I am working on Google Colab because I don't have enough space in my laptop. I have my yolo model and have cloned the trackeval repository to test on the personpath22 dataset, I ran this code from ultralytics import YOLO
import os
Load trained model
model = YOLO("/content/drive/MyDrive/best.pt")
path = "/content/drive/MyDrive/dataset/personpath22/raw_data"
dir = os.listdir(path)
for file in dir:
if file.endswith((".avi",".mp4","wmv")):
results = model.track(source='/content/drive/MyDrive/dataset/personpath22/raw_data/'+file)
with open(f"/content/drive/MyDrive/TRACKER_FOLDER/person_path_22-test/custom_tracker/data/{file}.txt", 'w') as f:
for frame_id, result in enumerate(results):
for box in result.boxes:
Check if box.id is not None before accessing its attributes
if box.id is not None:
bbox = box.xyxy[0].tolist() # Convert from tensor to list
track_id = box.id.item() # Get track id
conf = box.conf.item() # Get confidence score
f.write(f'{frame_id+1},{track_id},{bbox[0]},{bbox[1]},{bbox[2]-bbox[0]},{bbox[3]-bbox[1]},-1,-1,{conf}\n')
which gave me the tracking result of the model, than I ran this code
!python scripts/run_person_path_22.py --BENCHMARK MOT20 --TRACKERS_TO_EVAL YOLOv8x --TRACKERS_FOLDER /content/drive/MyDrive/TRACKER_FOLDER --GT_FOLDER /content/drive/MyDrive/tracking-dataset/dataset/personpath22/annotation/anno_amodal_2022
I am working on Google Colab because I don't have enough space in my laptop. I have my yolo model and have cloned the trackeval repository to test on the personpath22 dataset, I ran this code from ultralytics import YOLO import os
Load trained model
model = YOLO("/content/drive/MyDrive/best.pt")
path = "/content/drive/MyDrive/dataset/personpath22/raw_data" dir = os.listdir(path)
for file in dir: if file.endswith((".avi",".mp4","wmv")): results = model.track(source='/content/drive/MyDrive/dataset/personpath22/raw_data/'+file)
with open(f"/content/drive/MyDrive/TRACKER_FOLDER/person_path_22-test/custom_tracker/data/{file}.txt", 'w') as f: for frame_id, result in enumerate(results): for box in result.boxes:
Check if box.id is not None before accessing its attributes
which gave me the tracking result of the model, than I ran this code !python scripts/run_person_path_22.py --BENCHMARK MOT20 --TRACKERS_TO_EVAL YOLOv8x --TRACKERS_FOLDER /content/drive/MyDrive/TRACKER_FOLDER --GT_FOLDER /content/drive/MyDrive/tracking-dataset/dataset/personpath22/annotation/anno_amodal_2022
but it keeps saying there's no seqini file despite it being there: Eval Config: USE_PARALLEL : False NUM_PARALLEL_CORES : 8 BREAK_ON_ERROR : True RETURN_ON_ERROR : False LOG_ON_ERROR : /content/drive/MyDrive/TrackEval/error_log.txt PRINT_RESULTS : True PRINT_ONLY_COMBINED : False PRINT_CONFIG : True TIME_PROGRESS : True DISPLAY_LESS_PROGRESS : False OUTPUT_SUMMARY : True OUTPUT_EMPTY_CLASSES : True OUTPUT_DETAILED : True PLOT_CURVES : True
PersonPath22 Config: PRINT_CONFIG : True GT_FOLDER : /content/drive/MyDrive/TrackEval/data/gt/person_path_22 TRACKERS_FOLDER : /content/drive/MyDrive/TRACKER_FOLDER OUTPUT_FOLDER : ['/content/eval_results.txt'] TRACKERS_TO_EVAL : ['MyTracker'] CLASSES_TO_EVAL : ['pedestrian'] BENCHMARK : MOT20 SPLIT_TO_EVAL : test INPUT_AS_ZIP : False DO_PREPROC : True TRACKER_SUB_FOLDER : data OUTPUT_SUB_FOLDER : TRACKER_DISPLAY_NAMES : None SEQMAP_FOLDER : None SEQMAP_FILE : None SEQ_INFO : None GT_LOC_FORMAT : {gt_folder}/{seq}/gt/gt.txt SKIP_SPLIT_FOL : False Traceback (most recent call last): File "/content/drive/MyDrive/TrackEval/scripts/run_person_path_22.py", line 105, in dataset_list = [trackeval.datasets.PersonPath22(dataset_config)] File "/content/drive/MyDrive/TrackEval/trackeval/datasets/person_path_22.py", line 81, in init self.seq_list, self.seq_lengths = self._get_seq_info() File "/content/drive/MyDrive/TrackEval/trackeval/datasets/person_path_22.py", line 167, in _get_seq_info raise TrackEvalException('ini file does not exist: ' + seq + '/' + os.path.basename(ini_file)) trackeval.utils.TrackEvalException: ini file does not exist: uid_vid_00008.mp4/seqinfo.ini
I think it is a path problem but can someone provide the correct path format so I can adjust my files to it?