5.51 GiB 已分配； 417.00 MiB 免费；内存不足的 PyTorch CUDA 总共保留了 5.53 GiB
5.51 GiB already allocated; 417.00 MiB free; 5.53 GiB reserved in total by PyTorch CUDA out of memory
我不确定为什么 运行 此单元格会抛出 CUDA out of memory 错误，我该如何解决？每次我必须从 $ nvidi-smi jupyter notebook 的列表中执行一个 kill -9 PID，这个单元格就是 运行。重新开始后，我仍然遇到同样的问题。
#torch.autograd.set_detect_anomaly(True)
network = Network()
network.cuda()
criterion = nn.MSELoss()
optimizer = optim.Adam(network.parameters(), lr=0.0001)
loss_min = np.inf
num_epochs = 10
start_time = time.time()
for epoch in range(1,num_epochs+1):
loss_train = 0
loss_test = 0
running_loss = 0
network.train()
print('size of train loader is: ', len(train_loader))
for step in range(1,len(train_loader)+1):
##images, landmarks = next(iter(train_loader))
##print(type(images))
batch = next(iter(train_loader))
images, landmarks = batch['image'], batch['landmarks']
images = images.permute(0,3,1,2)
images = images.cuda()
#RuntimeError: Given groups=1, weight of size [64, 3, 7, 7], expected input[64, 600, 800, 3] to have 3 channels, but got 600 channels instead
landmarks = landmarks.view(landmarks.size(0),-1).cuda()
print('images shape: ', images.shape)
print('landmarks shape: ', landmarks.shape)
##images = torchvision.transforms.Normalize(images)
##landmarks = torchvision.transforms.Normalize(landmarks)
predictions = network(images)
# clear all the gradients before calculating them
optimizer.zero_grad()
# find the loss for the current step
loss_train_step = criterion(predictions.float(), landmarks.float())
print("type(loss_train_step) is: ", type(loss_train_step))
print("loss_train_step.dtype is: ",loss_train_step.dtype)
##loss_train_step = loss_train_step.to(torch.float32)
# calculate the gradients
loss_train_step.backward()
# update the parameters
optimizer.step()
loss_train += loss_train_step.item()
running_loss = loss_train/step
print_overwrite(step, len(train_loader), running_loss, 'train')
network.eval()
with torch.no_grad():
for step in range(1,len(test_loader)+1):
batch = next(iter(train_loader))
images, landmarks = batch['image'], batch['landmarks']
images = images.cuda()
landmarks = landmarks.view(landmarks.size(0),-1).cuda()
predictions = network(images)
# find the loss for the current step
loss_test_step = criterion(predictions, landmarks)
loss_test += loss_test_step.item()
running_loss = loss_test/step
print_overwrite(step, len(test_loader), running_loss, 'Testing')
loss_train /= len(train_loader)
loss_test /= len(test_loader)
print('\n--------------------------------------------------')
print('Epoch: {} Train Loss: {:.4f} Test Loss: {:.4f}'.format(epoch, loss_train, loss_test))
print('--------------------------------------------------')
if loss_test < loss_min:
loss_min = loss_test
torch.save(network.state_dict(), '../moth_landmarks.pth')
print("\nMinimum Test Loss of {:.4f} at epoch {}/{}".format(loss_min, epoch, num_epochs))
print('Model Saved\n')
print('Training Complete')
print("Total Elapsed Time : {} s".format(time.time()-start_time))
完整日志为：
size of train loader is: 12
images shape: torch.Size([64, 3, 600, 800])
landmarks shape: torch.Size([64, 8])
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-18-efa8f1a4056e> in <module>
44 ##landmarks = torchvision.transforms.Normalize(landmarks)
45
---> 46 predictions = network(images)
47
48 # clear all the gradients before calculating them
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
720 result = self._slow_forward(*input, **kwargs)
721 else:
--> 722 result = self.forward(*input, **kwargs)
723 for hook in itertools.chain(
724 _global_forward_hooks.values(),
<ipython-input-11-46116d2a7101> in forward(self, x)
