Giter Site home page Giter Site logo

yukangwang / deepflux Goto Github PK

View Code? Open in Web Editor NEW
51.0 5.0 17.0 2.4 MB

DeepFlux for Skeletons in the wild (CVPR 2019 & IJCV 2020)

License: Other

CMake 2.85% Makefile 0.67% Dockerfile 0.08% C++ 80.14% Cuda 5.72% MATLAB 0.90% Python 9.21% Shell 0.44%
skeletonization symmetry-detection

deepflux's People

Contributors

jianqiangwan avatar yukangwang avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar

deepflux's Issues

data labelling

Hi, I would train with my own custom datasets. What software/tool can I use to label them?

Thanks!

RuntimeError when running train.py

Hi, Thanks for the great work!

I ran into this error when I was trying to train scripts in my Ubuntu18.04 python3 environment, any idea why this happened? Thanks!

command: python3 train.py --gpu 0 --dataset sklarge --initmodel ../../models/VGG_ILSVRC_16_layers.caffemodel

Traceback (most recent call last):
File "train.py", line 283, in
write_net(args.dataset)
File "train.py", line 107, in write_net
net.sdcrop = crop(net.upsd, net.relu3_3)
File "/usr/lib/python3/dist-packages/caffe/coord_map.py", line 178, in crop
ax, a, b = coord_map_from_to(top_from, top_to)
File "/usr/lib/python3/dist-packages/caffe/coord_map.py", line 168, in coord_map_from_to
raise RuntimeError('Could not compute map between tops; are they '
RuntimeError: Could not compute map between tops; are they connected by spatial layers?

AttributeError: 'module' object has no attribute 'cv'

I have installed opencv3.4.3,when run the train.py i get the Traceback... Could you help me look it

Python 2.7.13 |Continuum Analytics, Inc.| (default, Dec 20 2016, 23:09:15)
[GCC 4.4.7 20120313 (Red Hat 4.4.7-1)] on linux2
Type "help", "copyright", "credits" or "license" for more information.
Anaconda is brought to you by Continuum Analytics.
Please check out: http://continuum.io/thanks and https://anaconda.org

import cv2
print cv2.version
3.4.3
exit()

Traceback (most recent call last):
File "train.py", line 279, in
train(args.initmodel, args.gpu)
File "train.py", line 258, in train
solver = caffe.AdamSolver('solver.prototxt')
File "/home/disk/yeler082/DeepFlux/examples/DeepFlux/pylayerUtils.py", line 46 , in reshape
self.image, self.flux, self.dilmask = self.loadsklarge(self.fnLst[self.idx]. split()[0],self.fnLst[self.idx].split()[1])
File "/home/disk/yeler082/DeepFlux/examples/DeepFlux/pylayerUtils.py", line 98 , in loadsklarge
dst, labels = cv2.distanceTransformWithLabels(rev, cv2.cv.CV_DIST_L2, cv2.cv .CV_DIST_MASK_PRECISE, labelType=cv2.DIST_LABEL_PIXEL)
AttributeError: 'module' object has no attribute 'cv'

custom detection

Can i train this to detect skeleton of another objects like drones or something?

PR-curve data

Dear Wang, can you provide the data for PR-curves?

About the aumentation.m file

Hi,
I really appreciate the great job, thanks for your sharing!
But I don't get the aumentation.m file . Could you please tell me the reason?
Thanks again.

Undefined variable $thr in eval_py.sh

In DeepFlux/examples/DeepFlux/evaluation/eval_py.sh, where python ../inference.py $deploy $model $gpu $imageDir/ $thr $dks $eks $detDir/ is executed, there isn't such variable defined as $thr. I think instead of $thr, it should be $lamda.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.