...
Developers should be prepared to integrate with and use their deep learning portfolio. Before we get some scope on their API's and endpoints some background in deep learning (a specialized subset of machine learning concentrated on the "Greedy Layer-Wise Unsupervised Pretraining procedure" - Hinton, 2006 - University of Toronto) and the "Long Short-Term Memory model - Hochreiter and Schmidhuber 1997" will be required.
Design/Theory Preparation
Get the following Nov 2016 MIT book from Amazon by Ian Goodfellow, Yoshua Benglo, Aaron Courville - (one for work, and one for home - as it is usually out of stock). Review your linear transformation and matrix math to prep.
Installing Tensorflow
follow/verify via https://www.tensorflow.org/install/install_mac
| Code Block | ||||
|---|---|---|---|---|
| ||||
obrien:obrienlabs amdocs$ docker run -it tensorflow/tensorflow bash
Unable to find image 'tensorflow/tensorflow:latest' locally
latest: Pulling from tensorflow/tensorflow
22dc81ace0ea: Pull complete
1a8b3c87dba3: Pull complete
91390a1c435a: Pull complete
07844b14977e: Pull complete
b78396653dae: Pull complete
22bb9efa20f2: Pull complete
e385adcc1f05: Pull complete
da0eaa434771: Pull complete
f3ad8e6a231d: Pull complete
1da6064a2568: Pull complete
e701d2aeb76d: Pull complete
cba62e3f7418: Pull complete
3b523741fd2e: Pull complete
Digest: sha256:f3b5484e3335d2eb72940a6addde6f714173ff46c8a13c06aaf10915e96bc539
Status: Downloaded newer image for tensorflow/tensorflow:latest
root@4c49aac50ce1:/notebooks# python
Python 2.7.12 (default, Dec 4 2017, 14:50:18)
[GCC 5.4.0 20160609] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> import tensorflow as tf
/usr/local/lib/python2.7/dist-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
>>> hello = tf.constant('Hello, TensorFlow!')
>>> sess = tf.Session()
2018-04-22 23:57:53.221560: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
>>> print(sess.run(hello))
Hello, TensorFlow! |
AIaaS
Open Source
Acumos
TensorFlow
...