10 def forward(self, x):
11 x = x.float()
---> 12 out = self.model(x)
13 return out
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
720 result = self._slow_forward(*input, **kwargs)
721 else:
--> 722 result = self.forward(*input, **kwargs)
723 for hook in itertools.chain(
724 _global_forward_hooks.values(),
~/anaconda3/lib/python3.7/site-packages/torchvision/models/resnet.py in forward(self, x)
218
219 def forward(self, x):
--> 220 return self._forward_impl(x)
221
222
~/anaconda3/lib/python3.7/site-packages/torchvision/models/resnet.py in _forward_impl(self, x)
206 x = self.maxpool(x)
207
--> 208 x = self.layer1(x)
209 x = self.layer2(x)
210 x = self.layer3(x)
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
720 result = self._slow_forward(*input, **kwargs)
721 else:
--> 722 result = self.forward(*input, **kwargs)
723 for hook in itertools.chain(
724 _global_forward_hooks.values(),
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/container.py in forward(self, input)
115 def forward(self, input):
116 for module in self:
--> 117 input = module(input)
118 return input
119
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
720 result = self._slow_forward(*input, **kwargs)
721 else:
--> 722 result = self.forward(*input, **kwargs)
723 for hook in itertools.chain(
724 _global_forward_hooks.values(),
~/anaconda3/lib/python3.7/site-packages/torchvision/models/resnet.py in forward(self, x)
57 identity = x
58
---> 59 out = self.conv1(x)
60 out = self.bn1(out)
61 out = self.relu(out)
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
720 result = self._slow_forward(*input, **kwargs)
721 else:
--> 722 result = self.forward(*input, **kwargs)
723 for hook in itertools.chain(
724 _global_forward_hooks.values(),
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/conv.py in forward(self, input)
417
418 def forward(self, input: Tensor) -> Tensor:
--> 419 return self._conv_forward(input, self.weight)
420
421 class Conv3d(_ConvNd):
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/conv.py in _conv_forward(self, input, weight)
414 _pair(0), self.dilation, self.groups)
415 return F.conv2d(input, weight, self.bias, self.stride,
--> 416 self.padding, self.dilation, self.groups)
417
418 def forward(self, input: Tensor) -> Tensor:
RuntimeError: CUDA out of memory. Tried to allocate 470.00 MiB (GPU 0; 7.80 GiB total capacity; 5.51 GiB already allocated; 417.00 MiB free; 5.53 GiB reserved in total by PyTorch)
这是在 运行 连接此单元格之后的 $ nvidia-smi 输出：
$ nvidia-smi
Tue Oct 13 23:14:01 2020
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 450.51.06 Driver Version: 450.51.06 CUDA Version: 11.0 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 GeForce RTX 2070 Off | 00000000:01:00.0 Off | N/A |
| N/A 47C P8 13W / N/A | 7609MiB / 7982MiB | 5% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 1424 G /usr/lib/xorg/Xorg 733MiB |
| 0 N/A N/A 1767 G /usr/bin/gnome-shell 426MiB |
| 0 N/A N/A 6420 G /usr/lib/firefox/firefox 2MiB |
| 0 N/A N/A 6949 G /usr/lib/firefox/firefox 2MiB |
| 0 N/A N/A 8888 G /usr/lib/firefox/firefox 2MiB |
| 0 N/A N/A 10610 G /usr/lib/firefox/firefox 2MiB |
| 0 N/A N/A 14943 G /usr/lib/firefox/firefox 2MiB |
| 0 N/A N/A 16181 C ...mona/anaconda3/bin/python 6429MiB |
+-----------------------------------------------------------------------------+
我有 NVIDIA GeForce RTX 2070 GPU。
我也切换了这两条线，但仍然没有机会，仍然是同样的错误：
images = images.permute(0,3,1,2)
images = images.cuda()
我还检查了 nvidia-smi 运行 在该单元上方的所有单元之后，其中 none 导致了这个 CUDA 内存不足错误。
在这里将 batch_size 从 64 更改为 2 解决了问题：
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=2, shuffle=True, num_workers=4)
