Scikit Learn

TensorFlow is a open source software libary for numerical computions using dataflow graphs. TensorFlow was originally developed for the purpose of conducting machine learing and deep learning network research, but the system is general enough to be application in a wide variety of other domain's as well.

Skflow scikit Flow provide a set of high level model classes that you can use to easily intergrate with your existing Scikit-Learn pipeline code. Scikit Flow is a simplified interface for TensorFlow, to get people started on preddictive analytics and data mining. Scikit Flow has been merged into Tensorflow since version 0.8 and now Called Tensor Flow Learn.

Keras Keras is a minimalist, highly modular nerual networks library, written in Python and capable of running on top of either TensorFlow or Theano.

TensorFlow main Classes tf.Graph() tf.Operation() tf.Tensor() tf.Session()

Some Useful funtions: tf.get_default_session() tf.get_default_graph() tf.reset_default_graph() ops.reset_default_graph() tf.device("/cpu:0") tf.name_scope(value)

TensorFlow Optimizers GradientDescentOptimizer AdagradOptimizer AdagradOptimizer MomentumOptimizer AdamOptimizer FtrlOptimizer RMSPropOptimizer

Reduction reduce_sum reduce_prod reduce_min reduce_max reduce_mean reduce_all reduce_any accumulate_n Activation Functins tf.nn? relu relu6 elu softplus dropsign dropout bias_add sigmoid tanh sigmoid_cross_entropy_with_logits softmax log_softwax softwax_ tf.convert_to_tensor(value)

Skflow main classes TensorFlowClassifier TensorFlowRegressor TensorFlowDNNRegressor TensorFlowLinearClassifier TensorFlowLinearRegressor TensorFlowRNNClassifier TensorFlowRNNRegressor