RuntimeError: Too many open files when I use pytorch dataloader. (Not opening any files) - neural-network

Question

I am trying to build and train a neural network using more low level pytorch.
I have the following simple toy code that defines and trains a 6-layer fully connected neural network. The dataset is from a simple sinusoidal function.
# initialise network weights
W1 = torch.randn((1, 30), requires_grad=True)
W2 = torch.randn((30, 30), requires_grad=True)
W3 = torch.randn((30, 30), requires_grad=True)
W4 = torch.randn((30, 30), requires_grad=True)
W5 = torch.randn((30, 30), requires_grad=True)
W6 = torch.randn((30, 1), requires_grad=True)
B1 = torch.randn((30), requires_grad=True)
B2 = torch.randn((30), requires_grad=True)
B3 = torch.randn((30), requires_grad=True)
B4 = torch.randn((30), requires_grad=True)
B5 = torch.randn((30), requires_grad=True)
B6 = torch.randn((1), requires_grad=True)
def Neural_net(x, W1, W2, W3, W4, W5 , W6, B1, B2, B3, B4, B5, B6):
# calculate hidden and output layers
h1 = torch.tanh((x # W1) + B1)
h2 = torch.tanh((h1 # W2) + B2)
h3 = torch.tanh((h2 # W3) + B3)
h4 = torch.tanh((h3 # W4) + B4)
h5 = torch.tanh((h4 # W5) + B5)
output = (h5 # W6) + B6
return output
# generating dataset
features = torch.linspace(1,20,50)
features = features.view(len(features),1)
labels = torch.sin(0.5*features)
# Creating Dataloader
data_size = np.shape(features)[0]
data_set = torch.FloatTensor(features)
labels = torch.FloatTensor(labels)
dataset = TensorDataset(data_set, labels)
num_batches = 10
dataloader = torch.utils.data.DataLoader(dataset, batch_size=data_size//num_batches,
shuffle=True, num_workers=2, drop_last=False)
# training
num_epochs = 10000
criterion = torch.nn.MSELoss()
h = 0.01/num_batches
for epoch in range(num_epochs):
for i, data in enumerate(dataloader):
x = data[0]
y = data[1]
dL1 = 0
dL2 = 0
dL3 = 0
dL4 = 0
dL5 = 0
dL6 = 0
dLb1 = 0
dLb2 = 0
dLb3 = 0
dLb4 = 0
dLb5 = 0
dLb6 = 0
# forward
outputs = Neural_net(x, W1, W2, W3, W4, W5,W6, B1, B2, B3, B4, B5, B6)
loss = criterion(outputs, y)
# backward
dL1 = torch.autograd.grad(loss,W1,create_graph=True)[0]
dL2 = torch.autograd.grad(loss,W2,create_graph=True)[0]
dL3 = torch.autograd.grad(loss,W3,create_graph=True)[0]
dL4 = torch.autograd.grad(loss,W4,create_graph=True)[0]
dL5 = torch.autograd.grad(loss,W5,create_graph=True)[0]
dL6 = torch.autograd.grad(loss,W6,create_graph=True)[0]
dLb1 = torch.autograd.grad(loss,B1,create_graph=True)[0]
dLb2 = torch.autograd.grad(loss,B2,create_graph=True)[0]
dLb3 = torch.autograd.grad(loss,B3,create_graph=True)[0]
dLb4 = torch.autograd.grad(loss,B4,create_graph=True)[0]
dLb5 = torch.autograd.grad(loss,B5,create_graph=True)[0]
dLb6 = torch.autograd.grad(loss,B6,create_graph=True)[0]
# optimise
W1 = W1 - h * dL1
W2 = W2 - h * dL2
W3 = W3 - h * dL3
W4 = W4 - h * dL4
W5 = W5 - h * dL5
W6 = W6 - h * dL6
#
B1 = B1 - h * dLb1
B2 = B2 - h * dLb2
B3 = B3 - h * dLb3
B4 = B4 - h * dLb4
B5 = B5 - h * dLb5
B6 = B6 - h * dLb6
if epoch%10 == 0:
print('epoch = ',epoch,'loss = ', loss)
The problem is, that while the code seems to work at first, training the neural network for a number of epochs, the code stops with the following Runtime error after some time:
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
Input In [24], in <cell line: 5>()
3 h = 0.01/num_batches
5 for epoch in range(num_epochs): # loop over the dataset multiple times
----> 7 for i, data in enumerate(dataloader):#, 0):
8 x = data[0]
9 y = data[1]
File ~/anaconda3/lib/python3.8/site-packages/torch/utils/data/dataloader.py:517, in _BaseDataLoaderIter.__next__(self)
515 if self._sampler_iter is None:
516 self._reset()
--> 517 data = self._next_data()
518 self._num_yielded += 1
519 if self._dataset_kind == _DatasetKind.Iterable and \
520 self._IterableDataset_len_called is not None and \
521 self._num_yielded > self._IterableDataset_len_called:
File ~/anaconda3/lib/python3.8/site-packages/torch/utils/data/dataloader.py:1182, in _MultiProcessingDataLoaderIter._next_data(self)
1179 return self._process_data(data)
1181 assert not self._shutdown and self._tasks_outstanding > 0
-> 1182 idx, data = self._get_data()
1183 self._tasks_outstanding -= 1
1184 if self._dataset_kind == _DatasetKind.Iterable:
1185 # Check for _IterableDatasetStopIteration
File ~/anaconda3/lib/python3.8/site-packages/torch/utils/data/dataloader.py:1148, in _MultiProcessingDataLoaderIter._get_data(self)
1144 # In this case, `self._data_queue` is a `queue.Queue`,. But we don't
1145 # need to call `.task_done()` because we don't use `.join()`.
1146 else:
1147 while True:
-> 1148 success, data = self._try_get_data()
1149 if success:
1150 return data
File ~/anaconda3/lib/python3.8/site-packages/torch/utils/data/dataloader.py:1013, in _MultiProcessingDataLoaderIter._try_get_data(self, timeout)
1011 except OSError as e:
1012 if e.errno == errno.EMFILE:
-> 1013 raise RuntimeError(
1014 "Too many open files. Communication with the"
1015 " workers is no longer possible. Please increase the"
1016 " limit using `ulimit -n` in the shell or change the"
1017 " sharing strategy by calling"
1018 " `torch.multiprocessing.set_sharing_strategy('file_system')`"
1019 " at the beginning of your code") from None
1020 raise
RuntimeError: Too many open files. Communication with the workers is no longer possible. Please increase the limit using `ulimit -n` in the shell or change the sharing strategy by calling `torch.multiprocessing.set_sharing_strategy('file_system')` at the beginning of your code
Any help would be very appreciated.