/keras_zoo

Keras implementation of Classification, Detection and Segmentation Networks

Primary LanguagePython

Keras implementation of Classification, Detection and Segmentation Networks

Introduction

This repo contains the code to train and evaluate state of the art classification, detection and segmentation methods in a unified Keras framework working with Theano and TensorFlow. Pretrained models are also supplied.

Available models

Classification

Detection

Segmentation

Available dataset wrappers

Classification

  • MIT dataset described in .
  • TT100K classsification dataset described in .
  • INRIA pedestrian dataset described in .
  • ImageNet dataset described in .
  • Pascal dataset described in .

Detection

  • TT100K detection dataset described in .
  • INRIA pedestrian dataset described in .

Segmentation

Installation

You need to install :

Run experiments

All the parameters of the experiment are defined at config/dataset.py where dataset.py is the name of the dataset to use. Configure this file according to you needs.

To train/test a model in Theano, use the command: THEANO_FLAGS='device=cuda0,floatX=float32,lib.cnmem=0.95' python train.py -c config/dataset.py -e expName where dataset is the name of the dataset you want to use and expName the name of the experiment.

To train/test a model in TensorFlow, use the command: CUDA_VISIBLE_DEVICES=0 python train.py -c config/dataset.py -e expName -s SharedPath -l LocalPath where dataset is the name of the dataset you want to use and expName the name of the experiment, SharedPath points to the folder in which the shared path is (same for LocalPath).

All the logs of the experiments are stored in the result folder of the experiment.

Authors

David Vázquez, Adriana Romero, Michal Drozdzal, Lluis Gomez

How to cite

TODO

  • Relaunch: Remember the number of the last epoch