s-gupta / rcnn-depth Goto Github PK
View Code? Open in Web Editor NEWLearning Rich Features from RGB-D Images for Object Detection and Segmentation
License: BSD 2-Clause "Simplified" License
Learning Rich Features from RGB-D Images for Object Detection and Segmentation
License: BSD 2-Clause "Simplified" License
I followed the steps in this issue: #2, and got to running the demo() command. However, when I run it, I get the following output
demo();
runname =
release
Time taken for computing ng at scale 1: 8.929.
Time taken for computing ng at scale 2: 4.930.
Invalid MEX-file
'/home/belov/rcnn-depth/eccv14-code/structured-edges/private/edgesDetectMex.mexa64': dlopen:
cannot load any more object with static TLS
Error in edgesDetect (line 68)
if(nargout<4), [E,inds] = edgesDetectMex(model,I,chnsReg,chnsSim);
Error in edgesDetect (line 46)
if(nargout<4), [E1,~,inds{i}]=edgesDetect(I1,model,ng1);
Error in getAllCues (line 23)
Es = edgesDetect(Iin, model, zeros([size(Iin(:,:,1)), 0]));
Error in detectEdge (line 17)
cues = getAllCues(Iin, Din, C, colorModel, opts.rgbd3opts.vars, cacheFile);
Error in run_all (line 12)
[E, Es, O] = detectEdge(I, D, [], C, model, sc, [], []);
Error in demo (line 6)
run_all(I, D, RD, C, out_file);
I looked up issues regarding static TLS errors, and they were caused by a bug that should have been fixed in the latest release (I am running R2014b).
Hi I'm new to Caffe and deep learning. As stated here I'd like to use all the cores on my machine to achieve faster performance. I'm running the code on HP Envy 15t-j100 (4 real cores, 8 virtual cores).
I want to know which part can be done in parallel? and also I want to know how I should go about this multi-threading?!
Can you provide me with some resources?
Hello, following the steps in Readme and when running demo.m this problem arises:
runname =
release
Time taken for computing ng at scale 1: 5.525.
Time taken for computing ng at scale 2: 2.891.
Undefined function 'mex_contour_sides' for input arguments of type 'double'.
Error in contours2OWT>fit_contour (line 188)
[skel, labels, is_v, is_e, assign, vertices, edges, ...
Error in contours2OWT>create_finest_partition (line 43)
contours = fit_contour(double(ws_bw));
Error in contours2OWT (line 25)
ws_wt = create_finest_partition(pb_cont, pb_ori);
Error in contours_to_ucm>img2ucm (line 87)
[owt2, superpixels] = contours2OWT(E, O);
Error in contours_to_ucm>img2ucm_scale (line 66)
[ucm2, times] = img2ucm(E, O, param.mult_Pb, param.sat_sPb, param.nvec, param.dthresh, param.ic_gamma);
Error in contours_to_ucm (line 47)
[ucms{s}, times] = img2ucm_scale(E{s}, O{s}, param);
Error in run_all (line 13)
[ucm2 ucms] = contours_to_ucm(I, sc, Es, O);
Error in demo (line 6)
run_all(I, D, RD, C, out_file);
I don't know where it is possible that the problem exists. How can I figure it out? Many thanks!
Hi,
I was going through the save_HHA code and I realize that to calculate the horizontal disparity you are using a fixed value 31000. I was wondering where this value comes from. I checked but I did not found the explanation for that. First I was thinking that it was a trick to obtain a value between 0 and 255, however, I realized that the maximum possible value of the disparity was 310, because you are forcing to be 100 the minimum value of pc(:,:,3). Is there any reason for this value?
I would appreciate if you can help with this doubt. @s-gupta
Best Regards,
Hi,
I tried to compile caffe, but it will always give error about "cv".
My platform is CUDA 8.0+Ubuntu 16.04+opencv 3.2.0, i searched internet and found results that nobody seems to compile successfully using opencv 3.2.0, i wonder if it is true? If so, what should i do?
