Closed Bergylta closed 7 months ago
A clear and concise description of what the bug is.
Input: Model: GU_black_round_gobies_model3 Movie: /mimer/NOBACKUP/groups/snic2021-6-9/project_movies/movies_GU/Testing_model_movie/ Confidence Threshold: 0,5
# @title <font size="5">↓ ឵឵<i>Run model over selected custom footage</font> { vertical-output: true } eval_dir = mlp.detect_yolov5( source=source_value, save_dir=save_dir.selected, conf_thres=conf_thres.value, artifact_dir=artifact_dir, save_output=True, exp_name="detect",
Output:
wandb version 0.16.0 is available! To upgrade, please run: $ pip install wandb --upgrade Tracking run with wandb version 0.13.2 Run data is saved locally in /mimer/NOBACKUP/groups/snic2021-6-9/wandb/run-20231115_142310-4cyx310m Syncing run [predict](https://wandb.ai/koster/model-evaluations/runs/4cyx310m) to [Weights & Biases](https://wandb.ai/koster/model-evaluations) ([docs](https://wandb.me/run)) YOLOv5 🚀 2023-10-30 Python-3.8.10 torch-2.1.0+cu121 CUDA:0 (NVIDIA A40, 45626MiB) Fusing layers... Model summary: 226 layers, 21041679 parameters, 0 gradients --------------------------------------------------------------------------- ZeroDivisionError Traceback (most recent call last) Cell In[16], line 2 1 # @title <font size="5">↓ ឵឵<i>Run model over selected custom footage</font> { vertical-output: true } ----> 2 eval_dir = mlp.detect_yolov5( 3 source=source_value, 4 save_dir=save_dir.selected, 5 conf_thres=conf_thres.value, 6 artifact_dir=artifact_dir, 7 save_output=True, 8 exp_name="detect", 9 ) File /usr/src/app/kso-dev/kso_utils/project.py:1334, in MLProjectProcessor.detect_yolov5(self, exp_name, source, save_dir, conf_thres, artifact_dir, img_size, save_output) 1325 eval_dir = increment_path(Path(save_dir) / exp_name, exist_ok=False) 1326 weights_path = [ 1327 f 1328 for f in Path(artifact_dir).iterdir() (...) 1332 and "best" in str(f) 1333 ][0] -> 1334 self.modules["detect"].run( 1335 weights=weights_path, 1336 source=source, 1337 conf_thres=conf_thres, 1338 save_txt=True, 1339 save_conf=True, 1340 project=save_dir, 1341 name=exp_name, 1342 nosave=not save_output, 1343 ) 1344 self.save_detections_wandb(conf_thres, weights_path, eval_dir) 1345 if wandb.run is not None: File /usr/local/lib/python3.8/dist-packages/torch/utils/_contextlib.py:115, in context_decorator.<locals>.decorate_context(*args, **kwargs) 112 @functools.wraps(func) 113 def decorate_context(*args, **kwargs): 114 with ctx_factory(): --> 115 return func(*args, **kwargs) File /usr/src/app/kso-dev/yolov5/detect.py:265, in run(weights, source, data, imgsz, conf_thres, iou_thres, max_det, device, view_img, save_txt, save_conf, save_crop, nosave, classes, agnostic_nms, augment, visualize, update, project, name, exist_ok, line_thickness, hide_labels, hide_conf, half, dnn, vid_stride) 260 LOGGER.info( 261 f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms" 262 ) 264 # Print results --> 265 t = tuple(x.t / seen * 1e3 for x in dt) # speeds per image 266 LOGGER.info( 267 f"Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}" 268 % t 269 ) 270 if save_txt or save_img: File /usr/src/app/kso-dev/yolov5/detect.py:265, in <genexpr>(.0) 260 LOGGER.info( 261 f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms" 262 ) 264 # Print results --> 265 t = tuple(x.t / seen * 1e3 for x in dt) # speeds per image 266 LOGGER.info( 267 f"Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}" 268 % t 269 ) 270 if save_txt or save_img: ZeroDivisionError: float division by zero
A clear and concise description of what you expected to happen.
If applicable, add screenshots to help explain your problem.
🐛 Bug
A clear and concise description of what the bug is.
To Reproduce (REQUIRED)
Input: Model: GU_black_round_gobies_model3 Movie: /mimer/NOBACKUP/groups/snic2021-6-9/project_movies/movies_GU/Testing_model_movie/ Confidence Threshold: 0,5
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