Error in training: ...insufficient shared memory (shm) error message

FF2k25 · September 3, 2025, 8:53am

Hi all,
during training of an example about Car Detection with YOLOv5 imported model (following the GitHub instruction) I’ve got many of these errors:

…
RuntimeError: DataLoader worker (pid 973) is killed by signal: Bus error. It is possible that dataloader’s workers are out of shared memory. Please try to raise your shared memory limit.
_error_if_any_worker_fails()
…
ERROR: Unexpected bus error encountered in worker. This might be caused by insufficient shared memory (shm).
ERROR: Unexpected bus error encountered in worker. This might be caused by insufficient shared memory (shm).
ERROR: Unexpected bus error encountered in worker. This might be caused by insufficient shared memory (shm).
ERROR: Unexpected bus error encountered in worker. This might be caused by insufficient shared memory (shm).
…

It is a memory trouble, but how I can solve it?

Thanks and best regards for any help on this matter.
Fabio

marcpous · September 3, 2025, 2:46pm

Hello @FF2k25 first of all welcome to the Edge Impulse community!

In the other hand, could you please share more details? Where do you get those errors?

Thanks!

FF2k25 · September 3, 2025, 2:50pm

Hi marcpous,
first of all thanks for your support.
I’ve this error into the training output window after some time I’ve press the Save & train button.
As model I’m using YOLOv5 imported as per instruction on GitHub.
Model used Small - 7.2M params.
My input layer is about 1,228,800 features, I’m using a images training set made of image with size 640x640 and Color depth RGB.

I’ve enclosed also the log for your reference.

[spinner-done] Job scheduled e[0;37mat 03 Sep 2025 11:41:42e[0m
[spinner-done] Job started e[0;37mat 03 Sep 2025 11:41:45e[0m

[spinner-done] Job scheduled e[0;37mat 03 Sep 2025 11:41:54e[0m
[spinner-done] Job started e[0;37mat 03 Sep 2025 11:41:55e[0m
Transforming Edge Impulse data format into something compatible with YOLOv5
[  1/360] Converting images...
[289/360] Converting images...
[360/360] Converting images...
Transforming Edge Impulse data format into something compatible with YOLOv5 OK

e[34me[1mtrain: e[0mweights=/app/yolov5s.pt, cfg=, data=/tmp/data/data.yaml, hyp=data/hyps/hyp.scratch-low.yaml, epochs=60, batch_size=32, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, noplots=False, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, optimizer=SGD, sync_bn=False, workers=8, project=runs/train, name=yolov5_results, exist_ok=False, quad=False, cos_lr=False, label_smoothing=0.0, patience=100, freeze=[10], save_period=-1, seed=0, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest
e[34me[1mgithub: e[0mskipping check (not a git repository), for updates see https://github.com/ultralytics/yolov5
/usr/local/lib/python3.8/dist-packages/torch/cuda/__init__.py:88: UserWarning: CUDA initialization: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 34: CUDA driver is a stub library (Triggered internally at ../c10/cuda/CUDAFunctions.cpp:109.)
  return torch._C._cuda_getDeviceCount() > 0
YOLOv5 🚀 2022-9-11 Python-3.8.10 torch-1.13.1+cu117 CPU

e[34me[1mhyperparameters: e[0mlr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=0.05, cls=0.5, cls_pw=1.0, obj=1.0, obj_pw=1.0, iou_t=0.2, anchor_t=4.0, fl_gamma=0.0, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0
e[34me[1mWeights & Biases: e[0mrun 'pip install wandb' to automatically track and visualize YOLOv5 🚀 runs in Weights & Biases
e[34me[1mClearML: e[0mrun 'pip install clearml' to automatically track, visualize and remotely train YOLOv5 🚀 in ClearML
e[34me[1mComet: e[0mrun 'pip install comet_ml' to automatically track and visualize YOLOv5 🚀 runs in Comet
e[34me[1mTensorBoard: e[0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/
Overriding model.yaml nc=80 with nc=1

