TensorFlow的封裝

TensorFlow是比較底層的深度學習API，TF-Slim、TFLearn、Keras和TensorLayer均嘗試簡化TensorFlow/Theano，它們對TensorFlow/Theano的進行高層封裝，API實現更加的工程化。從1.0開始，TensorFlow官方支持Keras，因此Keras會成爲主流。

TF-Slim: A high level library to define complex models in TensorFlow.
連接：https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/slim

TFLearn: A deep learning library featuring a higher-level API for TensorFlow.
連接：http://tflearn.org/

Keras: A deep learning library for TensorFlow/Theano in Python. Convnets, recurrent neural networks, and more.
連接：https://keras.io/

TensorLayer: A deep learning and reinforcement learning library for TensorFlow.
連接：http://tensorlayer.readthedocs.io/en/latest/index.html

PS: 一個對比的討論：
https://www.zhihu.com/question/50030898/answer/119785042