{"id":13934951,"url":"https://github.com/ageron/tensorflow-safari-course","last_synced_at":"2025-07-04T04:36:55.326Z","repository":{"id":20297165,"uuid":"88989974","full_name":"ageron/tensorflow-safari-course","owner":"ageron","description":"⛔️ DEPRECATED — Exercises and solutions to accompany my Safari course introducing TensorFlow.","archived":false,"fork":false,"pushed_at":"2023-10-03T23:44:09.000Z","size":2558,"stargazers_count":175,"open_issues_count":2,"forks_count":119,"subscribers_count":19,"default_branch":"main","last_synced_at":"2025-04-02T11:07:23.941Z","etag":null,"topics":["archived"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ageron.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null}},"created_at":"2017-04-21T14:04:08.000Z","updated_at":"2025-01-24T17:40:46.000Z","dependencies_parsed_at":"2024-04-17T23:57:01.705Z","dependency_job_id":"84822c09-22f1-42e1-b361-ba31507d678a","html_url":"https://github.com/ageron/tensorflow-safari-course","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ageron%2Ftensorflow-safari-course","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ageron%2Ftensorflow-safari-course/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ageron%2Ftensorflow-safari-course/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ageron%2Ftensorflow-safari-course/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ageron","download_url":"https://codeload.github.com/ageron/tensorflow-safari-course/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248045231,"owners_count":21038553,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["archived"],"created_at":"2024-08-07T23:01:19.638Z","updated_at":"2025-04-09T13:06:35.295Z","avatar_url":"https://github.com/ageron.png","language":"Jupyter Notebook","funding_links":[],"categories":["Jupyter Notebook"],"sub_categories":[],"readme":"# ⛔️ DEPRECATED\n\n**This project is no longer supported, please consider using https://github.com/ageron/tf2_course instead.**\n\nIntroduction to TensorFlow\n==========================\n\nThis project accompanies my **Introduction to TensorFlow** live online trainings ([April 27-28](https://www.safaribooksonline.com/live-training/courses/introduction-to-tensorflow/0636920079460/), [June 21-22](https://www.safaribooksonline.com/live-training/courses/introduction-to-tensorflow/0636920073918/), [September 13-14](https://www.safaribooksonline.com/live-training/courses/introduction-to-tensorflow/0636920079521),  [December 13-14](https://www.safaribooksonline.com/live-training/courses/introduction-to-tensorflow/0636920079583/) 2017). It contains the exercises and their solutions, in the form of [Jupyter](http://jupyter.org/) notebooks.\n\nDuring the course itself, a URL will be provided for running the notebooks. You can participate in the course without installing anything local. If you prefer to work on a local installation, please follow the installation instructions below.\n\n[![book](https://raw.githubusercontent.com/ageron/tensorflow-safari-course/master/images/intro_to_tf_course.png)](https://www.safaribooksonline.com/live-training/courses/introduction-to-tensorflow/0636920079460/)\n\nIf you are looking for the code accompanying my O'Reilly book, [Hands-on Machine Learning with Scikit-Learn and TensorFlow](http://shop.oreilly.com/product/0636920052289.do), visit this GitHub project: [handson-ml](https://github.com/ageron/handson-ml).\n\n# Installation\n\nFirst, you will need to install [git](https://git-scm.com/), if you don't have it already.\n\nNext, clone this repository by opening a terminal and typing the following commands:\n\n    $ cd $HOME  # or any other development directory you prefer\n    $ git clone https://github.com/ageron/tensorflow-safari-course.git\n    $ cd tensorflow-safari-course\n\nIf you are familiar with Python and you know how to install Python libraries, go ahead and install NumPy, Matplotlib, Jupyter and TensorFlow (see `requirements.txt` for details), and jump to the [Starting Jupyter](#starting-jupyter) section. If you need detailed instructions, read on.\n\nYou obviously need Python. Python 2 is already preinstalled on most systems nowadays, and sometimes even Python 3. You can check which version(s) you have by typing the following commands:\n\n    $ python --version   # for Python 2\n    $ python3 --version  # for Python 3\n\nAny Python 3 version should be fine, as well as Python 2.6 or 2.7. However, if you don't have Python 3, I recommend installing it (Python 2 should work, but it is deprecated so Python 3 is preferable). To do so, you have several options: on Windows or MacOSX, you can just download it from [python.org](https://www.python.org/downloads/). On MacOSX, you can alternatively use [MacPorts](https://www.macports.org/) or [Homebrew](https://brew.sh/). On Linux, unless you know what you are doing, you should use your system's packaging system. For example, on Debian or Ubuntu, type:\n\n    $ sudo apt-get update\n    $ sudo apt-get install python3\n\nAnother option is to download and install [Anaconda](https://www.continuum.io/downloads). This is a package that includes both Python and many scientific libraries. You should prefer the Python 3 version.\n\n## Using Anaconda\nIf you chose to install Anaconda, you can optionally create an isolated Python environment dedicated to this course. This is recommended as it makes it possible to have a different environment for each project (e.g. one for this course), with potentially different libraries and library versions:\n\n    $ conda create -n tfintro python=3.5 anaconda\n    $ source activate tfintro\n\nThis creates a fresh Python 3.5 environment called `tfintro`, and it activates it. This environment contains all the scientific libraries that come with Anaconda. This includes all the libraries we will need (NumPy, Matplotlib and Jupyter), except for TensorFlow, so let's install it:\n\n    $ conda install -n tfintro -c conda-forge tensorflow=1.4.0\n\nThis installs TensorFlow 1.4.0 in the `tfintro` environment (fetching it from the `conda-forge` repository). If you chose not to create a `tfintro` environment, then just remove the `-n tfintro` option.\n\nYou are all set! Next, jump to the [Starting Jupyter](#starting-jupyter) section.\n\n## Using pip \nIf you are not using Anaconda, you need to install several scientific Python libraries that are necessary for this course: NumPy, Jupyter, Matplotlib and TensorFlow. For this, you can either use Python's integrated packaging system, pip, or you may prefer to use your system's own packaging system (if available, e.g. on Linux, or on MacOSX when using MacPorts or Homebrew). The advantage of using pip is that it is easy to create multiple isolated Python environments with different libraries and different library versions (e.g. one environment for each project). The advantage of using your system's packaging system is that there is less risk of having conflicts between the Python libraries versions and your system's other packages. Since I have many projects with different library requirements, I prefer to use pip with isolated environments.\n\nThese are the commands you need to type in a terminal if you want to use pip to install the required libraries. Note: in all the following commands, if you chose to use Python 2 rather than Python 3, you must replace `pip3` with `pip`, and `python3` with `python`.\n\nFirst you need to make sure you have the latest version of pip installed:\n\n    $ pip3 install --user --upgrade pip\n\nThe `--user` option will install the latest version of pip only for the current user. If you prefer to install it system wide (i.e. for all users), you must have administrator rights (e.g. use `sudo pip3` instead of `pip3` on Linux), and you should remove the `--user` option. The same is true of the command below that uses the `--user` option.\n\nNext, you can optionally create an isolated environment. As explained above, this is recommended as it makes it possible to have a different environment for each project (e.g. one for this course), with potentially very different libraries, and different versions:\n\n    $ pip3 install --user --upgrade virtualenv\n    $ virtualenv -p `which python3` env\n\nThis creates a new directory called `env` in the current directory, containing an isolated Python environment using Python 3. If you have multiple versions of Python 3 installed on your system, you can replace \\``which python3`\\` with the path to the Python executable you prefer to use.\n\nNow you want to activate this environment. You will need to run this command every time you want to use it.\n\n    $ source ./env/bin/activate\n\nNext, use pip to install the required python packages. If you are not using virtualenv, you should add the `--user` option (or else you will probably need administrator rights, e.g. using `sudo pip3` instead of `pip3` on Linux).\n\n    $ pip3 install --upgrade -r requirements.txt\n\nGreat! You're all set, you just need to start Jupyter now.\n\n## Starting Jupyter\nTo start Jupyter, simply type:\n\n    $ jupyter notebook\n\nThis should open up your browser, and you should see Jupyter's tree view, with the contents of the current directory. If your browser does not open automatically, visit [localhost:8888](http://localhost:8888/tree).\n\nNext, just click on any `*.ipynb` to open a Jupyter notebook.\n\nThat's it! Now, have fun learning TensorFlow!\n\n## Using Docker\n\nThere is a docker image available for this course: esztiorm/0636920073925\n\nIf you wish to create your own image using the Dockerfile, please note that the path \"tmp/data\" should be changed to \"/home/jovyan/tmp/data\" in notebooks 8 through 11.\n\n`mnist = input_data.read_data_sets(\"/home/jovyan/tmp/data/\")`\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fageron%2Ftensorflow-safari-course","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fageron%2Ftensorflow-safari-course","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fageron%2Ftensorflow-safari-course/lists"}