Skip to main content

Code of the master thesis

Project description

Master Thesis

Allows reproduction of results in my master thesis.

Downloads License Python versions

The package supports testing and evaluating SSD and Bayesian SSD. The results can be visualised.

Installation

Please install python header files of your Python version. Those are needed to compile the pycocotools with Cython upon installation.

pip install twomartens.masterthesis
pip install 'git+https://github.com/philferriere/cocoapi.git#egg=pycocotools&subdirectory=PythonAPI'

The second line is important as Git dependencies cannot be specified in the setup.py file.

Please refer to GPU support for instructions on installing the non-Python dependencies for tensorflow.

Type the following to create the configuration file and to see the options:

tm-masterthesis config list

Especially the paths have to be set to the correct values.

Usage example

tm-masterthesis --help

Lists all available commands. As most commands are nested, it is advisable to request the help at different nesting levels.

tm-masterthesis config {get,set,list}

Allows for the modification and retrieval of the configuration values.

tm-masterthesis test {ssd,bayesian_ssd} iteration train_iteration

Tests the selected network, using iteration as identifier for the test run and train_iteration as identifier for the training iteration. If the config parameter ssd_test_pretrained is True then the training iteration is not relevant.

tm-masterthesis evaluate {ssd,bayesian_ssd} iteration

Runs the evaluation process using the test results identified by iteration, evaluation results are saved under iteration under the evaluation path.

tm-masterthesis visualise_metrics {ssd,bayesian_ssd} iteration

Uses the evaluation results stored under iteration and visualises it. The score JSON and the figure images are stored under iteration in a visualise folder under the output path.

There are more commands but the rest can be very tightly linked to requirements in the master thesis and might therefore not be of interest generally.

Development setup

Clone the repository locally. Then execute the following commands inside the repository:

git submodule init
git submodule update
pip install -e .
pip install 'git+https://github.com/philferriere/cocoapi.git#egg=pycocotools&subdirectory=PythonAPI'

Release History

  • 0.3.0
    • added cython dependency and information about required python header files
  • 0.2.0
    • added python 3.8 classifier
  • 0.1.0
    • first release

Meta

Jim Martens – @2martensgithub@2martens.de

Distributed under the Apache 2.0 license. See LICENSE for more information. The package contains the ssd_keras implementation of Pierluigi Ferrari.

https://github.com/2martens/

Contributing

  1. Fork it (https://github.com/2martens/masterthesis/fork)
  2. Create your feature branch (git checkout -b feature/fooBar)
  3. Commit your changes (git commit -am 'Add some fooBar')
  4. Push to the branch (git push origin feature/fooBar)
  5. Create a new Pull Request

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for twomartens.masterthesis, version 0.3.0
Filename, size File type Python version Upload date Hashes
Filename, size twomartens.masterthesis-0.3.0-py3-none-any.whl (196.0 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size twomartens.masterthesis-0.3.0.tar.gz (160.1 kB) File type Source Python version None Upload date Hashes View

Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page