sachini/niloc

Neural Inertial Localization

niloc's Issues

UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 64: invalid start byte

Hi @Sachini

I am direct testing your model based on your given checkpoint and dataset. I am unable to perform testing and getting error, please look into this

Command
./test_imu.sh universityA /media/cvpr/CM_22/niloc/niloc_model_release/A/version_0/best_checkpoint.ckpt

Traceback

universityA Building
2
Arguments count: 9
scheduled_2branch test_cfg.test_name=out
directory  /media/cvpr/CM_22/niloc/
Traceback (most recent call last):
  File "/media/cvpr/CM_22/niloc/niloc/cmd_test_file.py", line 84, in <module>
    checkpoints = get_checkpoints(cmds[my_file_idx].split("=", 1)[1])
  File "/media/cvpr/CM_22/niloc/niloc/cmd_test_file.py", line 36, in get_checkpoints
    for s in f.readlines():
  File "/home/cvpr/anaconda3/lib/python3.9/codecs.py", line 322, in decode
    (result, consumed) = self._buffer_decode(data, self.errors, final)
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 64: invalid start byte

checkpoint files are not loaded

checkpoint files are not loaded properly using a script. Can you please show the demo here?

Loading pre-computed results

License

What license do you intend to use on the code?

code

I am really want to know when your code could be released.

Request for Assistance Regarding Missing Map File

I trust this message finds you well.

I hope this message finds you well. I am writing to seek your assistance with a critical issue that has arisen during my recent experiments.

In the context of our experiments, there is a key file known as the "not load grid" file that is essential for reproducing the results. Regrettably, this file seems to be missing from the experimental setup, and as a result, we are unable to replicate the experiments successfully.

I understand that this file is vital for the reproducibility of the experiments, and its absence has posed a significant challenge. I would greatly appreciate your guidance and support in obtaining or reconstructing the "not load grid" file to ensure that we can continue our research effectively.

If there are any specific procedures, sources, or recommendations you can provide to help us resolve this issue, it would be immensely valuable.

Your expertise and assistance in this matter would be greatly appreciated, and I am looking forward to your kind response.

Thank you for your time and consideration.

xxx. txt not found

Thank you very much for your outstanding work, I have benefited greatly from it.
However, when I run the code, I encounter several problems that I would like to ask for advice?
When I ran the code, there was an error of "xxx. txt not found". I only found the hdf5 files in the dataset download link you mentioned, but did not see the txt files. How is the txt file generated? Do I miss any data preprocessing processes?
I am looking forward your answers! Thanks again!!！^v^

Interested in your work, when will the code be open sourced?

omegaconf.errors.ConfigAttributeError: Key 'io' is not in struct

Does someone encountered this error?
"
File "/home/omer/anaconda3/envs/niloc_test/lib/python3.8/site-packages/omegaconf/_utils.py", line 610, in _raise
raise ex # set end OC_CAUSE=1 for full backtrace
omegaconf.errors.ConfigAttributeError: Key 'io' is not in struct
full_key: io
reference_type=Optional[Dict[Union[str, Enum], Any]]
object_type=dict
"

when would release the source code?

Hello,
Thank you very much for this great work!
I am really want to know when your code could be released.

Best,

Applicability of NILoc to urban canyon problem

Hi @Sachini,

First, I'd like to thank you for the effort to make your source code, models, etc. available for others to use. It doesn't seem to be the norm, but for those who can't create these tools from scratch, it's very valuable.

I'd like to present a different use case for NILoc and see if you think it (or maybe RONIN) may be applicable.

The problem I'm trying to solve is, starting from a known position (known by way of GNSS positioning), if I move to a different position where I don't have a GNSS signal (because it's obscured or for some other reason), if I'm capturing data from an IMU as I move from the known position to the second, can I deduce the second position from that IMU data? This is different from the situation in your research in that in my scenario there's no floor plan, as generally the locations in question are outdoors. I think that each point could be determined from the known origin point, rather than trying to do each sequentially (though perhaps always starting from the origin for each point would cumbersome), so maybe that would increase the odds of sucess.

I first tried to use the RONIN code, Android app, and models, but got stuck on the use of the game rotation vector (my question about this is here: Sachini/ronin#44 (comment)). I don't know if RoNIN is a better fit for the problem I'm trying to solve, though NILoc is geared toward location where RoNIN is more about navigation, so for that reason NILoc seems like the better fit.

Please let me know what thoughts you have and if you have any specific guidance on how I might proceed to use NILoc (or RoNIN) for my use case. I actually may have a working Tango phone, though I have never used it (it was procured for a different project that i didn't work on a few years ago). Sorry for the long post and thanks in advance.

Interpretation of Results

Thank you for the great code! Could you please teach me how to interpret the data obtained from running test_imu.sh?

1. The file summary.json contains 16 numbers for the key distance. I think it describes the percentage of frames where the error is below certain distance thresholds, but how does it correspond to the results in Table 2?
2. I believe the above results are for the localization task, but how can we reproduce the results for the relocalization task?

Looking forward to your response!