This code runs with no problem in local machine with RTX 3080. When I run it in Azure Cluster using MLOps Pipeline Templates, I get this error:
import time
import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
start_time = time.time()
# Define the transforms for the dataset
transform_train = transforms.Compose([
transforms.RandomCrop(32, padding=4),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
transform_test = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
# Load the CIFAR-10 dataset
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform_train)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=128, shuffle=True, num_workers=4)
testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform_test)
testloader = torch.utils.data.DataLoader(testset, batch_size=128, shuffle=False, num_workers=4)
# Define the ResNet50 model
model = torchvision.models.resnet50(pretrained=True)
num_features = model.fc.in_features
model.fc = nn.Linear(num_features, 10)
# Move the model to the GPU
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)
# Define the loss function and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)
# Train the model for 100 epochs
for epoch in range(2):
# for epoch in range(100):
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
inputs, labels = data
inputs, labels = inputs.to(device), labels.to(device)
optimizer.zero_grad()
outputs = model(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
print('[Epoch %d] loss: %.3f' % (epoch + 1, running_loss / len(trainloader)))
# Evaluate the model on the test set
correct = 0
total = 0
with torch.no_grad():
for data in testloader:
inputs, labels = data
inputs, labels = inputs.to(device), labels.to(device)
outputs = model(inputs)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Test accuracy: %.2f %%' % (100 * correct / total))
end_time = time.time()
elapsed_time = start_time - end_time
print('elapsed time: ', elapsed_time)
error:
Traceback (most recent call last):
File "/opt/conda/lib/python3.8/urllib/request.py", line 1354, in do_open
h.request(req.get_method(), req.selector, req.data, headers,
File "/opt/conda/lib/python3.8/http/client.py", line 1256, in request
self._send_request(method, url, body, headers, encode_chunked)
File "/opt/conda/lib/python3.8/http/client.py", line 1302, in _send_request
self.endheaders(body, encode_chunked=encode_chunked)
File "/opt/conda/lib/python3.8/http/client.py", line 1251, in endheaders
self._send_output(message_body, encode_chunked=encode_chunked)
File "/opt/conda/lib/python3.8/http/client.py", line 1011, in _send_output
self.send(msg)
File "/opt/conda/lib/python3.8/http/client.py", line 951, in send
self.connect()
File "/opt/conda/lib/python3.8/http/client.py", line 1418, in connect
super().connect()
File "/opt/conda/lib/python3.8/http/client.py", line 922, in connect
self.sock = self._create_connection(
File "/opt/conda/lib/python3.8/socket.py", line 787, in create_connection
for res in getaddrinfo(host, port, 0, SOCK_STREAM):
File "/opt/conda/lib/python3.8/socket.py", line 918, in getaddrinfo
for res in _socket.getaddrinfo(host, port, family, type, proto, flags):
socket.gaierror: [Errno -3] Temporary failure in name resolution
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "train.py", line 23, in <module>
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform_train)
File "/opt/conda/lib/python3.8/site-packages/torchvision/datasets/cifar.py", line 65, in __init__
self.download()
File "/opt/conda/lib/python3.8/site-packages/torchvision/datasets/cifar.py", line 141, in download
download_and_extract_archive(self.url, self.root, filename=self.filename, md5=self.tgz_md5)
File "/opt/conda/lib/python3.8/site-packages/torchvision/datasets/utils.py", line 430, in download_and_extract_archive
download_url(url, download_root, filename, md5)
File "/opt/conda/lib/python3.8/site-packages/torchvision/datasets/utils.py", line 131, in download_url
url = _get_redirect_url(url, max_hops=max_redirect_hops)
File "/opt/conda/lib/python3.8/site-packages/torchvision/datasets/utils.py", line 79, in _get_redirect_url
with urllib.request.urlopen(urllib.request.Request(url, headers=headers)) as response:
File "/opt/conda/lib/python3.8/urllib/request.py", line 222, in urlopen
return opener.open(url, data, timeout)
File "/opt/conda/lib/python3.8/urllib/request.py", line 525, in open
response = self._open(req, data)
File "/opt/conda/lib/python3.8/urllib/request.py", line 542, in _open
result = self._call_chain(self.handle_open, protocol, protocol +
File "/opt/conda/lib/python3.8/urllib/request.py", line 502, in _call_chain
result = func(*args)
File "/opt/conda/lib/python3.8/urllib/request.py", line 1397, in https_open
return self.do_open(http.client.HTTPSConnection, req,
File "/opt/conda/lib/python3.8/urllib/request.py", line 1357, in do_open
raise URLError(err)
urllib.error.URLError: <urlopen error [Errno -3] Temporary failure in name resolution>