*非常感谢 Sepehr Janghorbani 帮助我解决了这个问题。
我不确定为什么 运行 此单元格会抛出 CUDA out of memory 错误，我该如何解决？每次我必须从 $ nvidi-smi jupyter notebook 的列表中执行一个 kill -9 PID，这个单元格就是 运行。重新开始后，我仍然遇到同样的问题。
#torch.autograd.set_detect_anomaly(True)
network = Network()
network.cuda()
criterion = nn.MSELoss()
optimizer = optim.Adam(network.parameters(), lr=0.0001)
loss_min = np.inf
num_epochs = 10
start_time = time.time()
for epoch in range(1,num_epochs+1):
loss_train = 0
loss_test = 0
running_loss = 0
network.train()
print('size of train loader is: ', len(train_loader))
for step in range(1,len(train_loader)+1):
##images, landmarks = next(iter(train_loader))
##print(type(images))
batch = next(iter(train_loader))
images, landmarks = batch['image'], batch['landmarks']
images = images.permute(0,3,1,2)
images = images.cuda()
#RuntimeError: Given groups=1, weight of size [64, 3, 7, 7], expected input[64, 600, 800, 3] to have 3 channels, but got 600 channels instead
landmarks = landmarks.view(landmarks.size(0),-1).cuda()
print('images shape: ', images.shape)
print('landmarks shape: ', landmarks.shape)
##images = torchvision.transforms.Normalize(images)
##landmarks = torchvision.transforms.Normalize(landmarks)
predictions = network(images)
# clear all the gradients before calculating them
optimizer.zero_grad()
# find the loss for the current step
loss_train_step = criterion(predictions.float(), landmarks.float())
print("type(loss_train_step) is: ", type(loss_train_step))
print("loss_train_step.dtype is: ",loss_train_step.dtype)
##loss_train_step = loss_train_step.to(torch.float32)
# calculate the gradients
loss_train_step.backward()
# update the parameters
optimizer.step()
loss_train += loss_train_step.item()
running_loss = loss_train/step
print_overwrite(step, len(train_loader), running_loss, 'train')
network.eval()
with torch.no_grad():
for step in range(1,len(test_loader)+1):
batch = next(iter(train_loader))
images, landmarks = batch['image'], batch['landmarks']
images = images.cuda()
landmarks = landmarks.view(landmarks.size(0),-1).cuda()
predictions = network(images)
# find the loss for the current step
loss_test_step = criterion(predictions, landmarks)
loss_test += loss_test_step.item()
running_loss = loss_test/step
print_overwrite(step, len(test_loader), running_loss, 'Testing')
loss_train /= len(train_loader)
loss_test /= len(test_loader)
print('\n--------------------------------------------------')
print('Epoch: {} Train Loss: {:.4f} Test Loss: {:.4f}'.format(epoch, loss_train, loss_test))
print('--------------------------------------------------')
if loss_test < loss_min:
loss_min = loss_test
torch.save(network.state_dict(), '../moth_landmarks.pth')
print("\nMinimum Test Loss of {:.4f} at epoch {}/{}".format(loss_min, epoch, num_epochs))
print('Model Saved\n')
print('Training Complete')
print("Total Elapsed Time : {} s".format(time.time()-start_time))
完整日志为：
size of train loader is: 12
images shape: torch.Size([64, 3, 600, 800])
landmarks shape: torch.Size([64, 8])
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
<ipython-input-18-efa8f1a4056e> in <module>
44 ##landmarks = torchvision.transforms.Normalize(landmarks)
45
---> 46 predictions = network(images)
47
48 # clear all the gradients before calculating them
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
720 result = self._slow_forward(*input, **kwargs)
721 else:
--> 722 result = self.forward(*input, **kwargs)
723 for hook in itertools.chain(
724 _global_forward_hooks.values(),
<ipython-input-11-46116d2a7101> in forward(self, x)
10 def forward(self, x):
11 x = x.float()
---> 12 out = self.model(x)
