Hello everyone,
I’m trying to classify some drugs like very active, active, non active (label: 0, 1, 2) against the cancer. To do that I built a Graph Convolutional Network using PyTorch Geometric, this is the code:
n_features = 14
# definenet
class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = GCNConv(n_features, 50, cached=False)
self.bn1 = BatchNorm1d(50)
self.conv2 = GCNConv(50, 25, cached=False)
self.bn2 = BatchNorm1d(25)
self.fc1 = Linear(25, 25)
self.bn3 = BatchNorm1d(25)
self.fc2 = Linear(25, 25)
self.fc3 = Linear(25, 3)
def forward(self, x, edge_index, batch):
x = F.relu(self.conv1(x, edge_index))
x = self.bn1(x)
x = F.relu(self.conv2(x, edge_index))
x = self.bn2(x)
x = global_add_pool(x, batch)
x = F.relu(self.fc1(x))
x = self.bn3(x)
x = F.relu(self.fc2(x))
x = F.dropout(x, p=0.2, training=self.training)
x = self.fc3(x)
x = F.softmax(x, dim=1)
return x
My dataset contain 2476 samples where:
- 0, 1184 samples;
- 1, 826 samples;
- 2, 466 samples.
Every nodes of a graph contain a nodes features matrix with 14 features. When I train the net the loss seems to go down well, but the accuracy grows slowly and very badly. Below I show you the charts of the loss (train and val), of the accuracy (train and val) and the training loop that I use. What could I do to improve my model’s performance? Thank you all!
model = Net()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001,
weight_decay=0.0001)
criterion = torch.nn.CrossEntropyLoss()
def train():
model.train()
loss_all = 0
for data in train_loader:
optimizer.zero_grad()
output = model(data.x, data.edge_index, data.batch)
loss = criterion(output, data.y)
loss.backward()
loss_all += loss.item() * data.num_graphs
optimizer.step()
return loss_all / len(train_loader.dataset)
def test_loss(loader):
total_loss_val = 0
with torch.no_grad():
for data in loader:
output = model(data.x, data.edge_index, data.batch)
batch_loss = criterion(output, data.y)
total_loss_val += batch_loss.item() * data.num_graphs
return total_loss_val / len(loader.dataset)
def test(loader):
model.eval()
correct = 0
for data in loader:
output = model(data.x, data.edge_index, data.batch)
pred = output.max(dim=1)[1]
correct += pred.eq(data.y).sum().item()
return correct / len(loader.dataset)
hist = {"train_loss":[], "val_loss":[], "acc":[], "test_acc":[]}
for epoch in range(1, 301):
train_loss = train()
val_loss = test_loss(val_loader)
train_acc = test(train_loader)
test_acc = test(val_loader)
hist["train_loss"].append(train_loss)
hist["val_loss"].append(val_loss)
hist["acc"].append(train_acc)
hist["test_acc"].append(test_acc)
print(f'Epoch: {epoch}, Train loss: {train_loss:.3}, Val loss: {val_loss:.3}, Train_acc: {train_acc:.3}, Test_acc: {test_acc:.3}')