Thanks!
mex_contour_sides.cpp
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1277) : error C3771:
'resize' : friend declaration cannot be found in the nearest namespace scope
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1610) : see
reference to class template instantiation 'math::matrices::matrix<T,Syn>' being compiled
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1277) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1277) : error C2460:
'math::matrices::resize' : uses 'math::matrices::matrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1277) : error C2433:
'math::matrices::resize' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1277) : error C2365:
'math::matrices::resize' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1280) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1282) : error C3771:
'resize' : friend declaration cannot be found in the nearest namespace scope
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1282) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1282) : error C2460:
'math::matrices::resize' : uses 'math::matrices::matrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1282) : error C2433:
'math::matrices::resize' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1282) : error C2365:
'math::matrices::resize' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1286) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1292) : error C3771:
'resize' : friend declaration cannot be found in the nearest namespace scope
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1292) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1292) : error C2460:
'math::matrices::resize' : uses 'math::matrices::matrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1292) : error C2433:
'math::matrices::resize' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1292) : error C2365:
'math::matrices::resize' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1296) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1298) : error C3771:
'resize' : friend declaration cannot be found in the nearest namespace scope
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1298) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1298) : error C2460:
'math::matrices::resize' : uses 'math::matrices::matrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1298) : error C2433:
'math::matrices::resize' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1298) : error C2365:
'math::matrices::resize' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1303) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1310) : error C3771:
'resize' : friend declaration cannot be found in the nearest namespace scope
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1310) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1310) : error C2460:
'math::matrices::resize' : uses 'math::matrices::matrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1310) : error C2433:
'math::matrices::resize' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1310) : error C2365:
'math::matrices::resize' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1313) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1315) : error C3771:
'resize' : friend declaration cannot be found in the nearest namespace scope
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1315) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1315) : error C2460:
'math::matrices::resize' : uses 'math::matrices::matrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1315) : error C2433:
'math::matrices::resize' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1315) : error C2365:
'math::matrices::resize' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/matrix.hh(1319) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(903) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(1638) : see
reference to class template instantiation 'math::matrices::cmatrix<T,Syn>' being compiled
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(903) : error C2460:
'math::matrices::+' : uses 'math::matrices::cmatrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(903) : error C2433:
'math::matrices::+' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(903) : error C2365:
'math::matrices::operator +' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(903) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(904) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(904) : error C2460:
'math::matrices::-' : uses 'math::matrices::cmatrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(904) : error C2433:
'math::matrices::-' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(904) : error C2365:
'math::matrices::operator -' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(904) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(908) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(908) : error C2460:
'math::matrices::+' : uses 'math::matrices::cmatrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(908) : error C2433:
'math::matrices::+' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(908) : error C2365:
'math::matrices::operator +' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(908) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(909) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(909) : error C2460:
'math::matrices::-' : uses 'math::matrices::cmatrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(909) : error C2433:
'math::matrices::-' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(909) : error C2365:
'math::matrices::operator -' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(909) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(917) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(917) : error C2460:
'math::matrices::+' : uses 'math::matrices::cmatrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(917) : error C2433:
'math::matrices::+' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(917) : error C2365:
