17

There are two TFLearn projects

TF Learn (aka Scikit Flow)
https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/learn/python/learn

and

TFLearn: Deep learning library featuring a higher-level API for TensorFlow.
https://github.com/tflearn/tflearn

what is the status of these projects, are they going to stay separate or they going to merged together?

momeara
  • 1,341
  • 2
  • 17
  • 29

2 Answers2

6

TF.Learn is a built-in module inside TensorFlow built by Googlers and outside contributors. It's originally called skflow (Scikit Flow). It is for both deep learning as well as general machine learning. You can find the official tutorials on TensorFlow website.

Yuan Tang
  • 696
  • 4
  • 15
  • 1
    Now TF.Learn is renamed to be TensorFlow Estimators under `tf.estimator`. You can check our KDD paper for more details of the architectural design here: http://dl.acm.org/citation.cfm?id=3098171 – Yuan Tang Aug 20 '17 at 21:00
3

Tflearn is actually a separate package, which doesn't come with the standard tensorflow distribution. One needs to do pip install tflearn to actually install it. It seems the models included in tflearn are very limited (mainly DNN) but no linear classifiers for example, whereas tf.contrib.learn has more models, e.g.:

tf.contrib.learn.LinearClassifier
tsando
  • 4,557
  • 2
  • 33
  • 35
  • Is there any difference between a linear model and a neural network with one parametric layer and the identity as activation function? – Martin Thoma Jun 14 '17 at 17:42