                 from  n    params  module                                  arguments                     
  0                -1  1      3520  models.common.Conv                      [3, 32, 6, 2, 2]              
  1                -1  1     18560  models.common.Conv                      [32, 64, 3, 2]                
  2                -1  1     18816  models.common.C3                        [64, 64, 1]                   
  3                -1  1     73984  models.common.Conv                      [64, 128, 3, 2]               
  4                -1  2    115712  models.common.C3                        [128, 128, 2]                 
  5                -1  1    295424  models.common.Conv                      [128, 256, 3, 2]              
  6                -1  3    625152  models.common.C3                        [256, 256, 3]                 
  7                -1  1   1180672  models.common.Conv                      [256, 512, 3, 2]              
  8                -1  1   1182720  models.common.C3                        [512, 512, 1]                 
  9                -1  1    656896  models.common.SPPF                      [512, 512, 5]                 
 10                -1  1    131584  models.common.Conv                      [512, 256, 1, 1]              
 11                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          
 12           [-1, 6]  1         0  models.common.Concat                    [1]                           
 13                -1  1    361984  models.common.C3                        [512, 256, 1, False]          
 14                -1  1     33024  models.common.Conv                      [256, 128, 1, 1]              
 15                -1  1         0  torch.nn.modules.upsampling.Upsample    [None, 2, 'nearest']          
 16           [-1, 4]  1         0  models.common.Concat                    [1]                           
 17                -1  1     90880  models.common.C3                        [256, 128, 1, False]          
 18                -1  1    147712  models.common.Conv                      [128, 128, 3, 2]              
 19          [-1, 14]  1         0  models.common.Concat                    [1]                           
 20                -1  1    296448  models.common.C3                        [256, 256, 1, False]          
 21                -1  1    590336  models.common.Conv                      [256, 256, 3, 2]              
 22          [-1, 10]  1         0  models.common.Concat                    [1]                           
 23                -1  1   1182720  models.common.C3                        [512, 512, 1, False]          
 24      [17, 20, 23]  1     16182  models.yolo.Detect                      [1, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]
 23                -1  1   1182720  models.common.C3                        [512, 512, 1, False]          
 24      [17, 20, 23]  1     16182  models.yolo.Detect                      [1, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]
 23                -1  1   1182720  models.common.C3                        [512, 512, 1, False]          
 24      [17, 20, 23]  1     16182  models.yolo.Detect                      [1, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [128, 256, 512]]
Model summary: 270 layers, 7022326 parameters, 7022326 gradients, 15.9 GFLOPs

