Error when launching run_tracker: `no file /.../evaluation/list.txt` when selecting VOT18 path

[evalliETH]

Hi,

I am sorry if this issue of mine looks naive, I am just getting started with this.

When I type the code for running the tracker: python run_tracker.py segm default_params --dataset vot18 --sequence \media\evalli\HD_EUGI\Resolve_Videos\Elly_coreography.mp4 --debug 1, an error occurs, saying:

FileNotFoundError: [Errno 2] No such file or directory: '/home/evalli/d3s/pytracking/evaluation/list.txt'

I think this is related to the vot18-path selection in 'local.py', because every time I change that path, the error shows it, adding the 'list.txt' file who looks like missing or non-existing.

Do some of you know how to address this issue? Also, where is the VOT18 dataset located?

Thank you in advance, Eugenio

[caiyujue]

You can directly generate the sequence names contained in the VOT file into a txt file, of course the name is list.txt, or you can refer to the _get_sequence_list function on line 51 of evaluation/votdataset.py, but you may need to modify the names of some sequences

[alanlukezic]

The dataset where you want to test your tracker has to be in the correct form. For example, see the vot 2018 dataset and how it is loaded in the pytracking toolkit.

[evalliETH]

I am still confused. I have examined both 'vot18dataset.py' and 'votdataset.py' and understood how the dataset is loaded into the tracker. However I don't understand what it means to "generate the sequence names" into this '.txt' file. I have never used VOT (or any other dataset in this application for that matter), I am learning from scratch so I am sorry if these questions of mine look silly...

Maybe you could suggest some links for me to learn how to use this. I have looked on the VOT page but the documentation didn't really help me..

Thanks again!

[caiyujue]

the “list.txt”‘s content is as follows，it contains the names of 60 sequences of VOT2018，like this ants1 ants3 bag ball1 ball2 basketball birds1 blanket bmx bolt1 bolt2 book butterfly car1 conduction1 crabs1 crossing dinosaur drone1 drone_across drone_flip fernando fish1 fish2 fish3 flamingo1 frisbee girl glove godfather graduate gymnastics1 gymnastics2 gymnastics3 hand handball1 handball2 helicopter iceskater1 iceskater2 leaves matrix motocross1 motocross2 nature pedestrian1 rabbit racing road shaking sheep singer2 singer3 soccer1 soccer2 soldier tiger traffic wiper zebrafish1

[evalliETH]

Yeah, I figured the list should look like this. I have manually created the list, downloaded the annotations from the VOT2018 and copied the containing folders into '/evaluation'. I don't understand if I also have to save, say the 'ants1' sequence (frames) into the '/evaluation' folder or not, and how to do so in a way that the tracker reads them. I have analyzed the 'data.py' and 'tracker.py' to see how it reads the sequence and it appears as it reads frames. My question is still where are those frames read from.

[evalliETH]

I think I have found my error: I saved the frame folder with the wrong name under the sequence folder: it should be named '/color' and it was named automatically when downloading.

[mrlihellohorld]

Why is "pytracking/evaluation/local.py" not in the downloaded file?thanks

[alanlukezic]

The file should be generated manually by running the following commands: python -c "from pytracking.evaluation.environment import create_default_local_file; create_default_local_file()" python -c "from ltr.admin.environment import create_default_local_file; create_default_local_file()" please read the installation instructions and see the install.sh script for more details.