I am new to pytorch and while I tried my graph neural network model, I faced some very weird accuracy. I tried with other related resources in internet and this site but can not figure out what is the problem .My model is :
class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = ChebConv(132, 32,20) # input layer
self.conv2 = ChebConv(32, 12,20)
def forward(self, data): #define forward network
x, edge_index = data.x, data.edge_index
x = self.conv1(x, edge_index)
x = F.relu(x)
x = self.conv2(x, edge_index)
Model=Net()
print(Model)
Training and Test function is:
optimizer = torch.optim.Adam(model.parameters(), lr=0.001, weight_decay=5e-4)
def train():
model.train()
cum_loss = 0
for data in dataset: # Iterate in batches over the training dataset.
data = data.to(device)
out = model(data) #, data.batch) # Perform a single forward pass.
loss = F.mse_loss(out, data.y)
#loss = criterion(out, data.y) # Compute the loss.
cum_loss += loss
loss.backward() # Derive gradients.
optimizer.step() # Update parameters based on gradients.
optimizer.zero_grad() # Clear gradients.
print(f'Epoch: {epoch:03d}, loss: {cum_loss/len(dataset):.4f}')
csvwriter.writerow([epoch, (cum_loss/len(dataset)).cpu().detach().numpy()])
filename = "output1.1.csv"
filename_label = "output_label1.csv"
fields = ['a', 'b', ...]
#test function
def test(loader):
model.eval()
with open(filename, 'w') as csvfile, open(filename_label, 'w') as csvoutput:
csvwriter = csv.writer(csvfile)
csvoutwriter = csv.writer(csvoutput)
csvwriter.writerow(fields)
csvoutwriter.writerow(fields)
correct = 0
for data in loader:
data = data.to(device)
out = model(data)
correct += int((out.argmax(-1)==data.y.view(-1,1)).sum())
for i in range(10):
csvwriter.writerow(out.cpu().detach().numpy()[i,:])
csvoutwriter.writerow((data.y.cpu().detach()).numpy()[i,:])
return correct / len(loader) # Derive ratio of correct predictions.
model.train()
filename_train = "trainloss1.1.csv"
with open(filename_train, 'w') as csvfile:
csvwriter = csv.writer(csvfile)
csvwriter.writerow(['Epoch', 'Loss'])
for epoch in range(300):
train()
test_acc = test(dataset)
print(f'Test Acc: {test_acc:.4f}')
I get this accuracy very low
Epoch: 000, loss: 4.2021
Test Acc: 9.9178
I am new to pytorch and while I tried my graph neural network model, I faced some very weird accuracy. I tried with other resources in internet but can not figure out what is the problem .My model is :
class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = ChebConv(132, 32,20) # input layer
self.conv2 = ChebConv(32, 12,20)
def forward(self, data): #define forward network
x, edge_index = data.x, data.edge_index
x = self.conv1(x, edge_index)
x = F.relu(x)
x = self.conv2(x, edge_index)
Model=Net()
print(Model)
Training and Test function is:
optimizer = torch.optim.Adam(model.parameters(), lr=0.001, weight_decay=5e-4)
def train():
model.train()
cum_loss = 0
for data in dataset: # Iterate in batches over the training dataset.
data = data.to(device)
out = model(data) #, data.batch) # Perform a single forward pass.
loss = F.mse_loss(out, data.y)
#loss = criterion(out, data.y) # Compute the loss.
cum_loss += loss
loss.backward() # Derive gradients.
optimizer.step() # Update parameters based on gradients.
optimizer.zero_grad() # Clear gradients.
print(f'Epoch: {epoch:03d}, loss: {cum_loss/len(dataset):.4f}')
csvwriter.writerow([epoch, (cum_loss/len(dataset)).cpu().detach().numpy()])
filename = "output1.1.csv"
filename_label = "output_label1.csv"
fields = ['a', 'b', ...]
#test function
def test(loader):
model.eval()
with open(filename, 'w') as csvfile, open(filename_label, 'w') as csvoutput:
csvwriter = csv.writer(csvfile)
csvoutwriter = csv.writer(csvoutput)
csvwriter.writerow(fields)
csvoutwriter.writerow(fields)
correct = 0
for data in loader:
data = data.to(device)
out = model(data)
correct += int((out.argmax(-1)==data.y.view(-1,1)).sum())
for i in range(10):
csvwriter.writerow(out.cpu().detach().numpy()[i,:])
csvoutwriter.writerow((data.y.cpu().detach()).numpy()[i,:])
return correct / len(loader) # Derive ratio of correct predictions.
model.train()
filename_train = "trainloss1.1.csv"
with open(filename_train, 'w') as csvfile:
csvwriter = csv.writer(csvfile)
csvwriter.writerow(['Epoch', 'Loss'])
for epoch in range(300):
train()
test_acc = test(dataset)
print(f'Test Acc: {test_acc:.4f}')
I get this accuracy very low
Epoch: 000, loss: 4.2021
Test Acc: 9.9178
previously I tried changing the correct parameter in test data stating as
correct += int((out.argmax(-1)==data.y).sum())
which results in
RuntimeError: The size of tensor a (10) must match the size of tensor b (12) at non-singleton dimension 1
I got this runtime error and tried
correct += int((out.argmax(-1)==data.y.view(-1,1)).sum())
but having very low accuracy as I stated. How can I fix this problem? Am I doing something wrong here? My data size in loader is
Data(edge_attr=[18], edge_index=[2, 18], x=[10, 132], y=[10, 12])