Suraj Patni

Thanks for your work! `eval_hybrid.sh` and `eval_hybrid_seq.sh` are exactly same. Please make the desired changes in `eval_hybrid.sh`.

When I am reproducing the results, I got v. wrong results, as shown below:  So when I checked plotting the depths and uncertainties saved in `raw/disp` and `raw/uncert` then...

help wanted

1

### help-wanted please upload the requirements.txt file for that too. facing the compatibility issues for packages.

Signed-off-by: Suraj Patni

Please suggest how to resolve this error: ``` suraj@user:~/scratch/TheiaSfM$ mkdir build; cd build suraj@user:~/scratch/TheiaSfM/build$ cmake .. -- The C compiler identification is GNU 9.4.0 -- The CXX compiler identification is...

Random output of trajectories(ATE) on multiple runs of DROID-SLAM algorithm

1

Dear Authors, Thanks for the code! On running on a particular sequence of images multiple times, the output of DROID-SLAM varies a bit. **On debugging, I found out that the...

Just made these changes: 1. written DDP code for training and validation for faster training and validation. 2. resolved bug in `gma.py` and `encoders.py` (these modules were not used while...

What is the reason of setting the num_workers=128 (so high) ??

1

Hi, Thanks for your awesome work. What is the reason of setting the num_workers=128 (so high) ?? Is it a typo?? [at this line](https://github.com/drinkingcoder/FlowFormer-Official/blob/6ba7ea82b45394d3a7a25808399695427c9febd8/core/datasets.py#L231) @drinkingcoder