Model summary: 270 layers, 7022326 parameters, 7022326 gradients, 15.9 GFLOPs


Model summary: 270 layers, 7022326 parameters, 7022326 gradients, 15.9 GFLOPs

Transferred 343/349 items from /app/yolov5s.pt
freezing model.0.conv.weight
freezing model.0.bn.weight
freezing model.0.bn.bias
freezing model.1.conv.weight
freezing model.1.bn.weight
freezing model.1.bn.bias
freezing model.2.cv1.conv.weight
freezing model.2.cv1.bn.weight
freezing model.2.cv1.bn.bias
freezing model.2.cv2.conv.weight
freezing model.2.cv2.bn.weight
freezing model.2.cv2.bn.bias
freezing model.2.cv3.conv.weight
freezing model.2.cv3.bn.weight
freezing model.2.cv3.bn.bias
freezing model.2.m.0.cv1.conv.weight
freezing model.2.m.0.cv1.bn.weight
freezing model.2.m.0.cv1.bn.bias
freezing model.2.m.0.cv2.conv.weight
freezing model.2.m.0.cv2.bn.weight
freezing model.0.bn.bias
freezing model.1.conv.weight
freezing model.1.bn.weight
freezing model.1.bn.bias
freezing model.2.cv1.conv.weight
freezing model.2.cv1.bn.weight
freezing model.2.cv1.bn.bias
freezing model.2.cv2.conv.weight
freezing model.2.cv2.bn.weight
freezing model.2.cv2.bn.bias
freezing model.2.cv3.conv.weight
freezing model.2.cv3.bn.weight
freezing model.2.cv3.bn.bias
freezing model.2.m.0.cv1.conv.weight
freezing model.2.m.0.cv1.bn.weight
freezing model.2.m.0.cv1.bn.bias
freezing model.2.m.0.cv2.conv.weight
freezing model.2.m.0.cv2.bn.weight
freezing model.2.m.0.cv2.bn.bias
freezing model.3.conv.weight
freezing model.3.bn.weight
freezing model.3.bn.bias
freezing model.4.cv1.conv.weight
freezing model.4.cv1.bn.weight
freezing model.4.cv1.bn.bias
freezing model.4.cv2.conv.weight
freezing model.4.cv2.bn.weight
freezing model.4.cv2.bn.bias
freezing model.4.cv3.conv.weight
freezing model.4.cv3.bn.weight
freezing model.4.cv3.bn.bias
freezing model.4.m.0.cv1.conv.weight
freezing model.4.m.0.cv1.bn.weight
freezing model.4.m.0.cv1.bn.bias
freezing model.4.m.0.cv2.conv.weight
freezing model.4.m.0.cv2.bn.weight
freezing model.4.m.0.cv2.bn.bias
freezing model.4.m.1.cv1.conv.weight
freezing model.4.m.1.cv1.bn.weight
freezing model.4.m.1.cv1.bn.bias
Transferred 343/349 items from /app/yolov5s.pt
freezing model.0.conv.weight
freezing model.0.bn.weight
freezing model.0.bn.bias
freezing model.1.conv.weight
freezing model.1.bn.weight
freezing model.1.bn.bias
freezing model.2.cv1.conv.weight
freezing model.2.cv1.bn.weight
freezing model.2.cv1.bn.bias
freezing model.2.cv2.conv.weight
freezing model.2.cv2.bn.weight
freezing model.2.cv2.bn.bias
freezing model.2.cv3.conv.weight
freezing model.2.cv3.bn.weight
freezing model.2.cv3.bn.bias
freezing model.2.m.0.cv1.conv.weight
freezing model.2.m.0.cv1.bn.weight
freezing model.2.m.0.cv1.bn.bias
freezing model.2.m.0.cv2.conv.weight
freezing model.2.m.0.cv2.bn.weight
freezing model.2.m.0.cv2.bn.bias
freezing model.3.conv.weight
freezing model.3.bn.weight
freezing model.3.bn.bias
freezing model.4.cv1.conv.weight
freezing model.4.cv1.bn.weight
freezing model.4.cv1.bn.bias
freezing model.4.cv2.conv.weight
freezing model.4.cv2.bn.weight
freezing model.4.cv2.bn.bias
freezing model.4.cv3.conv.weight
freezing model.4.cv3.bn.weight
freezing model.4.cv3.bn.bias
freezing model.4.m.0.cv1.conv.weight
freezing model.4.m.0.cv1.bn.weight
freezing model.4.m.0.cv1.bn.bias
freezing model.4.m.0.cv2.conv.weight
freezing model.4.m.0.cv2.bn.weight
freezing model.4.m.0.cv2.bn.bias
freezing model.4.m.1.cv1.conv.weight
freezing model.4.m.1.cv1.bn.weight
freezing model.4.m.1.cv1.bn.bias
freezing model.4.m.1.cv2.conv.weight
freezing model.4.m.1.cv2.bn.weight
freezing model.4.m.1.cv2.bn.bias
freezing model.5.conv.weight
freezing model.5.bn.weight
freezing model.5.bn.bias
freezing model.6.cv1.conv.weight
freezing model.6.cv1.bn.weight
freezing model.6.cv1.bn.bias
freezing model.6.cv2.conv.weight
freezing model.6.cv2.bn.weight
freezing model.6.cv2.bn.bias
freezing model.2.m.0.cv2.bn.bias
freezing model.3.conv.weight
freezing model.3.bn.weight
freezing model.3.bn.bias
freezing model.4.cv1.conv.weight
freezing model.4.cv1.bn.weight
freezing model.4.cv1.bn.bias
freezing model.4.cv2.conv.weight
freezing model.4.cv2.bn.weight
freezing model.4.cv2.bn.bias
freezing model.4.cv3.conv.weight
