTK (algo conocíamos antes pero no el modo oficial). Dentro de poco tiempo tendremos la Release Candidate.

Nota: Gracias a @PabloDoval que me indicó que la versión oficial no está disponible todavía.

Este conjunto de herramientas no va orientado al típico programador Microsoft, este Toolkit está pensado para Científicos de Datos.

Lo mejor para conocer el mismo es recorrer alguna de las introducciones que posee en su homepage, Github o su Wiki. Cabe destacar, que la galería de ejemplos es bastante completa y que además podemos reutilizar y modificar estos ejemplos para adaptarlos a nuestras necesidades. Lo mejor para comprender lo que podemos encontrar es este video

Y además, el copy & paste textual de las funcionalidades que se incluyen.

Highly optimized, built-in components

  • Components can handle multi-dimensional dense or sparse data from Python, C++ or BrainScript
  • FFN, CNN, RNN/LSTM, Batch normalization, Sequence-to-Sequence with attention and more
  • Reinforcement learning, generative adversarial networks, supervised and unsupervised learning
  • Ability to add new user-defined core-components on the GPU from Python
  • Automatic hyperparameter tuning
  • Built-in readers optimized for massive datasets

Efficient resource usage

  • Parallelism with accuracy on multiple GPUs/machines via 1-bit SGD and Block Momentum
  • Memory sharing and other built-in methods to fit even the largest models in GPU memory

Easily express your own networks

  • Full APIs for defining networks, learners, readers, training and evaluation from Python, C++ and BrainScript
  • Evaluate models with Python, C++, C# and BrainScript
  • Interoperation with NumPy
  • Both high-level and low-level APIs available for ease of use and flexibility
  • Automatic shape inference based on your data
  • Fully optimized symbolic RNN loops (no unrolling needed)

Training and hosting with Azure

  • Takes advantage of high-speed resources when used with Azure GPU and Azure networks
  • Host trained models easily on Azure and add real-time training if desired

Saludos @ Toronto

El Bruno

References

Advertisements

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