'math::matrices::operator +' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(917) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(919) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(919) : error C2460:
'math::matrices::-' : uses 'math::matrices::cmatrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(919) : error C2433:
'math::matrices::-' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(919) : error C2365:
'math::matrices::operator -' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(919) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(926) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(926) : error C2460:
'math::matrices::+' : uses 'math::matrices::cmatrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(926) : error C2433:
'math::matrices::+' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(926) : error C2365:
'math::matrices::operator +' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(926) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(928) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(928) : error C2460:
'math::matrices::-' : uses 'math::matrices::cmatrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(928) : error C2433:
'math::matrices::-' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(928) : error C2365:
'math::matrices::operator -' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(928) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(938) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(938) : error C2460:
'math::matrices::+' : uses 'math::matrices::cmatrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(938) : error C2433:
'math::matrices::+' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(938) : error C2365:
'math::matrices::operator +' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(938) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(940) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(940) : error C2460:
'math::matrices::-' : uses 'math::matrices::cmatrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(940) : error C2433:
'math::matrices::-' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(940) : error C2365:
'math::matrices::operator -' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(940) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(947) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(947) : error C2460:
'math::matrices::+' : uses 'math::matrices::cmatrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(947) : error C2433:
'math::matrices::+' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(947) : error C2365:
'math::matrices::operator +' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(947) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(949) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(949) : error C2460:
'math::matrices::-' : uses 'math::matrices::cmatrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(949) : error C2433:
'math::matrices::-' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(949) : error C2365:
'math::matrices::operator -' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(949) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(959) : error C2143:
syntax error : missing ';' before '<'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(959) : error C2460:
'math::matrices::+' : uses 'math::matrices::cmatrix<T,Syn>', which is being defined
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(959) : error C2433:
'math::matrices::+' : 'friend' not permitted on data declarations
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(959) : error C2365:
'math::matrices::operator +' : redefinition; previous definition was 'function'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(959) : error C2238:
unexpected token(s) preceding ';'
E:\R-cnn\eccv14-code\mcg\src_windows\external\BSR\include\math/matrices/cmatrix.hh(959) : fatal error
C1003: error count exceeds 100; stopping compilation
出错 mcg_build (line 102)
eval(['mex ' fullfile(mcg_root_dir, 'src_windows', 'bsr', 'mex_contour_sides.cpp') ' -outdir '
fullfile(mcg_root_dir, 'lib'),...
Is there a script to run object detection on all the images and evaluate with the ground truth? It would be great if you could tell me any other parameters used (like thresholds) to obtain the results in the paper.
Hello,
Tried to launch demo. The next error has appeared.
"Error using edgesDetect (line 61)
Not enough input arguments.
Error in edgesDemo (line 25)
tic, E=edgesDetect(I,model); toc"
So, edgesDetect which you use in edgesDemo requires 3 arguments "I,model, ng", and in edgesDemo this function called with only 2 arguments "tic, E=edgesDetect(I,model); toc". What have to be in place of "ng", third input?
Thank you in advance.
Is it possible to save the groundTruth files as pngs? I unfortunately don't have matlab.
Hey! I am very interested about your code about instance segmentation or semantic segmentation. How can Iget these parts?
when I run 'jobName = 'test_edge_model'; script_edges;' in matlab the following is like :
(000 / 000 / 100)
***(000 / 000 / 100)
***(000 / 000 / 100)
***(000 / 000 / 100)
***(000 / 000 / 100)
***(000 / 000 / 100)
***(000 / 000 / 100)
********(000 / 000 / 100)
I find the code is error in 'collectJob.m' file, it always drop out of the 'try catch ' and never stop.
'. It can't load(fullfile(jobDir, sprintf('output-%03d.mat', i)), 'jobDone', 'jobMine', 'jobError'), there is no 'output-x.mat' int the jobDir.
The same proble when I run 'jobName = 'edges_to_ucms'; script_regions;
' in matlab. Could you tell me why?
Undefined function 'contours_to_ucm' for input arguments of type 'cell'.
Error in run_all (line 13)
[ucm2, ucms, elapsed_time] = contours_to_ucm(I, sc, Es, O);
Error in demo (line 6)
run_all(I, D, RD, C, out_file);
anyone can fix this?
Hi, thank you so much for sharing the code!
When I tried to download data from
http://www.cs.berkeley.edu/~sgupta/eccv14/eccv14-data.tgz ,
I cannot connect to the server.
The same thing happened to the pretrained models.
How can I solve it?
Thank you !
I am trying to test on a couple of examples from the NYU set.