13 return out
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
720 result = self._slow_forward(*input, **kwargs)
721 else:
--> 722 result = self.forward(*input, **kwargs)
723 for hook in itertools.chain(
724 _global_forward_hooks.values(),
~/anaconda3/lib/python3.7/site-packages/torchvision/models/resnet.py in forward(self, x)
218
219 def forward(self, x):
--> 220 return self._forward_impl(x)
221
222
~/anaconda3/lib/python3.7/site-packages/torchvision/models/resnet.py in _forward_impl(self, x)
206 x = self.maxpool(x)
207
--> 208 x = self.layer1(x)
209 x = self.layer2(x)
210 x = self.layer3(x)
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
720 result = self._slow_forward(*input, **kwargs)
721 else:
--> 722 result = self.forward(*input, **kwargs)
723 for hook in itertools.chain(
724 _global_forward_hooks.values(),
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/container.py in forward(self, input)
115 def forward(self, input):
116 for module in self:
--> 117 input = module(input)
118 return input
119
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
720 result = self._slow_forward(*input, **kwargs)
721 else:
--> 722 result = self.forward(*input, **kwargs)
723 for hook in itertools.chain(
724 _global_forward_hooks.values(),
~/anaconda3/lib/python3.7/site-packages/torchvision/models/resnet.py in forward(self, x)
57 identity = x
58
---> 59 out = self.conv1(x)
60 out = self.bn1(out)
61 out = self.relu(out)
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
720 result = self._slow_forward(*input, **kwargs)
721 else:
--> 722 result = self.forward(*input, **kwargs)
723 for hook in itertools.chain(
724 _global_forward_hooks.values(),
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/conv.py in forward(self, input)
417
418 def forward(self, input: Tensor) -> Tensor:
--> 419 return self._conv_forward(input, self.weight)
420
421 class Conv3d(_ConvNd):
~/anaconda3/lib/python3.7/site-packages/torch/nn/modules/conv.py in _conv_forward(self, input, weight)
414 _pair(0), self.dilation, self.groups)
415 return F.conv2d(input, weight, self.bias, self.stride,
--> 416 self.padding, self.dilation, self.groups)
417
418 def forward(self, input: Tensor) -> Tensor:
RuntimeError: CUDA out of memory. Tried to allocate 470.00 MiB (GPU 0; 7.80 GiB total capacity; 5.51 GiB already allocated; 417.00 MiB free; 5.53 GiB reserved in total by PyTorch)
这是在 运行 连接此单元格之后的 $ nvidia-smi 输出：
$ nvidia-smi
Tue Oct 13 23:14:01 2020
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 450.51.06 Driver Version: 450.51.06 CUDA Version: 11.0 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 GeForce RTX 2070 Off | 00000000:01:00.0 Off | N/A |
| N/A 47C P8 13W / N/A | 7609MiB / 7982MiB | 5% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 1424 G /usr/lib/xorg/Xorg 733MiB |
| 0 N/A N/A 1767 G /usr/bin/gnome-shell 426MiB |
| 0 N/A N/A 6420 G /usr/lib/firefox/firefox 2MiB |
| 0 N/A N/A 6949 G /usr/lib/firefox/firefox 2MiB |
| 0 N/A N/A 8888 G /usr/lib/firefox/firefox 2MiB |
| 0 N/A N/A 10610 G /usr/lib/firefox/firefox 2MiB |
| 0 N/A N/A 14943 G /usr/lib/firefox/firefox 2MiB |
| 0 N/A N/A 16181 C ...mona/anaconda3/bin/python 6429MiB |
+-----------------------------------------------------------------------------+
我有 NVIDIA GeForce RTX 2070 GPU。
我也切换了这两条线，但仍然没有机会，仍然是同样的错误：
images = images.permute(0,3,1,2)
images = images.cuda()
我还检查了 nvidia-smi 运行 在该单元上方的所有单元之后，其中 none 导致了这个 CUDA 内存不足错误。
在这里将 batch_size 从 64 更改为 2 解决了问题：
train_loader = torch.utils.data.DataLoader(train_dataset, batch_size=2, shuffle=True, num_workers=4)
*非常感谢 Sepehr Janghorbani 帮助我解决了这个问题。