Notebooks to upload/download marine footage, connect to a citizen science project, train machine learning models and publish marine biological observations.
GNU General Public License v3.0
4
stars
12
forks
source link
Issue in Tutorial 8 when aggregating frames in preparation for model training #329
Before submitting a bug report, please be aware that your issue must be reproducible with all of the following, otherwise it is non-actionable, and we can not help you:
Current repo: run git fetch && git status -uno to check and git pull to update repo
If this is a custom dataset/training question you must include your train*.jpg, test*.jpg and results.png figures, or we can not help you. You can generate these with utils.plot_results().
π Bug
A clear and concise description of what the bug is.
# Run the preparation script
mlp.prepare_dataset(
agg_df=pp.aggregated_zoo_classifications,
out_path=output_folder.selected,
img_size=(720, 540),
perc_test=percentage_test.value,
)
Output:
Species
Bolocera tuediae
INFO:root:Retrieving movies that are available locally
INFO:root:All 135 movies are mapped from the server
INFO:root:There are 135 movies
INFO:root:There are movies available, but the subject metadata does not contain frame numbers and will therefore not be used.
100%|ββββββββββ| 806/806 [02:53<00:00, 4.65it/s]
Saving frames...: 100%|ββββββββββ| 806/806 [01:20<00:00, 9.99it/s]
INFO:root:Frames extracted successfully
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
File /usr/src/app/kso-dev/kso_utils/project.py:1213, in MLProjectProcessor.prepare_dataset.<locals>.on_button_clicked(b)
1211 self.species_of_interest = species_list.value
1212 # code for prepare dataset for machine learning
-> 1213 self.modules["yolo_utils"].frame_aggregation(
1214 project=self.project,
1215 server_connection=self.server_connection,
1216 db_connection=self.db_connection,
1217 out_path=out_path,
1218 perc_test=perc_test,
1219 class_list=self.species_of_interest,
1220 img_size=img_size,
1221 remove_nulls=remove_nulls,
1222 track_frames=track_frames,
1223 n_tracked_frames=n_tracked_frames,
1224 agg_df=agg_df,
1225 )
File /usr/src/app/kso-dev/kso_utils/yolo_utils.py:831, in frame_aggregation(project, server_connection, db_connection, out_path, perc_test, class_list, img_size, out_format, remove_nulls, track_frames, n_tracked_frames, agg_df)
822 raise Exception(
823 "No frames found for the selected species. Please retry with a different configuration."
824 )
826 # Pre-process frames
827 # Comment out for the moment as we do not typically need this for all cases
828 # process_frames(out_path + "/images", size=tuple(img_size))
829
830 # Create training/test sets
--> 831 split_frames(out_path, perc_test)
File /usr/src/app/kso-dev/kso_utils/yolo_utils.py:285, in split_frames(data_path, perc_test)
282 if counter >= index_test + 1:
283 # Avoid leaking frames into test set
284 if movie_name != latest_movie or movie_name == title:
--> 285 file_valid.write(pathAndFilename + "\n")
286 else:
287 file_train.write(pathAndFilename + "\n")
TypeError: unsupported operand type(s) for +: 'PosixPath' and 'str'
Expected behavior
A clear and concise description of what you expected to happen.
Environment
If applicable, add screenshots to help explain your problem.
Before submitting a bug report, please be aware that your issue must be reproducible with all of the following, otherwise it is non-actionable, and we can not help you:
git fetch && git status -uno
to check andgit pull
to update repoIf this is a custom dataset/training question you must include your
train*.jpg
,test*.jpg
andresults.png
figures, or we can not help you. You can generate these withutils.plot_results()
.π Bug
A clear and concise description of what the bug is.
To Reproduce (REQUIRED)
Input: Workflow: KSO_tagging_species_new(Hardbottom) Folder: /mimer/NOBACKUP/groups/snic2021-6-9/tmp_dir/KSO_christian_new_frames/ Threshold:0,2
Output:
Expected behavior
A clear and concise description of what you expected to happen.
Environment
If applicable, add screenshots to help explain your problem.
Additional context
Add any other context about the problem here.