freezing model.4.cv3.bn.weight
freezing model.4.cv3.bn.bias
freezing model.4.m.0.cv1.conv.weight
freezing model.4.m.0.cv1.bn.weight
freezing model.4.m.0.cv1.bn.bias
freezing model.4.m.0.cv2.conv.weight
freezing model.4.m.0.cv2.bn.weight
freezing model.4.m.0.cv2.bn.bias
freezing model.4.m.1.cv1.conv.weight
freezing model.4.m.1.cv1.bn.weight
freezing model.4.m.1.cv1.bn.bias
Transferred 343/349 items from /app/yolov5s.pt
freezing model.0.conv.weight
freezing model.0.bn.weight
freezing model.0.bn.bias
freezing model.1.conv.weight
freezing model.1.bn.weight
freezing model.1.bn.bias
freezing model.2.cv1.conv.weight
freezing model.2.cv1.bn.weight
freezing model.2.cv1.bn.bias
freezing model.2.cv2.conv.weight
freezing model.2.cv2.bn.weight
freezing model.2.cv2.bn.bias
freezing model.2.cv3.conv.weight
freezing model.2.cv3.bn.weight
freezing model.2.cv3.bn.bias
freezing model.2.m.0.cv1.conv.weight
freezing model.2.m.0.cv1.bn.weight
freezing model.2.m.0.cv1.bn.bias
freezing model.2.m.0.cv2.conv.weight
freezing model.2.m.0.cv2.bn.weight
freezing model.2.m.0.cv2.bn.bias
freezing model.3.conv.weight
freezing model.3.bn.weight
freezing model.3.bn.bias
freezing model.4.cv1.conv.weight
freezing model.4.cv1.bn.weight
freezing model.4.cv1.bn.bias
freezing model.4.cv2.conv.weight
freezing model.4.cv2.bn.weight
freezing model.4.cv2.bn.bias
freezing model.4.cv3.conv.weight
freezing model.4.cv3.bn.weight
freezing model.4.cv3.bn.bias
freezing model.4.m.0.cv1.conv.weight
freezing model.4.m.0.cv1.bn.weight
freezing model.4.m.0.cv1.bn.bias
freezing model.4.m.0.cv2.conv.weight
freezing model.4.m.0.cv2.bn.weight
freezing model.4.m.0.cv2.bn.bias
freezing model.4.m.1.cv1.conv.weight
freezing model.4.m.1.cv1.bn.weight
freezing model.4.m.1.cv1.bn.bias
freezing model.4.m.1.cv2.conv.weight
freezing model.4.m.1.cv2.bn.weight
freezing model.4.m.1.cv2.bn.bias
freezing model.5.conv.weight
freezing model.5.bn.weight
freezing model.5.bn.bias
freezing model.6.cv1.conv.weight
freezing model.6.cv1.bn.weight
freezing model.6.cv1.bn.bias
freezing model.6.cv2.conv.weight
freezing model.6.cv2.bn.weight
freezing model.6.cv2.bn.bias
freezing model.6.cv3.conv.weight
freezing model.6.cv3.bn.weight
freezing model.6.cv3.bn.bias
freezing model.6.m.0.cv1.conv.weight
freezing model.6.m.0.cv1.bn.weight
freezing model.6.m.0.cv1.bn.bias
freezing model.6.m.0.cv2.conv.weight
freezing model.6.m.0.cv2.bn.weight
freezing model.6.m.0.cv2.bn.bias
freezing model.6.m.1.cv1.conv.weight
freezing model.4.m.1.cv2.bn.weight
freezing model.4.m.1.cv2.bn.bias
freezing model.5.conv.weight
freezing model.5.bn.weight
freezing model.5.bn.bias
freezing model.6.cv1.conv.weight
freezing model.6.cv1.bn.weight
freezing model.6.cv1.bn.bias
freezing model.6.cv2.conv.weight
freezing model.6.cv2.bn.weight
freezing model.6.cv2.bn.bias
freezing model.6.cv3.conv.weight
freezing model.6.cv3.bn.weight
freezing model.6.cv3.bn.bias
freezing model.6.m.0.cv1.conv.weight
freezing model.6.m.0.cv1.bn.weight
freezing model.6.m.0.cv1.bn.bias
freezing model.6.m.0.cv2.conv.weight
freezing model.6.m.0.cv2.bn.bias
freezing model.6.m.1.cv1.conv.weight
freezing model.6.m.1.cv1.bn.weight
freezing model.6.m.1.cv1.bn.bias
freezing model.6.m.1.cv2.conv.weight
freezing model.6.m.1.cv2.bn.weight
freezing model.6.m.1.cv2.bn.bias
freezing model.6.m.2.cv1.conv.weight
freezing model.6.m.2.cv1.bn.weight
freezing model.6.m.2.cv1.bn.bias
freezing model.6.m.2.cv2.conv.weight
freezing model.6.m.2.cv2.bn.weight
freezing model.6.m.2.cv2.bn.bias
freezing model.7.conv.weight
freezing model.7.bn.weight
freezing model.7.bn.bias
freezing model.8.cv1.conv.weight
freezing model.8.cv1.bn.weight
freezing model.8.cv1.bn.bias
freezing model.8.cv2.conv.weight
freezing model.8.cv2.bn.weight
freezing model.8.cv2.bn.bias
freezing model.8.cv3.conv.weight
freezing model.8.cv3.bn.weight
freezing model.8.cv3.bn.bias
freezing model.8.m.0.cv1.conv.weight
freezing model.8.m.0.cv1.bn.weight
freezing model.8.m.0.cv1.bn.bias
freezing model.8.m.0.cv2.conv.weight
freezing model.8.m.0.cv2.bn.weight
freezing model.8.m.0.cv2.bn.bias
freezing model.9.cv1.conv.weight
freezing model.9.cv1.bn.weight
freezing model.9.cv1.bn.bias
