Giter Club home page Giter Club logo

carnd-tensorflow-lab's Introduction

TensorFlow Neural Network Lab

Udacity - Self-Driving Car NanoDegree

notMNIST dataset samples

We've prepared a Jupyter notebook that will guide you through the process of creating a single layer neural network in TensorFlow.

Environment Set-up

Follow the set-up instruction for the Term 1 Starter Kit. Contained within are instructions for utilizing a Jupyter notebook within Docker; if you use Anaconda make sure to activate the environment first with

source activate {environment_name}

and then open the notebook with

jupyter notebook

The Lab

The notebook has 3 problems for you to solve:

  • Problem 1: Normalize the features
  • Problem 2: Use TensorFlow operations to create features, labels, weight, and biases tensors
  • Problem 3: Tune the learning rate, number of steps, and batch size for the best accuracy

This is a self-assessed lab. Compare your answers to the solutions here. If you have any difficulty completing the lab, Udacity provides a few services to answer any questions you might have.

Help

Remember that you can get assistance from mentors and fellow students in Student Hub or in Knowledge. You can also review the concepts from the previous lessons.

carnd-tensorflow-lab's People

Contributors

andrewpaster avatar baumanab avatar brok-bucholtz avatar citlaligm avatar dsilver829 avatar gawy avatar joshuacook avatar mvirgo avatar pejvan avatar seogyusik avatar sudkul avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

carnd-tensorflow-lab's Issues

Password for Jupyter

I am running from my local laptop (Ubuntu 16.4) and conda. When I start jupyter notebook from carnd-term1 environment it is asking for a password.

Anyone know what it is?

Thanks,

Matt

Latest docker image somehow has tensorflow 0.11

I'm going through the Intro To TensorFlow lab and the call to

global_variables_initializer()

fails as 0.11 is looking for initialize_all_variables()

I see that pull request #7 correctly made these changes and specified the updated version of tensorflow, but when I check the version that showed up in the docker image I just pulled today, this is the result:

tf.__version__
0.11.0

tf.global_variables_initializer() throws missing attribute error in Docker container

When running the lab.ipynb with the docker image(udacity/carnd-tensorflow-lab), tf.global_variables_initializer throws missing attribute error. However, replacing it with tf.initialize_all_variables works.
I see that the change was done with the following commit:
update TensorFlow Variable initialization function commit f9c4346

Does that mean the tensorflow version in the docker image is old and does not supports global_variables_initializer?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.