https://github.com/jianlizh429/tensorflow-learning

Learning tensorflow
https://github.com/jianlizh429/tensorflow-learning

Last synced: about 1 month ago
JSON representation

Learning tensorflow

• Host: GitHub
• URL: https://github.com/jianlizh429/tensorflow-learning
• Owner: JianliZh429
• License: mit
• Created: 2018-03-27T07:43:44.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2018-11-02T01:34:56.000Z (about 6 years ago)
• Last Synced: 2024-04-14T03:50:27.035Z (9 months ago)
• Language: Python
• Size: 29.7 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Tensorflow learning

A sample repository of my tensorflow learning

# Note 1

**Constant values are `stored` in the graph definition**

**Sessions `allocate memory` to store variable values**

# Note 2

**Feed values into placeholders with a dictionary (feed_dict)**

**Easy to use but `poor` performance**

# Note 3

**Separate the assembling of graph and executing ops**

**Use Python attribute to ensure a function is `only` loaded the `first` time it’s called**

# Note 4 Should we always use tf.data?

**For prototyping, feed dict can be faster and easier to write (pythonic)**

**tf.data is tricky to use when you have complicated preprocessing or multiple data sources**

**NLP data is normally just a sequence of integers. In this case, transferring the data over to GPU is pretty quick, so the speedup of tf.data isn't that large**