Bia B

Hello, yes. I used this code to get accuracy and the overall. https://github.com/xy-guo/MVSNet_pytorch/tree/master/evaluations/dtu

You need to run BaseEvalMain_web.m and after ComputeStat_web.m in matlab terminal. When you download Matlab pay attention to also check there to download statistisc, otherwise you will get some errors....

Download from here the Points: https://roboimagedata2.compute.dtu.dk/data/MVS/Points.zip (Points.zip\Points\stl) https://roboimagedata2.compute.dtu.dk/data/MVS/SampleSet.zip (from this you'll get the OBSmask SampleSet.zip\SampleSet\MVS Data\ObsMask) You need to download this folders mentioned, unzip and set the paths in the...

I also got the same error, this is the output with `import faulthandler; faulthandler.enable()` added in the code. ``` (venv_requirments) :~/thesis-nets/flowmap$ python3.11 -m flowmap.overfit dataset=images dataset.images.root=/home/thesis-nets/flowmap/birds_compact/birds_compact rm: cannot remove 'outputs/local':...

I did with boths requirements files, and get the same problem, will try the second point: Directly cloning CoTracker or integrating it as a submodule to avoid using the Torch...

Hi, could you please share the Google Colab notebook you use?