Auto-tuning fails #34
Comments
|
Thanks for the detailed report. It seems that there are two different issues here. First, the failure of the Azure Kinect SDK to initialize. I googled the error message and got this, does this help? Second, the failure of BAD SLAM to load the calibration file. It is unclear to me why this fails. The content of the file looks fine, and since it fails in line 146, the program apparently also succeeds to open the file. However, it cannot parse the text for some reason. It should however be easy to debug this by inserting some debug output around here, for example output the content of |
|
Thanks @puzzlepaint. Regarding this, I've installed the SDK using provided Debian package. It's not possible to apply that change without building from source, right? I could not find why it cannot parse the Maybe I can decrease some parameters manually? But I don't know which ones to play with. Let me append the file here so you might suggest some tweaks. I have a GeForce RTX 2080 Ti btw. |
|
I don't think that it is necessary to modify the SDK. You could for example try to insert the suggested fix QLocale::setDefault(QLocale::C);
setlocale(LC_ALL, "C");here after creating the QApplication object, as it seems that the construction of QApplication performs the locale change that seems to cause this issue. It is surprising to me that the "too many resources requested" error happens for a GeForce RTX 2080 Ti. But it is expected that the test won't work, as they will not pick up the changed parameters from the auto tuning file (as indicated in the Readme). It should work in the actual application. If you want to fix the tests, you could try to insert the following: boost::filesystem::path program_dir = boost::filesystem::path(argv[0]).parent_path();
if (!CUDAAutoTuner::Instance().LoadParametersFile(
(program_dir / "resources" / "auto_tuning_result.txt").string().c_str())) {
LOG(WARNING) << "No auto-tuning file found -> using default parameters."
" GPU performance is thus probably slightly worse than it"
" could be.";
}in the test main function here (and probably |
|
It seems that your advice worked. Appreciate your help, @puzzlepaint. Also, the output is really promising. Thanks for open sourcing such a work! |
…ssue with the K4A SDK (GitHub issue #34)
I am trying to use the application with Azure Kinect through live input. After hassling with dependencies I am stuck at a point which I think not far from the the successful end. Here is the current state:
./badslamand select Azure K4A Live Input this is the error messagebadslam_testcan be seen in this link. (Since it was too long, I've linked the file)To do that I need a dataset, live input would not work as it is stated in the README. I've downloaded Cable1 from ETH3D SLAM benchmark. The autotune asks for
associated.txtcalibration.txtdepth(folder)rgb(folder). So I downloaded all ofcables_1_mono.zip, cables_1_stereo.zip, cables_1_rgbd.zip, cables_1_imu.zip, cables_1_raw.zipand combine the data in them to getassociated.txtcalibration.txtdepth(folder)rgb(folder).Then I run this command to auto tune.
python3 scripts/auto_tune_parameters.py ~/projects/badslam/build_RelWithDebInfo/applications/badslam/badslam ~/projects/cables_1 --sequential_ba --sequential_loop_detectionOutput is
It says it cannot read calibration file and dataset. I am not sure if there is a problem in calibration file. I've also checked permissions of file, it's fine. Here is the content of
calibration.txtI can provide more logs if needed. Thanks in advance!
The text was updated successfully, but these errors were encountered: