Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
1/20 0G 2.888 30.52 4.322 22 1920: 100%|██████████| 300/300 [13:00<00:00, 2.60s/it]
Class Images Instances Box(P R mAP50 mAP50-95): 0%| | 0/19 [00:00<?, ?it/s]/AppleInternal/Library/BuildRoots/91a344b1-f985-11ee-b563-fe8bc7981bff/Library/Caches/com.apple.xbs/Sources/MetalPerformanceShaders/MPSNDArray/Kernels/MPSNDArrayGatherND.mm:256: failed assertion `Rank of updates array (1) must be greater than or equal to inner-most dimension of indices array (300)'
/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/multiprocessing/resource_tracker.py:254: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown
warnings.warn('resource_tracker: There appear to be %d '
this error accrues on m3 mac device = "mps"
model = YOLO("yolov10n.pt") # load a pretrained model
device = "mps"
model.train(data=file_path, epochs=20, batch=8, workers=8, device=device, augment=True, imgsz=1920)
if using device = "cpu" second stage didn't gives an error and train continue without any issues
/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/multiprocessing/resource_tracker.py:254: UserWarning: resource_tracker: There appear to be 1 leaked semaphore objects to clean up at shutdown warnings.warn('resource_tracker: There appear to be %d '
this error accrues on m3 mac device = "mps"
if using device = "cpu" second stage didn't gives an error and train continue without any issues
env: Python 3.12.2 tourch 2.3.1 ultralytics 8.2.45
Is that any recommendations make it work on m3 mac under device = "mps"?