freezing model.9.cv2.conv.weight
freezing model.9.cv2.bn.weight
freezing model.9.cv2.bn.bias
freezing model.6.m.1.cv1.bn.weight
freezing model.6.m.1.cv1.bn.bias
freezing model.6.m.1.cv2.conv.weight
freezing model.6.m.1.cv2.bn.weight
freezing model.6.m.1.cv2.bn.bias
freezing model.6.m.2.cv1.conv.weight
freezing model.6.m.2.cv1.bn.weight
freezing model.6.m.2.cv1.bn.bias
freezing model.6.m.2.cv2.conv.weight
freezing model.6.m.2.cv2.bn.weight
freezing model.6.m.2.cv2.bn.bias
freezing model.7.conv.weight
freezing model.7.bn.weight
freezing model.7.bn.bias
freezing model.8.cv1.conv.weight
freezing model.8.cv1.bn.weight
freezing model.8.cv1.bn.bias
freezing model.8.cv2.conv.weight
freezing model.8.cv2.bn.weight
freezing model.8.cv2.bn.bias
freezing model.8.cv3.conv.weight
freezing model.8.cv3.bn.weight
freezing model.8.cv3.bn.bias
freezing model.8.m.0.cv1.conv.weight
freezing model.8.m.0.cv2.conv.weight
freezing model.8.m.0.cv2.bn.weight
freezing model.8.m.0.cv2.bn.bias
freezing model.9.cv1.conv.weight
freezing model.9.cv1.bn.weight
freezing model.9.cv1.bn.bias
freezing model.9.cv2.conv.weight
e[34me[1moptimizer:e[0m SGD(lr=0.01) with parameter groups 57 weight(decay=0.0), 60 weight(decay=0.0005), 60 bias
freezing model.6.m.0.cv1.conv.weight
freezing model.6.m.0.cv1.bn.weight
freezing model.6.m.0.cv1.bn.bias
freezing model.6.m.0.cv2.conv.weight
freezing model.6.m.0.cv2.bn.weight
freezing model.6.m.0.cv2.bn.bias
freezing model.6.m.1.cv1.conv.weight
freezing model.4.m.1.cv2.bn.weight
freezing model.4.m.1.cv2.bn.bias
freezing model.5.conv.weight
freezing model.5.bn.weight
freezing model.5.bn.bias
freezing model.6.cv1.conv.weight
freezing model.6.cv1.bn.weight
freezing model.6.cv1.bn.bias
freezing model.6.cv2.conv.weight
freezing model.6.cv2.bn.weight
freezing model.6.cv2.bn.bias
freezing model.6.cv3.conv.weight
freezing model.6.cv3.bn.weight
freezing model.6.cv3.bn.bias
freezing model.6.m.0.cv1.conv.weight
freezing model.6.m.0.cv1.bn.weight
freezing model.6.m.0.cv1.bn.bias
freezing model.6.m.0.cv2.conv.weight
freezing model.6.m.0.cv2.bn.bias
freezing model.6.m.1.cv1.conv.weight
freezing model.6.m.1.cv1.bn.weight
freezing model.6.m.1.cv1.bn.bias
freezing model.6.m.1.cv2.conv.weight
freezing model.6.m.1.cv2.bn.weight
freezing model.6.m.1.cv2.bn.bias
freezing model.6.m.2.cv1.conv.weight
freezing model.6.m.2.cv1.bn.weight
freezing model.6.m.2.cv2.bn.bias
freezing model.7.conv.weight
freezing model.7.bn.weight
freezing model.7.bn.bias
freezing model.8.cv1.conv.weight
freezing model.8.cv1.bn.weight
freezing model.8.cv1.bn.bias
freezing model.8.cv2.conv.weight
freezing model.8.cv2.bn.weight
freezing model.8.cv2.bn.bias
freezing model.8.cv3.conv.weight
freezing model.8.cv3.bn.weight
freezing model.8.cv3.bn.bias
freezing model.8.m.0.cv1.conv.weight
freezing model.8.m.0.cv1.bn.weight
freezing model.9.cv2.bn.weight
freezing model.9.cv2.bn.bias
freezing model.6.m.1.cv1.bn.weight
freezing model.6.m.1.cv1.bn.bias
freezing model.6.m.1.cv2.conv.weight
freezing model.6.m.1.cv2.bn.weight
freezing model.6.m.1.cv2.bn.bias
freezing model.6.m.2.cv1.conv.weight
freezing model.6.m.2.cv1.bn.weight
freezing model.6.m.2.cv1.bn.bias
freezing model.6.m.2.cv2.conv.weight
freezing model.6.m.2.cv2.bn.weight
freezing model.6.m.2.cv2.bn.bias
freezing model.7.conv.weight
freezing model.7.bn.weight
freezing model.7.bn.bias
freezing model.8.cv1.conv.weight
freezing model.8.cv1.bn.weight
freezing model.8.cv1.bn.bias
freezing model.8.cv2.conv.weight
freezing model.8.cv2.bn.weight
freezing model.8.cv2.bn.bias
freezing model.8.cv3.conv.weight
freezing model.8.cv3.bn.weight
freezing model.8.cv3.bn.bias
freezing model.8.m.0.cv1.conv.weight
freezing model.8.m.0.cv2.conv.weight
freezing model.8.m.0.cv2.bn.weight
freezing model.8.m.0.cv2.bn.bias
freezing model.9.cv1.conv.weight
freezing model.9.cv1.bn.weight
freezing model.9.cv1.bn.bias
freezing model.9.cv2.conv.weight
e[34me[1moptimizer:e[0m SGD(lr=0.01) with parameter groups 57 weight(decay=0.0), 60 weight(decay=0.0005), 60 bias
e[34me[1malbumentations: e[0mBlur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01), CLAHE(p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8))

