Li-Chongyi / Zero-DCE

Zero-DCE code and model
799 stars 191 forks source link

CUDA out of memory #20

Open buptlj opened 3 years ago

buptlj commented 3 years ago

hi, thanks for your great work. I have a problem when i run lowlight_test.py. 刚开始执行没有问题,测试一定数量的图片之后,提示显存不足,暂时没发现什么问题。 ` data/test_data/DICM/32.jpg 0.001220703125 data/test_data/LIME/6.bmp 0.0012459754943847656 data/test_data/LIME/8.bmp 0.0011720657348632812 data/test_data/LIME/4.bmp 0.0012981891632080078 data/test_data/LIME/7.bmp 0.0016331672668457031 data/test_data/LIME/1.bmp 0.0012412071228027344 data/test_data/LIME/2.bmp 0.0011746883392333984 data/test_data/LIME/9.bmp 0.0011982917785644531 data/test_data/LIME/5.bmp Traceback (most recent call last): File "lowlight_test.py", line 63, in lowlight(image) File "lowlighttest.py", line 35, in lowlight ,enhancedimage, = DCE_net(data_lowlight) File "/home/mi/anaconda3/envs/zero-dce/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(*input, *kwargs) File "/home/mi/workspace/projects/low-light-enhancement/Zero-DCE/Zero-DCE_code/model.py", line 37, in forward x4 = self.relu(self.e_conv4(x3)) File "/home/mi/anaconda3/envs/zero-dce/lib/python3.8/site-packages/torch/nn/modules/module.py", line 722, in _call_impl result = self.forward(input, **kwargs) File "/home/mi/anaconda3/envs/zero-dce/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 419, in forward return self._conv_forward(input, self.weight) File "/home/mi/anaconda3/envs/zero-dce/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 415, in _conv_forward return F.conv2d(input, weight, self.bias, self.stride, RuntimeError: CUDA out of memory. Tried to allocate 368.00 MiB

`

buptlj commented 3 years ago

找到原因了,是data/test_data/LIME/5.bmp这张图片太大了,我测试机器显存2G。

frensher commented 3 years ago

为什么我300*300的图片都会报错