I add the line test_data.imlist = test_data.imlist(1:2);
after
test_data = struct('dataType', 'test', 'imlist', {getImageSet('test')}, ...
'image_dir', fullfile(c.dataDir, 'images', filesep()), ...
'dep_dir', fullfile(c.dataDir, 'depth', filesep()), ...
'ground_truth_dir', fullfile(c.benchmarkGtDir, filesep()), 'ext', 'png', ...
'res_dir', fullfile(p.contours_model_dir, 'test', 'modelNyuRgbd-3'));
in script_edges.m and then run at the prompt:
clear; jobName = 'test_edge_model'; script_edges;
But this runs for a really long time inspite of being just two images, and I have to eventually use a control+c to end it.
What am I missing?
Hello, I am on Rama Chellappa's team and I am trying to run your code however whenever I run demo(); it gives me an error that tells me it is out of memory.
after it gives me the time for hole filling it says:
Out of memory. Type HELP MEMORY for your options.
Error in compute_base_features (line181)
tmp = common_perimeters+common_perimeters';
...
Is there anyway to optimize the code so that I don't get this error?
I am running it on a virtual box with windows 7 as host and ubuntu 14.04 as guest using ~5G ram and 64 G hard drive.
When I try to run rcnn_build();
I get the following errors:
> In rcnn_build (line 8)
Error using mex
/tmp/mex_7347092241600_14443/tron.o: In function `TRON::trcg(double, double*, double*, double*)':
tron.cpp:(.text+0x1ed): undefined reference to `dnrm2_'
tron.cpp:(.text+0x20e): undefined reference to `ddot_'
tron.cpp:(.text+0x242): undefined reference to `dnrm2_'
tron.cpp:(.text+0x280): undefined reference to `ddot_'
tron.cpp:(.text+0x2a7): undefined reference to `daxpy_'
tron.cpp:(.text+0x2b6): undefined reference to `dnrm2_'
tron.cpp:(.text+0x316): undefined reference to `daxpy_'
tron.cpp:(.text+0x32a): undefined reference to `ddot_'
tron.cpp:(.text+0x343): undefined reference to `ddot_'
tron.cpp:(.text+0x35c): undefined reference to `ddot_'
tron.cpp:(.text+0x413): undefined reference to `daxpy_'
tron.cpp:(.text+0x444): undefined reference to `daxpy_'
tron.cpp:(.text+0x473): undefined reference to `daxpy_'
tron.cpp:(.text+0x487): undefined reference to `ddot_'
tron.cpp:(.text+0x4a8): undefined reference to `dscal_'
tron.cpp:(.text+0x4c0): undefined reference to `daxpy_'
/tmp/mex_7347092241600_14443/tron.o: In function `TRON::tron(double*)':
tron.cpp:(.text+0x652): undefined reference to `dnrm2_'
tron.cpp:(.text+0x6de): undefined reference to `daxpy_'
tron.cpp:(.text+0x6f3): undefined reference to `ddot_'
tron.cpp:(.text+0x710): undefined reference to `ddot_'
tron.cpp:(.text+0x758): undefined reference to `dnrm2_'
tron.cpp:(.text+0x94b): undefined reference to `dnrm2_'
collect2: error: ld returned 1 exit status
Error in rcnn_build (line 8)
mex -outdir . ...
All of the other toolboxes compile fine, and every step up to this point was fine. Any idea what's going on here?
Hi,
I have prepared my data set which contains RGBD 4 channels. I find that the depth image is of uint16 type which leads to that pixel value range in my depth image is from 1 to 2^16 which is different from the range of RGB channel (uint8) which is from 1 to 2^8.
I rescale the depth image range from( 1 to 2^16) to (1 to 2^8) by using matlab function "im2uint8" to make sure that all the 4 channels are in the same scale.
Just want to double check that whether this is the correct way to deal with it?
Thanks!
I have been able to obtain object detections and now I would like to evaluate the detections as done in the paper. Could you tell me how I can obtain the APb and APr scores?