e[34me[1mtrain: e[0mScanning '/tmp/data/train/labels' images and labels...:   0% 0/288 [00:00<?, ?it/s]
e[34me[1mtrain: e[0mScanning '/tmp/data/train/labels' images and labels...12 found, 0 missing, 0 empty, 0 corrupt:   4% 12/288 [00:00<00:02, 94.60it/s]
e[34me[1mtrain: e[0mScanning '/tmp/data/train/labels' images and labels...183 found, 0 missing, 6 empty, 0 corrupt:  64% 183/288 [00:00<00:00, 950.19it/s]
e[34me[1mtrain: e[0mScanning '/tmp/data/train/labels' images and labels...288 found, 0 missing, 10 empty, 0 corrupt: 100% 288/288 [00:00<00:00, 1245.83it/s]
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00031.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00092.jpg: 1 duplicate labels removed

e[34me[1mtrain: e[0mScanning '/tmp/data/train/labels' images and labels...:   0% 0/288 [00:00<?, ?it/s]
e[34me[1mtrain: e[0mScanning '/tmp/data/train/labels' images and labels...12 found, 0 missing, 0 empty, 0 corrupt:   4% 12/288 [00:00<00:02, 94.60it/s]
e[34me[1mtrain: e[0mScanning '/tmp/data/train/labels' images and labels...183 found, 0 missing, 6 empty, 0 corrupt:  64% 183/288 [00:00<00:00, 950.19it/s]
e[34me[1mtrain: e[0mScanning '/tmp/data/train/labels' images and labels...288 found, 0 missing, 10 empty, 0 corrupt: 100% 288/288 [00:00<00:00, 1245.83it/s]
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00031.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00092.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00169.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00197.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00217.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00246.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00031.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00092.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00169.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00197.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00217.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00246.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mNew cache created: /tmp/data/train/labels.cache
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00169.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00197.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00217.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00246.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00031.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00092.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00169.jpg: 1 duplicate labels removed
e[34me[1mtrain: e[0mWARNING: /tmp/data/train/images/image00197.jpg: 1 duplicate labels removed

  0% 0/288 [00:00<?, ?it/s]
e[34me[1mtrain: e[0mCaching images (0.0GB ram):   7% 20/288 [00:00<00:02, 108.16it/s]
e[34me[1mtrain: e[0mCaching images (0.0GB ram):  14% 40/288 [00:00<00:01, 147.67it/s]
e[34me[1mtrain: e[0mCaching images (0.1GB ram):  20% 57/288 [00:00<00:01, 153.71it/s]
e[34me[1mtrain: e[0mCaching images (0.1GB ram):  27% 77/288 [00:00<00:01, 128.21it/s]
e[34me[1mtrain: e[0mCaching images (0.1GB ram):  33% 94/288 [00:00<00:01, 139.19it/s]
e[34me[1mtrain: e[0mCaching images (0.1GB ram):  38% 109/288 [00:00<00:01, 141.59it/s]
e[34me[1mtrain: e[0mCaching images (0.2GB ram):  43% 124/288 [00:00<00:01, 143.50it/s]
e[34me[1mtrain: e[0mCaching images (0.2GB ram):  50% 144/288 [00:00<00:00, 159.32it/s]
e[34me[1mtrain: e[0mCaching images (0.2GB ram):  56% 161/288 [00:01<00:00, 160.13it/s]
e[34me[1mtrain: e[0mCaching images (0.2GB ram):  62% 178/288 [00:01<00:00, 128.66it/s]
e[34me[1mtrain: e[0mCaching images (0.2GB ram):  67% 193/288 [00:01<00:00, 133.42it/s]
e[34me[1mtrain: e[0mCaching images (0.3GB ram):  73% 210/288 [00:01<00:00, 141.91it/s]
e[34me[1mtrain: e[0mCaching images (0.3GB ram):  80% 231/288 [00:01<00:00, 128.48it/s]
e[34me[1mtrain: e[0mCaching images (0.3GB ram):  87% 250/288 [00:01<00:00, 141.32it/s]
e[34me[1mtrain: e[0mCaching images (0.3GB ram):  94% 270/288 [00:01<00:00, 155.78it/s]
e[34me[1mtrain: e[0mCaching images (0.4GB ram): 100% 287/288 [00:01<00:00, 157.26it/s]
e[34me[1mtrain: e[0mCaching images (0.4GB ram): 100% 288/288 [00:01<00:00, 144.57it/s]

e[34me[1mval: e[0mScanning '/tmp/data/valid/labels' images and labels...:   0% 0/72 [00:00<?, ?it/s]
e[34me[1mval: e[0mScanning '/tmp/data/valid/labels' images and labels...1 found, 0 missing, 0 empty, 0 corrupt:   1% 1/72 [00:00<00:14,  4.96it/s]
e[34me[1mval: e[0mScanning '/tmp/data/valid/labels' images and labels...72 found, 0 missing, 3 empty, 0 corrupt: 100% 72/72 [00:00<00:00, 240.00it/s]
e[34me[1mval: e[0mWARNING: /tmp/data/valid/images/image00026.jpg: 2 duplicate labels removed
e[34me[1mval: e[0mNew cache created: /tmp/data/valid/labels.cache

