yukangwang / deepflux Goto Github PK
View Code? Open in Web Editor NEWDeepFlux for Skeletons in the wild (CVPR 2019 & IJCV 2020)
License: Other
DeepFlux for Skeletons in the wild (CVPR 2019 & IJCV 2020)
License: Other
Hi, I would train with my own custom datasets. What software/tool can I use to label them?
Thanks!
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?
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'
Can i train this to detect skeleton of another objects like drones or something?
Dear Wang, can you provide the data for PR-curves?
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.
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
.
Here is a topic of reproducing deepflux, sunsmarterjie/SDL-Skeleton#8, could you give some advices?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.