RuntimeError: CUDA out of memory. Tried to allocate 42.00 MiB (GPU 0; 3.81 GiB total capacity; 2.79 GiB already allocated; 25.44 MiB free; 2.92 GiB reserved in total by PyTorch)

[imenselmi]

RuntimeError Traceback (most recent call last)
Cell In[27], line 44
42 # Specify the optimizer with a lower learning rate
43 optimizer = torch.optim.Adam(model.parameters(), lr=1e-4)
---> 44 _ = train_model(model,
45 criterion,
46 dataloaders,
47 optimizer,
48 bpath=exp_directory,
49 metrics=metrics,
50 num_epochs=epochs)
52 # Save the trained model
53 torch.save(model, exp_directory / 'weights.pt')

File ~/Documents/5G/DeepLabv3FineTuning/trainer.py:49, in train_model(model, criterion, dataloaders, optimizer, metrics, bpath, num_epochs)
47 # track history if only in train
48 with torch.set_grad_enabled(phase == 'Train'):
---> 49 outputs = model(inputs)
50 loss = criterion(outputs['out'], masks)
51 y_pred = outputs['out'].data.cpu().numpy().ravel()

File ~/.local/lib/python3.8/site-packages/torch/nn/modules/module.py:722, in Module._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(),
725 self._forward_hooks.values()):
726 hook_result = hook(self, input, result)

File ~/.local/lib/python3.8/site-packages/torchvision/models/segmentation/_utils.py:20, in _SimpleSegmentationModel.forward(self, x)
18 input_shape = x.shape[-2:]
19 # contract: features is a dict of tensors
---> 20 features = self.backbone(x)
22 result = OrderedDict()
23 x = features["out"]

File ~/.local/lib/python3.8/site-packages/torch/nn/modules/module.py:722, in Module._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(),
725 self._forward_hooks.values()):
726 hook_result = hook(self, input, result)

File ~/.local/lib/python3.8/site-packages/torchvision/models/_utils.py:63, in IntermediateLayerGetter.forward(self, x)
61 out = OrderedDict()
62 for name, module in self.items():
---> 63 x = module(x)
64 if name in self.return_layers:
65 out_name = self.return_layers[name]

File ~/.local/lib/python3.8/site-packages/torch/nn/modules/module.py:722, in Module._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(),
725 self._forward_hooks.values()):
726 hook_result = hook(self, input, result)

File ~/.local/lib/python3.8/site-packages/torch/nn/modules/container.py:117, in Sequential.forward(self, input)
115 def forward(self, input):
116 for module in self:
--> 117 input = module(input)
118 return input

File ~/.local/lib/python3.8/site-packages/torch/nn/modules/module.py:722, in Module._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(),
725 self._forward_hooks.values()):
726 hook_result = hook(self, input, result)

File ~/.local/lib/python3.8/site-packages/torchvision/models/resnet.py:112, in Bottleneck.forward(self, x)
109 out = self.bn2(out)
110 out = self.relu(out)
--> 112 out = self.conv3(out)
113 out = self.bn3(out)
115 if self.downsample is not None:

File ~/.local/lib/python3.8/site-packages/torch/nn/modules/module.py:722, in Module._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(),
725 self._forward_hooks.values()):
726 hook_result = hook(self, input, result)

File ~/.local/lib/python3.8/site-packages/torch/nn/modules/conv.py:419, in Conv2d.forward(self, input)
418 def forward(self, input: Tensor) -> Tensor:
--> 419 return self._conv_forward(input, self.weight)

File ~/.local/lib/python3.8/site-packages/torch/nn/modules/conv.py:415, in Conv2d._conv_forward(self, input, weight)
411 if self.padding_mode != 'zeros':
412 return F.conv2d(F.pad(input, self._reversed_padding_repeated_twice, mode=self.padding_mode),
413 weight, self.bias, self.stride,
414 _pair(0), self.dilation, self.groups)
--> 415 return F.conv2d(input, weight, self.bias, self.stride,
416 self.padding, self.dilation, self.groups)

RuntimeError: CUDA out of memory. Tried to allocate 42.00 MiB (GPU 0; 3.81 GiB total capacity; 2.79 GiB already allocated; 25.44 MiB free; 2.92 GiB reserved in total by PyTorch)

[silviazpi]

I fixed it by reducing the input image size but in a 4GB gpu it might not be runnable