SpongeBab
commented
2 years ago Same error in yolov3, but only occur when I set 'batch-size' = 32. I tried bs =1,2,8,16.It worked well. Run the test.py in the yolov3. this is my option:
opt = parser.parse_args(['--weights', 'runs/train/desk2-1000-yolov3-b1-640/weights/best.pt',
'--data', 'data/desk2-1000.yaml',
'--batch-size', '32',
'--img-size', '640',
'--conf-thres', '0.001',
'--iou-thres', '0.65',
'--name', 'desk2-1000-yolov3-b32-640',
'--save-metrics'])the whole result:
val: Scanning '..\Dataset\desk2-1000\valid.cache' images and labels... 200 found, 0 missing, 0 empty, 0 corrupted: 100%|██████████| 200/200 [00:00<?, ?it/s]
Class Images Labels P R mAP@.5 mAP@.5:.95: 14%|█▍ | 1/7 [00:03<00:23, 3.97s/it]Exception in thread Thread-3:
Traceback (most recent call last):
File "D:\Miniconda\envs\yolov5\lib\threading.py", line 954, in _bootstrap_inner
self.run()
File "D:\Miniconda\envs\yolov5\lib\threading.py", line 892, in run
self._target(*self._args, **self._kwargs)
File "E:\yolov3\utils\plots.py", line 162, in plot_images
img = cv2.resize(img, (w, h))
cv2.error: OpenCV(4.5.2) C:\Users\runneradmin\AppData\Local\Temp\pip-req-build-m8us58q4\opencv\modules\core\src\alloc.cpp:73: error: (-4:Insufficient memory) Failed to allocate 2810880 bytes in function 'cv::OutOfMemoryError'
Exception in thread Thread-4:
Traceback (most recent call last):
File "D:\Miniconda\envs\yolov5\lib\threading.py", line 954, in _bootstrap_inner
self.run()
File "D:\Miniconda\envs\yolov5\lib\threading.py", line 892, in run
self._target(*self._args, **self._kwargs)
File "E:\yolov3\utils\plots.py", line 132, in plot_images
images = images.cpu().float().numpy()
RuntimeError: [enforce fail at ..\c10\core\CPUAllocator.cpp:75] data. DefaultCPUAllocator: not enough memory: you tried to allocate 99090432 bytes. Buy new RAM!
Class Images Labels P R mAP@.5 mAP@.5:.95: 29%|██▊ | 2/7 [00:06<00:16, 3.34s/it]Exception in thread Thread-6:
Traceback (most recent call last):
File "D:\Miniconda\envs\yolov5\lib\threading.py", line 954, in _bootstrap_inner
self.run()
File "D:\Miniconda\envs\yolov5\lib\threading.py", line 892, in run
self._target(*self._args, **self._kwargs)
File "E:\yolov3\utils\plots.py", line 132, in plot_images
images = images.cpu().float().numpy()
RuntimeError: [enforce fail at ..\c10\core\CPUAllocator.cpp:75] data. DefaultCPUAllocator: not enough memory: you tried to allocate 99090432 bytes. Buy new RAM!
Class Images Labels P R mAP@.5 mAP@.5:.95: 43%|████▎ | 3/7 [00:09<00:11, 2.92s/it]Exception in thread Thread-8:
Traceback (most recent call last):
File "D:\Miniconda\envs\yolov5\lib\threading.py", line 954, in _bootstrap_inner
self.run()
File "D:\Miniconda\envs\yolov5\lib\threading.py", line 892, in run
self._target(*self._args, **self._kwargs)
File "E:\yolov3\utils\plots.py", line 132, in plot_images
images = images.cpu().float().numpy()
RuntimeError: [enforce fail at ..\c10\core\CPUAllocator.cpp:75] data. DefaultCPUAllocator: not enough memory: you tried to allocate 99090432 bytes. Buy new RAM!
Class Images Labels P R mAP@.5 mAP@.5:.95: 100%|██████████| 7/7 [00:16<00:00, 2.35s/it]
all 200 5971 0.941 0.902 0.931 0.63
Speed: 16.5/3.5/19.9 ms inference/NMS/total per 640x640 image at batch-size 32
Results saved to runs\test\desk2-1000-yolov3-b32-6403
```****
glenn-jocher
github-actions[bot]
@glenn-jocher ,hi, today, when I update the yolov5 repo.I meet this error. I runed the val.py. I'm sure that I didn't make any change on the dataset or the model. I tried solve it but failed.Maybe it is because the multithread programming. can you have a look？
Edited: I tried bs=1,2,8...,the result is all the same.