Skip to content
Omnisupervised Omnidirectional Semantic Segmentation
Python
Branch: master
Clone or download

Latest commit

Fetching latest commit…
Cannot retrieve the latest commit at this time.

Files

Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
trained
EntropyLoss.py
README.md
dataset.py
dataset_loader.py
drnet.py
erfnet_encoder_pretrained.pth.tar
erfnet_imagenet.py
erfnet_pspnet.py
erfnet_pspnet_scse.py
eval_color.py
figure_psv.jpg
iouEval.py
segment.py
transform.py

README.md

OOSS

Omnisupervised Omnidirectional Semantic Segmentation

Datasets

PASS Datast Panoramic Annular Semantic Segmentation Dataset with pixel-wise labels (400 images).

Chengyuan Dataset Panoramas captured with an instrumented vehicle (650 images).

Streetview Dataset Panoramas collected in different cities including New York, Beijing, Shanghai, Changsha, Hangzhou, Huddersfield, Madrid, Karlsruhe and Sydney.

Example segmentation

Codes

Training:

CUDA_VISIBLE_DEVICES=0,1,2,3
python3 segment.py
--basedir /home/kyang/Downloads/
--num-epochs 200
--batch-size 12
--savedir /erfpsp
--datasets 'MAP' 'IDD20K'
--num-samples 18000
--alpha 0
--beta 0
--model erfnet_pspnet

Evaluation:

python3 eval_color.py
--datadir /home/kyang/Downloads/Mapillary/
--subset val
--loadDir ./trained/
--loadWeights model_best.pth
--loadModel erfnet_pspnet.py
--basedir /home/kyang/Downloads/
--datasets 'MAP' 'IDD20K'
You can’t perform that action at this time.