I’m using Pytorch Lightning. Here’s the model definition:
import torch
from torch import nn
# creates network class
class Net(pl.LightningModule):
def __init__(self):
super().__init__()
# defines conv layers
self.conv_layer_b1 = nn.Sequential(
nn.Conv2d(in_channels=3, out_channels=32,
kernel_size=3, padding=1),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2),
nn.Flatten(),
)
# passes dummy x matrix to find the input size of the fc layer
x = torch.randn(1, 3, 800, 600)
self._to_linear = None
self.forward(x)
# defines fc layer
self.fc_layer = nn.Sequential(
nn.Linear(in_features=self._to_linear,
out_features=256),
nn.ReLU(),
nn.Linear(256, 5),
)
# defines accuracy metric
self.accuracy = pl.metrics.Accuracy()
self.confusion_matrix = pl.metrics.ConfusionMatrix(num_classes=5)
def forward(self, x):
x = self.conv_layer_b1(x)
if self._to_linear is None:
# does not run fc layer if input size is not determined yet
self._to_linear = x.shape[1]
else:
x = self.fc_layer(x)
return x
def cross_entropy_loss(self, logits, y):
criterion = nn.CrossEntropyLoss()
return criterion(logits, y)
def training_step(self, train_batch, batch_idx):
x, y = train_batch
logits = self.forward(x)
train_loss = self.cross_entropy_loss(logits, y)
train_acc = self.accuracy(logits, y)
train_cm = self.confusion_matrix(logits, y)
self.log('train_loss', train_loss)
self.log('train_acc', train_acc)
self.log('train_cm', train_cm)
return train_loss
def validation_step(self, val_batch, batch_idx):
x, y = val_batch
logits = self.forward(x)
val_loss = self.cross_entropy_loss(logits, y)
val_acc = self.accuracy(logits, y)
return {'val_loss': val_loss, 'val_acc': val_acc}
def validation_epoch_end(self, outputs):
avg_val_loss = torch.stack([x['val_loss'] for x in outputs]).mean()
avg_val_acc = torch.stack([x['val_acc'] for x in outputs]).mean()
self.log("val_loss", avg_val_loss)
self.log("val_acc", avg_val_acc)
def configure_optimizers(self):
optimizer = torch.optim.Adam(self.parameters(), lr=0.0008)
return optimizer
The issue is probably not the machine since I’m using a cloud instance with 60 GBs of RAM and 12 GBs of VRAM. Whenever I run this model even for a single epoch, I get an out of memory error. On the CPU it looks like this:
RuntimeError: [enforce fail at CPUAllocator.cpp:64] . DefaultCPUAllocator: can't allocate memory: you tried to allocate 1966080000 bytes. Error code 12 (Cannot allocate memory)
and on the GPU it looks like this:
RuntimeError: CUDA out of memory. Tried to allocate 7.32 GiB (GPU 0; 11.17 GiB total capacity; 4.00 KiB already allocated; 2.56 GiB free; 2.00 MiB reserved in total by PyTorch)
Clearing the cache and reducing the batch size did not work. I’m a novice so clearly something here is exploding but I can’t tell what. Any help would be appreciated.
Thank you!