Hi everyone!
i am a beginner.
i am trying to train this network (from Udacity course - public repository) on google Colab
at first i have trained it regular.
but then i have try using GPU to see it its actually faster
for this i have used : (each one where needed)
“device = torch.device(“cuda” if torch.cuda.is_available() else “cpu”)”
“model.to(device)”
“data.to(device), target.to(device)”
i got an error - please see after the attached code
any help would be appreciated.
######################################################################
#the code:
import libraries
import torch
import numpy as np
from six.moves import urllib
opener = urllib.request.build_opener()
opener.addheaders = [(‘User-agent’, ‘Mozilla/5.0’)]
urllib.request.install_opener(opener)
from torchvision import datasets
import torchvision.transforms as transforms
number of subprocesses to use for data loading
num_workers = 0
how many samples per batch to load
batch_size = 20
convert data to torch.FloatTensor
transform = transforms.ToTensor()
choose the training and test datasets
train_data = datasets.MNIST(root=‘data’, train=True,
download=True, transform=transform)
test_data = datasets.MNIST(root=‘data’, train=False,
download=True, transform=transform)
prepare data loaders
train_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size,
num_workers=num_workers)
test_loader = torch.utils.data.DataLoader(test_data, batch_size=batch_size,
num_workers=num_workers)
import torch.nn as nn
import torch.nn.functional as F
TODO: Define the NN architecture
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
# linear layer (784 -> 10 hidden node)
self.fc1 = nn.Linear(28 * 28, 512)
self.fc2 = nn.Linear(512, 512)
self.fc3 = nn.Linear(512, 10)
self.dropout = nn.Dropout(0.2)
def forward(self, x):
# flatten image input
#x = x.view(-1, 28 * 28)
x.view(x.shape[0], -1)
# add hidden layer, with relu activation function
x = self.dropout(F.relu(self.fc1(x)))
x = self.dropout(F.relu(self.fc2(x)))
x = F.relu(self.fc3(x))
return x
initialize the NN
Use GPU if it’s available
device = torch.device(“cuda” if torch.cuda.is_available() else “cpu”)
model = Net()
print(model)
model.to(device) #but i get errors!!! and i dont know why!
specify loss function
criterion = nn.CrossEntropyLoss()
specify optimizer
optimizer = torch.optim.Adam(model.parameters(), lr= 0.003)
number of epochs to train the model
n_epochs = 30 # suggest training between 20-50 epochs
connect model to device
#model.train() # prep model for training
for epoch in range(n_epochs):
# monitor training loss
train_loss = 0.0
###################
# train the model #
###################
for data, target in train_loader:
#connect data and target to device:
data.to(device), target.to(device)
# clear the gradients of all optimized variables
optimizer.zero_grad()
# forward pass: compute predicted outputs by passing inputs to the model
output = model(data)
# calculate the loss
loss = criterion(output, target)
# backward pass: compute gradient of the loss with respect to model parameters
loss.backward()
# perform a single optimization step (parameter update)
optimizer.step()
# update running training loss
train_loss += loss.item()*data.size(0)
# print training statistics
# calculate average loss over an epoch
train_loss = train_loss/len(train_loader.dataset)
print('Epoch: {} \tTraining Loss: {:.6f}'.format(
epoch+1,
train_loss
))
RuntimeError Traceback (most recent call last)
in ()
24 optimizer.zero_grad()
25 # forward pass: compute predicted outputs by passing inputs to the model
—> 26 output = model(data)
27 # calculate the loss
28 loss = criterion(output, target)
4 frames
/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py in linear(input, weight, bias)
1846 if has_torch_function_variadic(input, weight, bias):
1847 return handle_torch_function(linear, (input, weight, bias), input, weight, bias=bias)
→ 1848 return torch._C._nn.linear(input, weight, bias)
1849
1850
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument mat2 in method wrapper_mm)