segmentation resources

Github resources
https://github.com/meetshah1995/pytorch-semseg

https://github.com/bodokaiser/piwise


4. Seg-net Cambridge University
Use 16 layers of fully convolutional layers with batch normalizations for semantic segmentation based on caffe framework.

5. V net

6. cascaded FCN
https://github.com/IBBM/Cascaded-FCN

7. Deeplab
http://liangchiehchen.com/projects/DeepLab.html

8. PSPNet
https://github.com/hszhao/PSPNet
9. E net
10. Microscopy image browser
http://mib.helsinki.fi/downloads.html
11.refinenet
https://github.com/guosheng/refinenet
12. recognet
http://cs231n.stanford.edu/reports/2016/pdfs/326_Report.pdf

Deepmask (Facebook)
13. MS-DNet,  UC Berkeley
http://docs.wixstatic.com/ugd/cc66e4_bb1cd44c5f354517bb3f7b8c1db45cc4.pdf
http://www.pnas.org/content/115/2/254
14. Mask-RCNN

15. facebook AI research Detectron

16. detectorch
https://github.com/ignacio-rocco/detectorch



https://github.com/imatge-upc


Resources

https://handong1587.github.io/deep_learning/2015/10/09/segmentation.html#u-net

http://brohrer.github.io/how_convolutional_neural_networks_work.html

http://www.cs.ox.ac.uk/people/nando.defreitas/machinelearning/
http://www.andrewjanowczyk.com/



https://gist.github.com/shelhamer/80667189b218ad570e82#file-readme-md

https://groups.google.com/forum/#!topic/caffe-users/3dxyJL-DpJc

https://github.com/jocicmarko/ultrasound-nerve-segmentation
https://github.com/warmspringwinds/tf-image-segmentation



- U-Net: Convolutional Networks for Biomedical Image Segmentation + http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net/ + https://github.com/dmlc/mxnet/issues/1514 + https://github.com/orobix/retina-unet + https://github.com/fvisin/reseg + https://github.com/yulequan/melanoma-recognition + http://www.andrewjanowczyk.com/use-case-1-nuclei-segmentation/ + https://github.com/junyanz/MCILBoost
https://github.com/ankurhanda/tf-unet

https://github.com/martinkersner/train-CRF-RNN
http://stackoverflow.com/questions/39428481/unknown-layer-type-crop-in-caffe-for-windows


https://groups.google.com/forum/#!topic/caffe-users/cN7ZWepXfkc

https://github.com/torrvision/crfasrnn


https://github.com/krrish94/DeepLearningResources


http://grammars.grlmc.com/DeepLearn2017/schedule/


Deploy caffemodel for segmentation


https://github.com/kolesman/SEC
How to deploy


https://github.com/ankurhanda/tf-unet
https://github.com/zizhaozhang/unet-tensorflow-keras



caffe train --solver=$solver_file 2>&1 | tee log.txt
using this code will automatically save the log.txt for plotting loss



Udacity
https://www.udacity.com/course/deep-learning--ud730
youtube collections
https://www.analyticsvidhya.com/blog/2016/12/21-deep-learning-videos-tutorials-courses-on-youtube-from-2016/


http://adilmoujahid.com/posts/2016/06/introduction-deep-learning-python-caffe/



How to assemble image pair for segmentation for training using lmdb and hdf5

1. lmdb:DIGITS is easy
but limited to 8 bit or RGB png or jpg files

2. hdf5:
https://stackoverflow.com/documentation/caffe/5344/prepare-data-for-training#t=201706122035441079419



lmdb on segnet iffuse
https://github.com/alexgkendall/caffe-segnet/issues/8



Calculation of dice coefficient and Jaccard index
https://github.com/HGGM-LIM/limtools



data curation for coco like annotation
pycococreator


FCIS
https://www.slideshare.net/ssuser70baac/fcis-fully-instanceaware-semantic-segmentation




1. check if cuda is available
torch.cuda.is_available() should return true if cuda is installed.




Comments