I tried running rcnn_build in the matlab terminal after following all directions in the readme. I got the following error:
Error using mex
/tmp/mex_17165510705607_10154/tron.o: In function TRON::trcg(double, double*, double*, double*)': tron.cpp:(.text+0x1d9): undefined reference to
dnrm2_'
tron.cpp:(.text+0x1fc): undefined reference to ddot_' tron.cpp:(.text+0x218): undefined reference to
dnrm2_'
tron.cpp:(.text+0x251): undefined reference to ddot_' tron.cpp:(.text+0x279): undefined reference to
daxpy_'
tron.cpp:(.text+0x289): undefined reference to dnrm2_' tron.cpp:(.text+0x2d8): undefined reference to
daxpy_'
tron.cpp:(.text+0x2ee): undefined reference to ddot_' tron.cpp:(.text+0x309): undefined reference to
ddot_'
tron.cpp:(.text+0x324): undefined reference to ddot_' tron.cpp:(.text+0x3c5): undefined reference to
daxpy_'
tron.cpp:(.text+0x3f5): undefined reference to daxpy_' tron.cpp:(.text+0x426): undefined reference to
daxpy_'
tron.cpp:(.text+0x43c): undefined reference to ddot_' tron.cpp:(.text+0x45f): undefined reference to
dscal_'
tron.cpp:(.text+0x479): undefined reference to daxpy_' /tmp/mex_17165510705607_10154/tron.o: In function
TRON::tron(double*)':
tron.cpp:(.text+0x585): undefined reference to dnrm2_' tron.cpp:(.text+0x799): undefined reference to
dnrm2_'
tron.cpp:(.text+0x924): undefined reference to daxpy_' tron.cpp:(.text+0x93a): undefined reference to
ddot_'
tron.cpp:(.text+0x959): undefined reference to ddot_' tron.cpp:(.text+0x9a6): undefined reference to
dnrm2_'
collect2: error: ld returned 1 exit status
How you calculate the depth image by the raw depth image? You have the code?
I am trying to run the demo on Matlab 2017a on Linux Mint 18.
First while trying to build Imagestack, by running: cd eccv14-code/rgbdutils/imagestack/ , make all -j 16
I got the following error:
/home/mafonso/rcnn-depth/eccv14-code/rgbdutils/imagestack/matlab/joint_bilateral_mex.cpp: In function ‘ImageStack::Image fromMat(const mxArray*)’:
/home/mafonso/rcnn-depth/eccv14-code/rgbdutils/imagestack/matlab/joint_bilateral_mex.cpp:25:43: error: cannot convert ‘const size_t* {aka const long unsigned int*}’ to ‘const int*’ in initialization
const int dims = mxGetDimensions(mxfeat);
^
/home/mafonso/rcnn-depth/eccv14-code/rgbdutils/imagestack/matlab/joint_bilateral_mex.cpp: In function ‘mxArray toMat(ImageStack::Window)’:
/home/mafonso/rcnn-depth/eccv14-code/rgbdutils/imagestack/matlab/joint_bilateral_mex.cpp:55:72: error: cannot convert ‘int*’ to ‘const size_t* {aka const long unsigned int*}’ for argument ‘2’ to ‘mxArray* mxCreateNumericArray(size_t, const size_t*, mxClassID, mxComplexity)’
mxArray *mxfeat = mxCreateNumericArray(4, out, mxSINGLE_CLASS, mxREAL);
^
Makefile.common:113: recipe for target 'joint_bilateral_mex' failed
make: *** [joint_bilateral_mex] Error 255
I manually changed the typecasting like this: const int dims = (int)mxGetDimensions(mxfeat);
and then it got built. However, when I tried to run demo() I got the following error:
Unexpected unknown exception from MEX file..
