antithing
antithing
[main.zip](https://github.com/aau-cns/mars_lib/files/12717890/main.zip) https://github.com/aau-cns/mars_lib/assets/11506730/9cc39c9f-4b73-4536-b2cb-dfbcf31a3c09 Thanks! Changes made (new main.cpp attached, as well as video). Not much improvement unfortunately. Lowering the measurement noise does help, but not enough to give a useable output....
Hi, thanks for getting back to me. This is using the current code, downloaded from git this morning. I have added `ALSOFT_LOGLEVEL=3`` to the preprocessor args, but i see the...
Okay! That gives me: ``` alrecord.exe -device "OpenAL Soft on Line In (Realtek Audio)" AL lib: (II) Initializing library v1.19.1-unknown UNKNOWN AL lib: (II) Supported backends: wasapi, dsound, winmm, null,...
Thank you! Pulling down the latest master just now and building gives me: ``` alrecord.exe -device "OpenAL Soft on Line In (Realtek Audio)" AL lib: (II) Initializing library v1.19.1-unknown UNKNOWN...
I tried: `alrecord.exe -device "OpenAL Soft on Microphone (Realtek Audio)" -r 48000 -b 32` and i get: ``` AL lib: (II) Initializing library v1.19.1-unknown UNKNOWN AL lib: (II) Supported backends:...
... Using, for example, the inbuilt windows voice recorder app, it works fine.
EDIT, I have run the setup.py correctly, and now I see: ``` (360monodepth) C:\\tools\NeuralDOF\360monodepth\code\python\src>python main.py --expname test_experiment --blending_method all --grid_size 8x7 Adding 'C:\\tools\NeuralDOF\360monodepth\code\python\src' to sys.path 2024-04-03 13:58:46,963 - utility.depthmap_align -...
I have edited `neus.py` to add a check: ``` # update train_num_rays if out['num_samples_full'].sum().item() > 0: if self.config.model.dynamic_ray_sampling: train_num_rays = int(self.train_num_rays * (self.train_num_samples / out['num_samples_full'].sum().item())) self.train_num_rays = min(int(self.train_num_rays * 0.9...
Hi, thanks for getting back to me. I have tried a few different DTU datasets. I am on windows,, could this be related to the fix in the fix-data-win branch?...
Hi @bennyguo, I can confirm that using the fix-win branch runs perfectly (I needed to downgrade the pytorch lightning version) and I can run on the nerf-synthetic dataset, and export...