# applied_deep_learning

**Repository Path**: wxzqs/applied_deep_learning

## Basic Information

- **Project Name**: applied_deep_learning
- **Description**: No description available
- **Primary Language**: Python
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2021-06-27
- **Last Updated**: 2021-06-27

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

## Introduction to applied deep learning

We will be using Python 3.x along with the following packages for the demos. The following packages will need to be installed:

**Windows Users:** Tensorflow only installs on python 3.5, the best way to aquire this is to download the appropriate Anaconda version. https://repo.continuum.io/archive/Anaconda3-4.2.0-Windows-x86_64.exe

1. TensorFlow
  * CPU version `pip install tensorflow`
  * GPU version `pip install tensorflow-gpu`
  * https://www.tensorflow.org/versions/r0.12/get_started/os_setup.html
2. Keras
  * `pip install keras`
  * https://keras.io/#installation
3. Gensim
  * `pip install gensim`
  * https://radimrehurek.com/gensim/install.html
4. Scikit-Image
  * `pip install scikit-image`
  * http://scikit-image.org/docs/dev/install.html
5. Scikit-Learn
  * `pip install scikit-learn`
  * http://scikit-learn.org/stable/install.html
6. h5py
  * http://docs.h5py.org/en/latest/build.html
7. PyEMD
  * `pip install pyemd`
  * https://github.com/wmayner/pyemd
  * May have to install Visual Studio 2015 build tools if you are on windows. http://landinghub.visualstudio.com/visual-cpp-build-tools

The packages above should take care of installing things like numpy and scipy. If you run into any problems where those need to be installed first then, install each of those first.

http://scipy.org/install.html

^__^ ^__^