Error in jointBilateral (line 16)
aa = joint_bilateral_mex(single(II), single(refII), sigma1, sigma2);
Error in computeNormals>filterItChopOffIS (line 65)
fFilt = jointBilateral(sp, f, 1, 1000);
Error in computeNormals (line 34)
AtA = filterItChopOffIS(cat(3, AtARaw, AtbRaw), superpixels, disparity, sigmaSupport, sigmaSuperpixel, sigmaDisparity);
Error in wrapperComputeNormals (line 39)
[N b] = computeNormals(X, Y, Z, disparity, missingMask, superpixels, sigmaSupport, sigmaDisparity, sigmaSuperpixel);
Error in yCues (line 11)
[N, b, pc] = wrapperComputeNormals(double(D)./100, false(size(D)), 3, s, C);
Error in getAllCues (line 14)
[y1, y2, y3, angl1, angl2] = yCues(D, C, 1);
Error in detectEdge (line 17)
cues = getAllCues(Iin, Din, C, colorModel, opts.rgbd3opts.vars, cacheFile);
Error in run_all (line 13)
[E, Es, O] = detectEdge(I, D, [], C, model, sc, [], []);
Error in demo (line 6)
run_all(I, D, RD, C, out_file);
Has anyone else faced this problem?
when I clone https://github.com/s-gupta/rcnn-depth.git eccv14-code,show this fatal,it seems like aux is reserved in Windows,What I can do for it ?
Hi, I'm trying to clone your repository(my OS is windows) and I ran into the following error.
$ git clone https://github.com/s-gupta/rcnn-depth.git eccv14-code
Cloning into 'eccv14-code'...
remote: Counting objects: 1144, done.
remote: Total 1144 (delta 0), reused 0 (delta 0), pack-reused 1144
Receiving objects: 100% (1144/1144), 2.41 MiB | 2.92 MiB/s, done.
Resolving deltas: 100% (428/428), done.
fatal: cannot create directory at 'mcg/src/aux': Invalid argument
warning: Clone succeeded, but checkout failed.
You can inspect what was checked out with 'git status'
and retry the checkout with 'git checkout -f HEAD'
After some searching, it turns out that aux is a reserved name for Windows which is why this error is popping out? Is there any way around this?
I've completed installing "rcnn-depth" according to help on Ubuntu 16.04.4 (gcc 5.4.0) except the step that I have to run rcnn_build();
witch resulted in error and as suggested in issue #2 I run make
in liblinear-1.94
and `liblinear-1.94/matlab' folders.
I've tried with both Matlab R2016b and Matlab R2012b (with editing matlab path in imagestack Makefile
and liblinear-1.94/matlab
Makefile
), both produce this error:
result of Matlab R2012b:
runname =
release
Invalid MEX-file
'/home/hojat/Documents/application/rcnn-depth/eccv14-code/rgbdutils/imagestack/matlab/joint_bilateral_mex.mexa64':
/usr/local/MATLAB/R2012b/bin/glnxa64/../../sys/os/glnxa64/libstdc++.so.6: version ``GLIBCXX_3.4.21' not found (required by
/home/hojat/Documents/application/rcnn-depth/eccv14-code/rgbdutils/imagestack/matlab/joint_bilateral_mex.mexa64)
Error in jointBilateral (line 16)
aa = joint_bilateral_mex(single(II), single(refII), sigma1, sigma2);
Error in computeNormals>filterItChopOffIS (line 65)
fFilt = jointBilateral(sp, f, 1, 1000);
Error in computeNormals (line 34)
AtA = filterItChopOffIS(cat(3, AtARaw, AtbRaw), superpixels, disparity,
sigmaSupport, sigmaSuperpixel, sigmaDisparity);
Error in wrapperComputeNormals (line 39)
[N b] = computeNormals(X, Y, Z, disparity, missingMask, superpixels, sigmaSupport,
sigmaDisparity, sigmaSuperpixel);
Error in yCues (line 11)
[N, b, pc] = wrapperComputeNormals(double(D)./100, false(size(D)), 3, s, C);
Error in getAllCues (line 12)
[y1, y2, y3, angl1, angl2] = yCues(D, C, 1);
Error in detectEdge (line 17)
cues = getAllCues(Iin, Din, C, colorModel, opts.rgbd3opts.vars, cacheFile);
Error in run_all (line 12)
[E, Es, O] = detectEdge(I, D, [], C, model, sc, [], []);
Error in demo (line 6)
run_all(I, D, RD, C, out_file);
what is GLIBCXX_3.4.21
? what is causing this error?
