TensorFlow:

Machine Intelligence made easier

https://slides.com/ramonraya/deck-2/live#/

Ramón Raya

software Dev

rraya@nearsoft.com

Machine Learning?

• Build it

• Train it

• Test it

Qué es TF?

• OpenSource

• Nodos como operaciones

• Tensors

3 # a rank 0 tensor; this is a scalar with shape []
[1. ,2., 3.] # a rank 1 tensor; this is a vector with shape [3]
[[1., 2., 3.], [4., 5., 6.]] # a rank 2 tensor; a matrix with shape [2, 3]
[[[1., 2., 3.]], [[7., 8., 9.]]] # a rank 3 tensor with shape [2, 1, 3]

Cuál es la magia?

• Arquitectura flexible

• Projecto de GMI research

Ahora un pequeño ejemplo explicado

Definiendo si una imagen contiene Darth Vader o Darth Maul

Inception by Google

Aqui nos colgamos

Key commands

python tensorflow/examples/image_retraining/retrain.py \
--bottleneck_dir=/tf_files/bottlenecks \
--how_many_training_steps 500 \
--model_dir=/tf_files/inception \
--output_graph=/tf_files/retrained_graph.pb \
--output_labels=/tf_files/retrained_labels.txt \
--image_dir /tf_files/flower_photos

Preguntas?

Enlaces útiles!

- Pagina central de TF:

www.tensoflow.org

- Video tutoriales por Siraj Raval:

https://www.youtube.com/playlist?list=PL2-dafEMk2A7YdKv4XfKpfbTH5z6rEEj3

- Codelab de imagenes:

https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/

- Machine Learning @ google research:

https://research.google.com/pubs/MachineIntelligence.html