  0% 0/72 [00:00<?, ?it/s]
e[34me[1mval: e[0mCaching images (0.0GB ram):   1% 1/72 [00:00<00:07,  9.92it/s]
e[34me[1mval: e[0mCaching images (0.0GB ram):   3% 2/72 [00:00<00:11,  6.23it/s]
e[34me[1mval: e[0mCaching images (0.0GB ram):  26% 19/72 [00:00<00:00, 62.38it/s]
e[34me[1mval: e[0mCaching images (0.0GB ram):  39% 28/72 [00:00<00:00, 54.27it/s]
e[34me[1mval: e[0mCaching images (0.0GB ram):  49% 35/72 [00:00<00:00, 46.12it/s]
e[34me[1mval: e[0mCaching images (0.1GB ram):  57% 41/72 [00:00<00:00, 49.08it/s]
e[34me[1mval: e[0mCaching images (0.1GB ram):  76% 55/72 [00:01<00:00, 71.28it/s]
e[34me[1mval: e[0mCaching images (0.1GB ram):  89% 64/72 [00:01<00:00, 60.75it/s]
e[34me[1mval: e[0mCaching images (0.1GB ram): 100% 72/72 [00:01<00:00, 55.32it/s]

e[34me[1mAutoAnchor: e[0m5.45 anchors/target, 1.000 Best Possible Recall (BPR). Current anchors are a good fit to dataset ✅
Plotting labels to runs/train/yolov5_results/labels.jpg... 
Image sizes 640 train, 640 val
Using 8 dataloader workers
Logging results to e[1mruns/train/yolov5_resultse[0m
Starting training for 60 epochs...
Image sizes 640 train, 640 val
Using 8 dataloader workers
Logging results to e[1mruns/train/yolov5_resultse[0m

      Epoch    GPU_mem   box_loss   obj_loss   cls_loss  Instances       Size
Logging results to e[1mruns/train/yolov5_resultse[0m
Starting training for 60 epochs...
Image sizes 640 train, 640 val

  0% 0/9 [00:00<?, ?it/s]
       0/59         0G     0.1252    0.04494          0        191        640:   0% 0/9 [04:20<?, ?it/s]
       0/59         0G     0.1252    0.04494          0        191        640:  11% 1/9 [07:07<56:57, 427.18s/it]
       0/59         0G     0.1246    0.04416          0        171        640:  11% 1/9 [09:16<56:57, 427.18s/it]
       0/59         0G     0.1246    0.04416          0        171        640:  22% 2/9 [09:16<29:24, 252.01s/it]
       0/59         0G     0.1244    0.04441          0        188        640:  22% 2/9 [11:30<29:24, 252.01s/it]
       0/59         0G     0.1244    0.04441          0        188        640:  33% 3/9 [11:31<19:50, 198.35s/it]
       0/59         0G     0.1235    0.04465          0        183        640:  33% 3/9 [14:04<19:50, 198.35s/it]
       0/59         0G     0.1235    0.04465          0        183        640:  44% 4/9 [14:04<15:03, 180.65s/it]
       0/59         0G     0.1229    0.04407          0        159        640:  44% 4/9 [16:36<15:03, 180.65s/it]
       0/59         0G     0.1229    0.04407          0        159        640:  56% 5/9 [16:36<11:20, 170.21s/it]
       0/59         0G     0.1222    0.04404          0        173        640:  56% 5/9 [19:32<11:20, 170.21s/it]
       0/59         0G     0.1222    0.04404          0        173        640:  67% 6/9 [19:32<08:37, 172.38s/it]
       0/59         0G     0.1212    0.04419          0        165        640:  67% 6/9 [22:07<08:37, 172.38s/it]
       0/59         0G     0.1212    0.04419          0        165        640:  78% 7/9 [22:07<05:32, 166.47s/it]
       0/59         0G     0.1202    0.04457          0        177        640:  78% 7/9 [24:51<05:32, 166.47s/it]
       0/59         0G     0.1202    0.04457          0        177        640:  89% 8/9 [24:51<02:45, 165.81s/it]
       0/59         0G     0.1189    0.04435          0        139        640:  89% 8/9 [26:57<02:45, 165.81s/it]
       0/59         0G     0.1189    0.04435          0        139        640: 100% 9/9 [26:57<00:00, 153.49s/it]
       0/59         0G     0.1189    0.04435          0        139        640: 100% 9/9 [26:58<00:00, 179.79s/it]
Traceback (most recent call last):
  File "train.py", line 630, in <module>
    main(opt)
  File "train.py", line 526, in main
    main(opt)
  File "train.py", line 526, in main
    train(opt.hyp, opt, device, callbacks)
  File "train.py", line 349, in train
    results, maps, _ = validate.run(data_dict,
  File "/usr/local/lib/python3.8/dist-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/app/yolov5/val.py", line 208, in run
    out, train_out = model(im) if compute_loss else (model(im, augment=augment), None)
  File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "/app/yolov5/models/yolo.py", line 189, in forward
    return self._forward_once(x, profile, visualize)  # single-scale inference, train
  File "/app/yolov5/models/yolo.py", line 102, in _forward_once
    x = m(x)  # run
  File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1194, in _call_impl
    train(opt.hyp, opt, device, callbacks)
  File "train.py", line 349, in train
    results, maps, _ = validate.run(data_dict,
  File "/usr/local/lib/python3.8/dist-packages/torch/autograd/grad_mode.py", line 27, in decorate_context
    return func(*args, **kwargs)
  File "/app/yolov5/val.py", line 208, in run
    return forward_call(*input, **kwargs)
  File "/app/yolov5/models/yolo.py", line 189, in forward
    return self._forward_once(x, profile, visualize)  # single-scale inference, train
  File "/app/yolov5/models/yolo.py", line 102, in _forward_once
    x = m(x)  # run
  File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "/app/yolov5/models/common.py", line 160, in forward
    return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))
  File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/container.py", line 204, in forward
    input = module(input)
  File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "/app/yolov5/models/common.py", line 113, in forward
    return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
  File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/_utils/signal_handling.py", line 66, in handler
    _error_if_any_worker_fails()
RuntimeError: DataLoader worker (pid 1488) is killed by signal: Bus error. It is possible that dataloader's workers are out of shared memory. Please try to raise your shared memory limit.
    return forward_call(*input, **kwargs)
  File "/app/yolov5/models/common.py", line 160, in forward
    return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), 1))
  File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/container.py", line 204, in forward
    input = module(input)
  File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1194, in _call_impl
    return forward_call(*input, **kwargs)
  File "/app/yolov5/models/common.py", line 113, in forward
    return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
  File "/usr/local/lib/python3.8/dist-packages/torch/utils/data/_utils/signal_handling.py", line 66, in handler
    _error_if_any_worker_fails()
RuntimeError: DataLoader worker (pid 1488) is killed by signal: Bus error. It is possible that dataloader's workers are out of shared memory. Please try to raise your shared memory limit.
Application exited with code 1
Application exited with code 1