Hello,
I am working on my thesis about using RGB-D images for object detection, and I found your paper's link, but unfortunately, it is not found. Could you please fix the link? I really appriciate
can this use in people seg?
When I input 'make all' in the terminal as the READEME file. There was some errors(5), like:
src/Network.cpp:304:5: error: use of undeclared identifier 'close'
close(sock)
Respected Sir,
I have read your research paper "Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images".
I want to implement this code on my own data. I have kinect sensor.
I want to ask that how to get RGB-D image from kinect with color image and point clouds.?
I mean which tool is used to get it from kinect sensor.?
I am waiting for your response.
Regards
I can't download eccv14-external-data.tgz
When I use wget http://www.cs.berkeley.edu/~sgupta/eccv14/eccv14-external-data.tgz
It return:
ERROR 404:Not Found
I can't find getPointCloudFromZ.m . where is it??
I have a challenging object segmentation problem, with bad lighting, multiple shadows and objects (cows) of different colours.
I've been able so far to detect and correctly classify some instances of the class 'cow' using a different CNN algorithm, but I can't delineate between instances of it (i.e. tell 'this is where cow1 ends and cow2 begins'). Can rcnn-depth handle this problem (I don't have matlab installed on my computer, so I haven't tried it yet)?
What's the difference between depth image and rawdepth image? And what does the missingMask stand for?
I tried to run demo in matlab after follwing the directions in the readme (building toolboxes, mcg, rcnn) and get the following error:
runname =
release
Undefined function 'joint_bilateral_mex' for
input arguments of type 'single'.
Error in jointBilateral (line 16)
aa = joint_bilateral_mex(single(II),
single(refII), sigma1, sigma2);
Error in computeNormals>filterItChopOffIS (line
65)
fFilt = jointBilateral(sp, f, 1, 1000);
Error in computeNormals (line 34)
AtA = filterItChopOffIS(cat(3, AtARaw,
AtbRaw), superpixels, disparity,
sigmaSupport, sigmaSuperpixel,
sigmaDisparity);
Error in wrapperComputeNormals (line 39)
[N b] = computeNormals(X, Y, Z,
disparity, missingMask, superpixels,
sigmaSupport, sigmaDisparity,
sigmaSuperpixel);
Error in yCues (line 11)
[N, b, pc] =
wrapperComputeNormals(double(D)./100,
false(size(D)), 3, s, C);
Error in getAllCues (line 12)
[y1, y2, y3, angl1, angl2] = yCues(D, C, 1);
Error in detectEdge (line 17)
cues = getAllCues(Iin, Din, C, colorModel,
opts.rgbd3opts.vars, cacheFile);
Error in run_all (line 12)
[E, Es, O] = detectEdge(I, D, [], C, model,
sc, [], []);
Error in demo (line 6)
run_all(I, D, RD, C, out_file);
Hi:
Paper in the depth image to HHA image process is not detailed; can inform the detailed steps。
Looking forward to your reply.
When I run the edgeboxDemo for instance, I get this error
Error using edgesDetect (line 63)
Not enough input arguments.
Error in edgeBoxes>edgeBoxesImg (line 84)
model.opts.nms=0; [E,O]=edgesDetect(I,model);
Error in edgeBoxes (line 74)
if(~iscell(I)), bbs=edgeBoxesImg(I,model,o); else n=length(I);
Here's my fix:
if ~exist('ng', 'var'), ng = zeros([size(I(:,:,1)), 0]); end
Not sure that it's totally right, but it does make everything appear to work.
