Skip to content

ardaa/kerasml

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Keras Machine Learning Example (Identify Cats and Dogs)

N|Solid

Installation

This project requires TensorFlow to run.

Check if Python and Pip is installed

$ python -V  # or: python3 -V
$ pip -V     # or: pip3 -V

To install these packages on Ubuntu:

$ sudo apt-get install python-pip python-dev python-virtualenv   # for Python 2.7
$ sudo apt-get install python3-pip python3-dev python-virtualenv # for Python 3.n

We recommend using pip version 8.1 or higher. If using a release before version 8.1, upgrade pip:

$ sudo pip install -U pip

If not using Ubuntu and setuptools is installed, use easy_install to install pip:

$ easy_install -U pip

Create a directory for the virtual environment and choose a Python interpreter.

$ mkdir ~/tensorflow  # somewhere to work out of
$ cd ~/tensorflow
 # Choose one of the following Python environments for the ./venv directory:
$ virtualenv --system-site-packages venv            # Use python default (Python 2.7)
$ virtualenv --system-site-packages -p python3 venv # Use Python 3.n

Activate the Virtualenv environment. Use one of these shell-specific commands to activate the virtual environment:

 $ source ~/tensorflow/venv/bin/activate      # bash, sh, ksh, or zsh
 $ source ~/tensorflow/venv/bin/activate.csh  # csh or tcsh
 $ . ~/tensorflow/venv/bin/activate.fish      # fish
When the Virtualenv is activated, the shell prompt displays as (venv) $.

Upgrade pip in the virtual environment. Within the active virtual environment, upgrade pip:

(venv)$ pip install -U pip

You can install other Python packages within the virtual environment without affecting packages outside the virtualenv.

Install TensorFlow in the virtual environment.

Choose one of the available TensorFlow packages for installation:

tensorflow —Current release for CPU tensorflow-gpu —Current release with GPU support tf-nightly —Nightly build for CPU tf-nightly-gpu —Nightly build with GPU support Within an active Virtualenv environment, use pip to install the package:

$ pip install -U tensorflow

Use pip list to show the packages installed in the virtual environment. Validate the install and test the version:

(venv)$ python -c "import tensorflow as tf; print(tf.__version__)"

TensorFlow is now installed. Use the deactivate command to stop the Python virtual environment.

Install Keras

Install Keras from PyPI (recommended):

$ sudo pip install keras

Alternatively: install Keras from the GitHub source: First, clone Keras using git:

$ git clone https://github.com/keras-team/keras.git

Then, cd to the Keras folder and run the install command:

$ cd keras
$ sudo python setup.py install

Keras is now installed.

Clone this repository

Clone this repository and cd in it.

$ git clone https://github.com/ardaa/kerasml.git
$ cd kerasml

Usage

If you want to train the model:

$ python train.py

If you want to predict using the model: Add the directory of file that you want to predict in predict.py at line 52.

img_path = 'test1/1.jpg'  # Change here
# Load the image as a tensor
new_image = load_image(img_path)

Then run it

$ pythonw predict.py

Development

Want to contribute? Great!

Fork the repository, make your changes and make a pull request.

Todos

  • Make the image to be predicted selectable from bash
  • Improve the model to run faster.

License

MIT

About

Keras Machine Learning Image Classifier

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages