Closed GotRobbd closed 3 weeks ago
Could you please provide more details about your issue? What's the exact error message thrown?
This is the full terminal text I get whilst trying to run the code: Windows 11 Pro, Python 3.10.11 venv, with all dependecies installed
PS D:\> & d:/.venv3/Scripts/Activate.ps1
(.venv3) PS D:\> cd .\TinyissimoYOLO\
(.venv3) PS D:\TinyissimoYOLO> python --version
Python 3.10.11
(.venv3) PS D:\TinyissimoYOLO> python a_train_export.py
WARNING ⚠️ no model scale passed. Assuming scale='b'.
New https://pypi.org/project/ultralytics/8.2.36 available 😃 Update with 'pip install -U ultralytics'
Ultralytics YOLOv8.1.29 🚀 Python-3.10.11 torch-2.0.0+cu117 CUDA:0 (NVIDIA GeForce GTX 1660 Ti, 6144MiB)
engine\trainer: task=detect, mode=train, model=./ultralytics/cfg/models/tinyissimo/tinyissimo-v5.yaml, data=../Data/data.yaml, epochs=50, time=None, patience=100, batch=64, imgsz=96, save=True, save_period=-1, cache=False, device=None, workers=8, project=results, name=exp17, exist_ok=False, pretrained=True, optimizer=SGD, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=10, resume=False, amp=True, fraction=1.0, profile=False, freeze=None, multi_scale=False, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, split=val, save_json=False, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, vid_stride=1, stream_buffer=False, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, embed=None, show=False, save_frames=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, show_boxes=True, line_width=None, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=None, workspace=4, nms=False, lr0=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=7.5, cls=0.5, dfl=1.5, pose=12.0, kobj=1.0, label_smoothing=0.0, nbs=64, 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, auto_augment=randaugment, erasing=0.4, crop_fraction=1.0, cfg=None, tracker=botsort.yaml, save_dir=results\exp17
Overriding model.yaml nc=20 with nc=1
WARNING ⚠️ no model scale passed. Assuming scale='b'.
from n params module arguments
0 -1 1 1760 ultralytics.nn.modules.conv.Conv [3, 16, 6, 2, 2]
1 -1 1 3504 ultralytics.nn.modules.conv.Conv [16, 24, 3, 2]
2 -1 1 2736 ultralytics.nn.modules.block.C3 [24, 24, 1]
3 -1 1 8720 ultralytics.nn.modules.conv.Conv [24, 40, 3, 2]
4 -1 2 11520 ultralytics.nn.modules.block.C3 [40, 40, 2]
5 -1 1 28960 ultralytics.nn.modules.conv.Conv [40, 80, 3, 2]
6 -1 3 61600 ultralytics.nn.modules.block.C3 [80, 80, 3]
7 -1 1 115520 ultralytics.nn.modules.conv.Conv [80, 160, 3, 2]
8 -1 1 116160 ultralytics.nn.modules.block.C3 [160, 160, 1]
9 -1 1 64480 ultralytics.nn.modules.block.SPPF [160, 160, 5]
10 -1 1 12960 ultralytics.nn.modules.conv.Conv [160, 80, 1, 1]
11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
12 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1]
13 -1 1 35680 ultralytics.nn.modules.block.C3 [160, 80, 1, False]
14 -1 1 3280 ultralytics.nn.modules.conv.Conv [80, 40, 1, 1]
15 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
16 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1]
17 -1 1 9040 ultralytics.nn.modules.block.C3 [80, 40, 1, False]
18 -1 1 14480 ultralytics.nn.modules.conv.Conv [40, 40, 3, 2]
19 [-1, 14] 1 0 ultralytics.nn.modules.conv.Concat [1]
20 -1 1 29280 ultralytics.nn.modules.block.C3 [80, 80, 1, False]
21 -1 1 57760 ultralytics.nn.modules.conv.Conv [80, 80, 3, 2]
22 [-1, 10] 1 0 ultralytics.nn.modules.conv.Concat [1]
23 -1 1 116160 ultralytics.nn.modules.block.C3 [160, 160, 1, False]
24 [17, 20, 23] 1 429739 ultralytics.nn.modules.head.Detect [1, [40, 80, 160]]
tinyissimo-v5 summary: 262 layers, 1123339 parameters, 1123323 gradients
TensorBoard: Start with 'tensorboard --logdir results\exp17', view at http://localhost:6006/
Freezing layer 'model.24.dfl.conv.weight'
AMP: running Automatic Mixed Precision (AMP) checks with YOLOv8n...
AMP: checks passed ✅
train: Scanning D:\SmartLight.ai\HEIMDALL_LOCAL_SETUP\Data\train\labels.cache... 936 images, 465 backgrounds, 0 corrupt: 100%|██████████| 936/936 [00:00<?, ?it/s]
WARNING ⚠️ no model scale passed. Assuming scale='b'.
New https://pypi.org/project/ultralytics/8.2.36 available 😃 Update with 'pip install -U ultralytics'
Ultralytics YOLOv8.1.29 🚀 Python-3.10.11 torch-2.0.0+cu117 CUDA:0 (NVIDIA GeForce GTX 1660 Ti, 6144MiB)
engine\trainer: task=detect, mode=train, model=./ultralytics/cfg/models/tinyissimo/tinyissimo-v5.yaml, data=../Data/data.yaml, epochs=50, time=None, patience=100, batch=64, imgsz=96, save=True, save_period=-1, cache=False, device=None, workers=8, project=results, name=exp18, exist_ok=False, pretrained=True, optimizer=SGD, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=10, resume=False, amp=True, fraction=1.0, profile=False, freeze=None, multi_scale=False, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, split=val, save_json=False, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, vid_stride=1, stream_buffer=False, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, embed=None, show=False, save_frames=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, show_boxes=True, line_width=None, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=None, workspace=4, nms=False, lr0=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=7.5, cls=0.5, dfl=1.5, pose=12.0, kobj=1.0, label_smoothing=0.0, nbs=64, 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, auto_augment=randaugment, erasing=0.4, crop_fraction=1.0, cfg=None, tracker=botsort.yaml, save_dir=results\exp18
Overriding model.yaml nc=20 with nc=1
WARNING ⚠️ no model scale passed. Assuming scale='b'.
from n params module arguments
0 -1 1 1760 ultralytics.nn.modules.conv.Conv [3, 16, 6, 2, 2]
1 -1 1 3504 ultralytics.nn.modules.conv.Conv [16, 24, 3, 2]
2 -1 1 2736 ultralytics.nn.modules.block.C3 [24, 24, 1]
3 -1 1 8720 ultralytics.nn.modules.conv.Conv [24, 40, 3, 2]
4 -1 2 11520 ultralytics.nn.modules.block.C3 [40, 40, 2]
5 -1 1 28960 ultralytics.nn.modules.conv.Conv [40, 80, 3, 2]
6 -1 3 61600 ultralytics.nn.modules.block.C3 [80, 80, 3]
7 -1 1 115520 ultralytics.nn.modules.conv.Conv [80, 160, 3, 2]
8 -1 1 116160 ultralytics.nn.modules.block.C3 [160, 160, 1]
9 -1 1 64480 ultralytics.nn.modules.block.SPPF [160, 160, 5]
10 -1 1 12960 ultralytics.nn.modules.conv.Conv [160, 80, 1, 1]
11 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
12 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1]
13 -1 1 35680 ultralytics.nn.modules.block.C3 [160, 80, 1, False]
14 -1 1 3280 ultralytics.nn.modules.conv.Conv [80, 40, 1, 1]
15 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
16 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1]
17 -1 1 9040 ultralytics.nn.modules.block.C3 [80, 40, 1, False]
18 -1 1 14480 ultralytics.nn.modules.conv.Conv [40, 40, 3, 2]
19 [-1, 14] 1 0 ultralytics.nn.modules.conv.Concat [1]
20 -1 1 29280 ultralytics.nn.modules.block.C3 [80, 80, 1, False]
21 -1 1 57760 ultralytics.nn.modules.conv.Conv [80, 80, 3, 2]
22 [-1, 10] 1 0 ultralytics.nn.modules.conv.Concat [1]
23 -1 1 116160 ultralytics.nn.modules.block.C3 [160, 160, 1, False]
24 [17, 20, 23] 1 429739 ultralytics.nn.modules.head.Detect [1, [40, 80, 160]]
tinyissimo-v5 summary: 262 layers, 1123339 parameters, 1123323 gradients
TensorBoard: Start with 'tensorboard --logdir results\exp18', view at http://localhost:6006/
Freezing layer 'model.24.dfl.conv.weight'
AMP: running Automatic Mixed Precision (AMP) checks with YOLOv8n...
