jswulff / pcaflow Goto Github PK
View Code? Open in Web Editor NEWLicense: Other
License: Other
Hi, Thank you for all your work !
I had ran the ./build.sh file and it turned out many warings. I choose to ignore this warnings and run the demo.py ,then it didn't work with the error below , can you give me some suggestion?Thank you !
root@desktop:/home/hh/pca# python demo.py /home/hh/pca/pcaflow Traceback (most recent call last): File "demo.py", line 3, in <module> from pcaflow import PCAFlow File "/home/hh/pca/pcaflow/PCAFlow.py", line 35, in <module> from solver.RobustQuadraticSolverCython import RobustQuadraticSolverCython as RobustQuadraticSolver ImportError: /home/hh/pca/pcaflow/solver/RobustQuadraticSolverCython.so: undefined symbol: dgetri_
Hi,
I am able to normally compile with build.sh. However, when running demo.py I am getting the following python error
Re-allocating matcher...
Traceback (most recent call last):
File "demo.py", line 46, in <module>
u,v = P.compute_flow()
File "/home/gustavo/pcaflow/pcaflow/PCAFlow.py", line 380, in compute_flow
**kwargs)
File "/home/gustavo/pcaflow/pcaflow/solver/EMSolver.py", line 364, in solve
inliers,H,shape_I_orig)
File "/home/gustavo/pcaflow/pcaflow/solver/EMSolver.py", line 493, in get_flow_GC
point_models)
File "/home/gustavo/pcaflow/pcaflow/solver/EMSolver.py", line 639, in _compute_unaries_color
G = mixture.GMM(n_components=nc,covariance_type='full').fit(P)
AttributeError: 'module' object has no attribute 'GMM'
Thank you so much for sharing your code.
When I run PCA_Layers, it returns 2 warnings:
~/anaconda3/envs/pca/lib/python2.7/site-packages/sklearn/utils/deprecation.py:77: DeprecationWarning: Function log_multivariate_normal_density is deprecated; The function log_multivariate_normal_density is deprecated in 0.18 and will be removed in 0.20.
warnings.warn(msg, category=DeprecationWarning)
~/anaconda3/envs/pca/lib/python2.7/site-packages/sklearn/utils/deprecation.py:58:
DeprecationWarning: Class GMM is deprecated; The class GMM is deprecated in 0.18 and will be removed in 0.20. Use class GaussianMixture instead.
warnings.warn(msg, category=DeprecationWarning)
Do these warning affect the output?
Thank you.
Hello,
Your code looks awesome! I'm trying to get it running on my machine, and I'm bumping into this error: not sure what I'm doing wrong?
On a Linux Ubuntu 16.04 machine, ran the build.sh script, appear to have prerequisites installed.
Running
python compute_flow.py -kitti -pcaflow image1.png image2.png output.flo
as shown:
(py2) anthony@aZ68MA-D2H-B3:/media/anthony/CA80455D8045515D/code-2tb/pcaflow$ python compute_flow.py -kitti -pcaflow image1.png image2.png output.flo
/media/anthony/CA80455D8045515D/code-2tb/pcaflow/pcaflow
*** LOADING PRESET pcaflow_kitti ***
[PARAMETERS MAIN]
NC: 500
SUBLAYER_NC: 200
SUBLAYER_lambda: 0.02
SUBLAYER_sigma: 0.95
debug: 0
em_additional_remove_outliers: 0
em_init_loc_weight: 0.4
features: libviso
features_clahe: 1
features_fast_limit: -1
features_libviso_bucket_size: 50
features_libviso_buckets_x: 8
features_libviso_buckets_y: 4
features_libviso_half_resolution: 0
features_libviso_match_binsize: 50
features_libviso_match_disp_tolerance: 1
features_libviso_match_radius: 200
features_libviso_multi_stage: 1
features_libviso_multiscale: 0
features_libviso_n_scales: 2
features_libviso_nms_n: 5
features_libviso_nms_tau: 25
features_libviso_outlier_disp_tolerance: 5
features_libviso_outlier_flow_tolerance: 7
features_libviso_refinement: 1
features_prune_border: 0.05
image_blur: 5
lambda: 0.4
model_color_n_mixtures: 1
model_factor_dist_to_median: 0.008
model_gamma: 350.0
model_gamma_c: 5.0
model_gamma_l: 6.5
model_gamma_warp: 1.0
model_sigma_w: 300.0
n_models: 1
remove_homography: 0
sigma: 0.55
Initializing matcher...
NC:
500
NC_MAX_PER:
250
WARNING: Image changed size. (0,0 => 435,1024).
Re-allocating matcher...
Traceback (most recent call last):
File "compute_flow.py", line 67, in <module>
main()
File "compute_flow.py", line 59, in main
u,v = P.compute_flow()
File "/media/anthony/CA80455D8045515D/code-2tb/pcaflow/pcaflow/PCAFlow.py", line 315, in compute_flow
kp1_,kp2_ = self.feature_matcher.get_features()
File "/media/anthony/CA80455D8045515D/code-2tb/pcaflow/pcaflow/features/FeatureMatcherLibviso.py", line 175, in get_features
feats_I1,feats_I2 = self.prune_second_stage(feats_I1.copy(),feats_I2.copy(),self.w,self.h)
File "/media/anthony/CA80455D8045515D/code-2tb/pcaflow/pcaflow/features/FeatureMatcherLibviso.py", line 198, in prune_second_stage
if not bin_occupied[b]:
IndexError: only integers, slices (`:`), ellipsis (`...`), numpy.newaxis (`None`) and integer or boolean arrays are valid indices
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.