Kamil

> replacing > `self._backend = type2backend[type(input)] `with `self._backend = type2backend[input.type()]` > solved the problem

Sounds like you are running on cpu and not on gpu. I am runninng on 24gb gpu and for "default_config_1080_ms.yaml" config it took good few seconds for one fullHD input...

ah, you are using two gpus (2x 24GB). That potentially may be the case. GPU usage indeed indicates that pytorch is using gpus. I didn't test the code (epe training...

> o ya, also i dont nderstand that much about batch universal demo from Mseg, because i thought with batch, the MSeg run on batches of images, but in that...

in compute_weights.py take a note that argument is in H, W (and not W, H), so for e.g. fullHD will be 1080 1920; it was my NaN reason > The...

> oww.. so the txt file i created is false? at least order looks ok. I have this order too ["screenshot", "msegs/gray4k", "NPZs", "gray_stencils"] the stat is just to make...

hey, I have tried two set-ups so far: - win10, NVIDIA RTX 3090 it trained 75k steps / day - linux, NVIDIA A6000 (48GB), ~150k steps / day my entire...

When you call compute_weights script before the training `python epe/matching/compute_weights.py matched_crops_PfD-Cityscapes.csv 526 957 crop_weights_PfD-Cityscapes.npz` please make sure that you have put height and width in the right order: **(height, width)**....

Hey, alongside replacing with the `_load_img` and applying `torch.from_numpy()`, I also needed to permute channels accordingly, and in the end make cpu detach in `matching/feature_based/sample_matches.py`. Below is my code: ```python...