mattiasmar
mattiasmar
mask.shape= torch.Size([10556]) loop_attr.shape= torch.Size([2708]) edge_attr.shape= torch.Size([10556])
Installed from source using the command: pip install git+https://github.com/pyg-team/pytorch_geometric.git When debugging with VS Code, the debugger doesn't stop at my PyG breakpoints. Not an expert yet of VS Code. Maybe...
Yes, WMT would be a good example. A request only: Could you enter the pjit as high up in the code as possible? As a user I want to pjit...
Related: Have you noticed that pytorch performance is much slower when calling the the pytorch code through rtabmap (through the pymatcher) compared to calling it a pure python (test) program?...
In the python code I call: ``` start = perf_counter() results= mymodel({**data_, **pred}) end = perf_counter() ``` I also load the input data from disk inside the python code as...
There is no such difference. I also tried with hard coding the input data (loading it from disk in the python code) and not using the whole rtabmap framework but...
Can one use pymatcher (e.g. SuperGlue) during localization, if KNN was used for mapping? @pxy522 What did you try?
@tsattler I tried your last suggestion: _first extract the features for all images into a single database, then match all images in the database, then use the mapper to reconstruct...
They don't share the exact same images, but they have a considerable (>90%) visual overlap.
Got it. I just copied a handful of images from one of the models in to the others, called the mapper again and now it works as expected. Would it...