While trying to train my model with 2 targets, I get the error…“ValueError: Target size (torch.Size([1, 1])) must be the same as input size (torch.Size([1, 2]))”. I have a data set with 2 targets. I tried a lot even by resizing the tensors but no use. Also if I make the output_dim = 1, it always predicts the same class out of two.
** Loading Training data
class SwelltrainDataset(T.utils.data.Dataset):
def __init__(self, Swelltrain):
sc = StandardScaler()
X_tr = sc.fit_transform(X_train)
Y_tr = y_train
self.X_tr = torch.tensor(X_tr, dtype = torch.float32)
self.Y_tr = torch.tensor(Y_tr, dtype = torch.float32)
def __len__(self):
return len(self.Y_tr)
def __getitem__(self, idx):
return self.X_tr[idx], self.Y_tr[idx]
train_ds = SwelltrainDataset(Swelltrain)
bat_size = 1
idx = np.append(np.where(train_ds.Y_tr == 0)[0],
np.where(train_ds.Y_tr == 1)[0],
)
train_ds.X_tr = train_ds.X_tr[idx]
train_ds.Y_tr = train_ds.Y_tr[idx]
train_ldr = T.utils.data.DataLoader(train_ds,
batch_size=bat_size, shuffle=True)
batch = next(iter(train_ldr))
I am using LSTM Model with dimensions: input_dim = 16, hidden_dim = 100, layer_dim = 1, output_dim = 2
class LSTMModel(nn.Module):
def __init__(self, input_dim, hidden_dim, layer_dim, output_dim):
super(LSTMModel, self).__init__()
self.hidden_dim = hidden_dim
self.layer_dim = layer_dim
self.lstm = nn.LSTM(input_dim, hidden_dim, layer_dim, dropout=1, batch_first=True, )
self.fc = nn.Linear(hidden_dim, output_dim)
def forward(self, x):
h0 = torch.zeros(self.layer_dim, x.size(0), self.hidden_dim).requires_grad_()
c0 = torch.zeros(self.layer_dim, x.size(0), self.hidden_dim).requires_grad_()
x, (hn, cn) = self.lstm(x, (h0.detach(), c0.detach()))
x = self.fc(x[:, -1, :])
return (x)
***Model Training
optimizer = optim.Adam(model.parameters(), lr=0.001)
loss_func = nn.BCEWithLogitsLoss()
epochs = 2
loss_list = []
model.train()
for epoch in range(epochs):
total_loss = []
for X_tr, Y_tr in train_ldr:
X_tr = X_tr.unsqueeze(1)
Y_tr = Y_tr.type(torch.LongTensor)
Y_tr = Y_tr.unsqueeze(1)
optimizer.zero_grad()
output = model(X_tr.float())
pred = output.argmax(dim=1, keepdim=True)
loss = loss_func(output, Y_tr.float())
loss.backward()
optimizer.step()
total_loss.append(loss.item())
loss_list.append(sum(total_loss)/len(total_loss))
print('Training [{:.0f}%]\tLoss: {:.4f}'.format(
100. * (epoch + 1) / epochs, loss_list[-1]))