This repository and codes are largely based on and modified from deeplab-pytorch. I highly recommend visiters to visit the GitHub.

• Performance on Pascal VOC12 (Image size: 381, Batch size: 26)

• Performance on Pascal VOC12 (Image size: 321, Batch size: 12)

• Operating System:
  • Ubuntu 16.04.5
• CUDA:
  • CUDA V10.0.130
• Nvidia driver:
  • 418.87.01
• Python:
  • python 3.6.8
• Python package:
  • tqdm, opencv-python, pydensecrf,...
• Pytorch:
  • pytorch-gpu 1.4.0

Visual Object Classes Challenge 2012 (VOC2012)

• Semantic Boundaries Dataset and Benchmark

python main.py train --config-path configs/voc12ImageNet.yaml

python main.py test --config-path configs/voc12Test.yaml

python main.py crf --config-path configs/voc12Test.yaml --n-jobs 8

• Please try small batch size and image size
• Disable evaluate during training

kazuto1011/deeplab-pytorch

1. kazuto1011/deeplab-pytorch

2. L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy, A. L. Yuille. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE TPAMI, 2018.
   Project / Code / arXiv paper

3. H. Caesar, J. Uijlings, V. Ferrari. COCO-Stuff: Thing and Stuff Classes in Context. In CVPR, 2018.
   Project / arXiv paper

4. M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, A. Zisserman. The PASCAL Visual Object Classes (VOC) Challenge. IJCV, 2010.
   Project / Paper