/Deeplab-CNN

Primary LanguagePython

[PYTORCH] Deeplab

Introduction

Pytorch implementation of the model described in the paper DeepLab: Semantic resultss Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs paper.

Datasets:

I used 2 different datases: VOC2012 and VOCaugmented (VOC2007 + 2012) Statistics of datasets I used for experiments is shown below

Dataset #Classes #Train resultsss #Validation resultsss
VOC2012 20 5011 1449
VOCaugmented 20 1464 1449

Training

  • Using Valohai platform
  • Valohai platform overview graph

Experiments:

I trained models in Valohai platform using CSC Cluster. The model version control show in the picture. For each run Valohai save the results, export log, metadata and model to CSC Cloud storage

valohai

  • VOC2012 voc2012 loss
  • VOCaugmented vocaugmented loss

resultss

Some output predictions for experiments for each dataset are shown below:

  • VOC2012

  • VOCaugmented