Thanks for your help.
Fabio

marcpous · September 4, 2025, 8:15am

@FF2k25 i have another question! what hardware are you using here?

I see this

/usr/local/lib/python3.8/dist-packages/torch/cuda/__init__.py:88: UserWarning: CUDA initialization: Unexpected error from cudaGetDeviceCount(). Did you run some cuda functions before calling NumCudaDevices() that might have already set an error? Error 34: CUDA driver is a stub library (Triggered internally at ../c10/cuda/CUDAFunctions.cpp:109.)
  return torch._C._cuda_getDeviceCount() > 0
YOLOv5 🚀 2022-9-11 Python-3.8.10 torch-1.13.1+cu117 CPU

so not sure if the device is trying to use only CPU instead of the GPU and can’t run the model due the memory.

RuntimeError: DataLoader worker (pid 1488) is killed by signal: Bus error. It is possible that dataloader's workers are out of shared memory. Please try to raise your shared memory limit.

FF2k25 · September 4, 2025, 8:18am

Dear marcpous, actually I’m just doing the training using the YOLOv5 model imported from GitHub. The destination, so the real hardware, will be the same as show into the following tutorial

that I’m using as reference in order to replicate it.

Do you need other info or screenshot of my EDGE Impulse settings?

Thanks for your help!
Fabio

marcpous · September 4, 2025, 9:02am

Yes please share more details @FF2k25

Thanks!

FF2k25 · September 4, 2025, 9:16am

Here some image taken from my EDGE IMPULSE dashboard.

BTW are equal to the one show into the reference tutorial that I’ve wrote above.

Thanks and best regards.
Fabio

FF2k25 · September 4, 2025, 9:16am

FF2k25 · September 4, 2025, 9:17am

FF2k25 · September 4, 2025, 9:18am

Target on the EDGE IMPULSE Object detection page is set to Raspberry Pi 5.
May be this error arise due to I’ve set the target to RPi5?
BR
Fabio

FF2k25 · September 4, 2025, 10:25am

Regarding your request about the hardware used this one at what hw is referring in details? I suppose that the training is made on the EDGE IMPULSE Server using the YOLOv5 model downloaded from GitHub and pushed on the account I’m using actually… It is right?
Thanks and best regards
F.

marcpous · September 4, 2025, 10:31am

Could you please share the address? i’m trying to reproduce!

FF2k25 · September 4, 2025, 10:42am

Here the link:

I’ve simply cloned the repo, then inside the folder I’ve used the two command on the CLI:

edge-impulse-blocks init
edge-impulse-blocks push

that is all I’ve did to upload the model on my EDGE IMPULSE account.

Project ID: 767584

Thanks!!
F.

FF2k25 · September 4, 2025, 2:10pm

Yep I’ve did another attempt using GPU setting into the dashboard and seems all was able to work nice and finish the train.
BR
Fabio