Hi,
is there a simple way to extract the bounding boxes that are used for the detection task? I've already found the function getGroundTruthBoxes(...)
and the file classMapping40.mat
but I haven't found the class mapping for the 20 classes you used for detection yet. Could you please give me a hint?
demo
runname =
release
Time taken for computing ng at scale 1: 5.574.
Time taken for computing ng at scale 2: 1.747.
Time for full_cands_from_hiers: 1.221
Time for hole_filling: 9.599
Time for compute_base_features: 17.843
Time for mex_fast_reduction: 1.835
Time for compute_full_features: 0.011
Time for cand2labels: 0.054
Time for depth features: 4.538
Undefined function or variable 'caffe'.
Error in rcnn_load_model (line 28)
caffe('init', rcnn_model.cnn.definition_file, rcnn_model.cnn.binary_file);
Error in run_all (line 41)
rcnn_model = rcnn_load_model(rcnn_model);
Error in demo (line 6)
run_all(I, D, RD, C, out_file);
I've installed and built everything
but when I run demo() in Matlab, it said function caffe('init',...) is undefined
I checked caffe/matlab/+caffe. the usage seems to be caffe_('...',...).
so I wonder if the version of caffe @s-gupta using is different with the current newest caffe, and what version should I use and download? plz
When I use the finetuning commands that print out to finetune the CNN,
'jobName = 'hha_cache_features'; I saw the script_detection.m file,there is a code ' the ' net_file = fullfile_ext(p.snapshot_dir, sprintf('nyud2_finetune_hha_iter_%d', snapshot), 'caffemodel'); ' but there is no nyud2_finetune_hha_iter_%d.caffemodel file in the cachedir/release/detection/dinetuning/snapshot dir. Is it a existing file or need to creat by my self?
I step by step according the Readme, but I did't creat any mat files in cachedir/release/output/regions, could you tell me which step do this? Because my cluster can noT adapt jobParallel, so I used for loop instead it to call some function, I think maybe some step I use a wrong funcion so that I didn't make the right outputs.
In addition, is caffe-0.999 version you use to run the rcnn?
Thank you for your answers!
Hi! @s-gupta, I just want to ask you when I run the demo() and find a error like that
Invalid MEX-file '/home/zz/graduate_2/rcnn-depth/eccv14-code/structured-edges/private/edgesDetectMex.mexa64': dlopen: cannot load any
more object with static TLS
How can I do to fix it?
When I run the saveHHA function to get my depth images turned into an HHA encoding, I get the message that getImage function could not be found. I tried looking through all of your repos but I couldn't find the function. Where are you getting getImage from? I thought about replacing it with imread instead but that doesn't give the necessary depth matrices. Can you tell me where you found the function?
@s-gupta hallo,perfessor .I meet some problem,and need your help sincerely.when I download the code,I can extract the files completly.I try on several computers,but it still does not work . I can not figure out it,could you help me?
and I still meet some other problem,is there lose some files? in the file "rcnn-depth-master/demo.m",
Whether the function file is not uploaded ?Need your help?How can I deal with this?
when I use 'git checkout e5cc609138a0bc4ce5177a67cf84952756d11b38' as the ReadMe.md indicates, I'm notified that "You are in 'detached HEAD' state.". Is that just Ok?
Error using mex
cc1plus: warning: /home/liuna/rcnn-depth/eccv14-code/mcg/src/aux: not a
directory
/home/liuna/rcnn-depth/eccv14-code/mcg/src/cands/mex_assess_one_sel.cpp:16:33:
fatal error: matlab_multiarray.hpp: No such file or directory
compilation terminated.
Error in mcg_build (line 64)
eval(['mex ''' build_file{ii} ''' -outdir ''' fullfile(mcg_root_dir, 'lib')
'''' include_str])
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.