I am having errors in executing the train function of my code in MLP.
This is the error:
mat1 and mat2 shapes cannot be multiplied (128x10 and 48x10)
My code for the train function is this:
class net(nn.Module):
def __init__(self, input_dim2, hidden_dim2, output_dim2):
super(net, self).__init__()
self.input_dim2 = input_dim2
self.fc1 = nn.Linear(input_dim2, hidden_dim2)
self.relu = nn.ReLU()
self.fc2 = nn.Linear(hidden_dim2, hidden_dim2)
self.fc3 = nn.Linear(hidden_dim2, output_dim2)
def forward(self, x):
x = self.fc1(x)
x = self.relu(x)
x = self.fc2(x)
x = self.relu(x)
x = self.fc3(x)
x = F.softmax(self.fc3(x))
return x
model = net(input_dim2, hidden_dim2, output_dim2) #create the network
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.RMSprop(model.parameters(), lr = learning_rate2)
def train(num_epochs2):
for i in range(num_epochs2):
tmp_loss = []
for (x,y) in train_loader:
print(y.shape)
print(x.shape)
outputs = model(x) #forward pass
print(outputs.shape)
loss = criterion(outputs, y) #loss computation
tmp_loss.append(loss.item()) #recording the loss
optimizer.zero_grad() #all the accumulated gradient
loss.backward() #auto-differentiaton - accumulation of gradient
optimizer.step() # a gradient step
print("Loss at {}th epoch: {}".format(i, np.mean(tmp_loss)))
I don't know where I'm wrong. My code seems to work okay.
From the limited message, I guess the place you are wrong are the following snippets:
x = self.fc3(x)
x = F.softmax(self.fc3(x))
Try to replace with:
x = self.fc3(x)
x = F.softmax(x)
A good question should include: error backtrace information and complete toy example which could repeat the errors!