CUDA error: out of memory

[DLYL2019]

你好，显卡GTX2080Ti,设置batch_size为2了，为什么运行train.py出现
Traceback (most recent call last):
File "F:/YL_file/compite/yoloV5/yolov5/train.py", line 395, in
train(hyp)
File "F:/YL_file/compite/yoloV5/yolov5/train.py", line 81, in train
model = Model(opt.cfg, nc=data_dict['nc']).to(device)
File "G:\vision\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 432, in to
return self._apply(convert)
File "G:\vision\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 208, in _apply
module._apply(fn)
File "G:\vision\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 208, in _apply
module._apply(fn)
File "G:\vision\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 208, in _apply
module._apply(fn)
[Previous line repeated 1 more time]
File "G:\vision\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 230, in _apply
param_applied = fn(param)
File "G:\vision\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 430, in convert
return t.to(device, dtype if t.is_floating_point() else None, non_blocking)
RuntimeError: CUDA error: out of memory

[DLLXW]

如果不是尺度太大，那就是你有其它进程占用了显卡，你仔细检查下吧。batch=2,就算是1024的输入尺度也不会超显存的

你好，显卡GTX2080Ti,设置batch_size为2了，为什么运行train.py出现
Traceback (most recent call last):
File "F:/YL_file/compite/yoloV5/yolov5/train.py", line 395, in
train(hyp)
File "F:/YL_file/compite/yoloV5/yolov5/train.py", line 81, in train
model = Model(opt.cfg, nc=data_dict['nc']).to(device)
File "G:\vision\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 432, in to
return self._apply(convert)
File "G:\vision\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 208, in _apply
module._apply(fn)
File "G:\vision\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 208, in _apply
module._apply(fn)
File "G:\vision\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 208, in _apply
module._apply(fn)
[Previous line repeated 1 more time]
File "G:\vision\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 230, in _apply
param_applied = fn(param)
File "G:\vision\anaconda3\lib\site-packages\torch\nn\modules\module.py", line 430, in convert
return t.to(device, dtype if t.is_floating_point() else None, non_blocking)
RuntimeError: CUDA error: out of memory

如果不是尺度太大，那就是你有其它进程占用了显卡，你仔细检查下吧。batch=2,就算是1024的输入尺度也不会超显存的