AMP: checks passed ✅
train: Scanning D:\SmartLight.ai\HEIMDALL_LOCAL_SETUP\Data\train\labels.cache... 936 images, 465 backgrounds, 0 corrupt: 100%|██████████| 936/936 [00:00<?, ?it/s]
Traceback (most recent call last):
File "<string>", line 1, in <module>
File "C:\Users\Ana\AppData\Local\Programs\Python\Python310\lib\multiprocessing\spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "C:\Users\Ana\AppData\Local\Programs\Python\Python310\lib\multiprocessing\spawn.py", line 125, in _main
prepare(preparation_data)
File "C:\Users\Ana\AppData\Local\Programs\Python\Python310\lib\multiprocessing\spawn.py", line 236, in prepare
_fixup_main_from_path(data['init_main_from_path'])
File "C:\Users\Ana\AppData\Local\Programs\Python\Python310\lib\multiprocessing\spawn.py", line 287, in _fixup_main_from_path
main_content = runpy.run_path(main_path,
File "C:\Users\Ana\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 289, in run_path
return _run_module_code(code, init_globals, run_name,
File "C:\Users\Ana\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 96, in _run_module_code
_run_code(code, mod_globals, init_globals,
File "C:\Users\Ana\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code
exec(code, run_globals)
File "D:\TinyissimoYOLO\a_train_export.py", line 12, in <module>
model.train(data="../Data/data.yaml", project="results", name="exp", optimizer='SGD', imgsz=img_size, epochs=50, batch=64)
File "D:\TinyissimoYOLO\ultralytics\engine\model.py", line 655, in train
self.trainer.train()
File "D:\TinyissimoYOLO\ultralytics\engine\trainer.py", line 213, in train
self._do_train(world_size)
File "D:\TinyissimoYOLO\ultralytics\engine\trainer.py", line 327, in _do_train
self._setup_train(world_size)
File "D:\TinyissimoYOLO\ultralytics\engine\trainer.py", line 291, in _setup_train
self.train_loader = self.get_dataloader(self.trainset, batch_size=batch_size, rank=RANK, mode="train")
File "D:\TinyissimoYOLO\ultralytics\models\yolo\detect\train.py", line 55, in get_dataloader
return build_dataloader(dataset, batch_size, workers, shuffle, rank) # return dataloader
File "D:\TinyissimoYOLO\ultralytics\data\build.py", line 114, in build_dataloader
return InfiniteDataLoader(
File "D:\TinyissimoYOLO\ultralytics\data\build.py", line 40, in __init__
self.iterator = super().__iter__()
File "D:\.venv3\lib\site-packages\torch\utils\data\dataloader.py", line 442, in __iter__
return self._get_iterator()
File "D:\.venv3\lib\site-packages\torch\utils\data\dataloader.py", line 388, in _get_iterator
return _MultiProcessingDataLoaderIter(self)
File "D:\.venv3\lib\site-packages\torch\utils\data\dataloader.py", line 1043, in __init__
w.start()
File "C:\Users\Ana\AppData\Local\Programs\Python\Python310\lib\multiprocessing\process.py", line 121, in start
self._popen = self._Popen(self)
File "C:\Users\Ana\AppData\Local\Programs\Python\Python310\lib\multiprocessing\context.py", line 224, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "C:\Users\Ana\AppData\Local\Programs\Python\Python310\lib\multiprocessing\context.py", line 336, in _Popen
return Popen(process_obj)
File "C:\Users\Ana\AppData\Local\Programs\Python\Python310\lib\multiprocessing\popen_spawn_win32.py", line 45, in __init__
prep_data = spawn.get_preparation_data(process_obj._name)
File "C:\Users\Ana\AppData\Local\Programs\Python\Python310\lib\multiprocessing\spawn.py", line 154, in get_preparation_data
_check_not_importing_main()
File "C:\Users\Ana\AppData\Local\Programs\Python\Python310\lib\multiprocessing\spawn.py", line 134, in _check_not_importing_main
raise RuntimeError('''
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.
This probably means that you are not using fork to start your
child processes and you have forgotten to use the proper idiom
in the main module:
if __name__ == '__main__':
freeze_support()
...
The "freeze_support()" line can be omitted if the program
is not going to be frozen to produce an executable.
It just hangs at the error, the only way to cancel the training process is by closing/killing the terminal.
Hey @GotRobbd,
Seems like this is an issue with the way Windows (which we don't usually use) handles subprocesses. See: https://stackoverflow.com/questions/18204782/runtimeerror-on-windows-trying-python-multiprocessing
In the a_train_export.py
could you try doing as the error message suggests and wrapping everything in a def main():
and then calling this main from the if __name__ == '__main__'
guard?
Something like this:
import torch
from ultralytics import YOLO
def main():
device = torch.device("cuda")
model_name = "./ultralytics/cfg/models/tinyissimo/tinyissimo-v8.yaml"
model = YOLO(model_name)
img_size = 256
input_size = (1, 1, img_size, img_size)
# Train
model.train(data="VOC.yaml", project="results", name="exp", optimizer='SGD', imgsz=img_size, epochs=1, batch=64)
# Export
model.export(format="onnx", project="results", name="exp", imgsz=[img_size,img_size])
if __name__ == '__main__':
main()
Hey @mandulaj ,
I have just tested the code above and it works! Thank you so much!
It would be very helpful for others if this can be either noted or pushed into the repository to prevent such scenario.
Certainly, I think @mojulian can do that
Trying to train the model on a CPU works as expected. However, when trying to run the training process through CUDA, the code halts and throws this error:
Is there a way to fix this?