Giving output of one neural network as an input to another in pytorch

I have a pretrained convolution neural network which produces and output of shape (X,164) where X is the number of test examples. So output layer has 164 nodes. I want to take this output and give this two another network which is simply a fully connected neural network whereby the first layer has 64 nodes and output layer has 1 node with sigmoid function. How can I do that? My first network looks like:

class LambdaBase(nn.Sequential):
    def __init__(self, fn, *args):
        super(LambdaBase, self).__init__(*args)
        self.lambda_func = fn

    def forward_prepare(self, input):
        output = []
        for module in self._modules.values():
            output.append(module(input))
        return output if output else input

class Lambda(LambdaBase):
    def forward(self, input):
        return self.lambda_func(self.forward_prepare(input))

class LambdaMap(LambdaBase):
    def forward(self, input):
        return list(map(self.lambda_func,self.forward_prepare(input)))

class LambdaReduce(LambdaBase):
    def forward(self, input):
        return reduce(self.lambda_func,self.forward_prepare(input))

def get_model(load_weights = True):
    pretrained_model_reloaded_th = nn.Sequential( # Sequential,
        nn.Conv2d(4,300,(19, 1)),
        nn.BatchNorm2d(300),
        nn.ReLU(),
        nn.MaxPool2d((3, 1),(3, 1)),
        nn.Conv2d(300,200,(11, 1)),
        nn.BatchNorm2d(200),
        nn.ReLU(),
        nn.MaxPool2d((4, 1),(4, 1)),
        nn.Conv2d(200,200,(7, 1)),
        nn.BatchNorm2d(200),
        nn.ReLU(),
        nn.MaxPool2d((4, 1),(4, 1)),
        Lambda(lambda x: x.view(x.size(0),-1)), # Reshape,
        nn.Sequential(Lambda(lambda x: x.view(1,-1) if 1==len(x.size()) else x ),nn.Linear(2000,1000)), # Linear,
        nn.BatchNorm1d(1000,1e-05,0.1,True),#BatchNorm1d,
        nn.ReLU(),
        nn.Dropout(0.3),
        nn.Sequential(Lambda(lambda x: x.view(1,-1) if 1==len(x.size()) else x ),nn.Linear(1000,1000)), # Linear,
        nn.BatchNorm1d(1000,1e-05,0.1,True),#BatchNorm1d,
        nn.ReLU(),
        nn.Dropout(0.3),
        nn.Sequential(Lambda(lambda x: x.view(1,-1) if 1==len(x.size()) else x ),nn.Linear(1000,164)), # Linear,
        nn.Sigmoid(),
    )
    if load_weights:
        sd = torch.load('pretrained_model.pth')
        pretrained_model_reloaded_th.load_state_dict(sd)
    return  pretrained_model_reloaded_th

model = get_model(load_weights = True)

If I want to get output for this model on my test set I can simply do:

output = model(X.float())

This produces a final output of shape (X,164). Now I want to take this output and give it to another neural network mentioned above. How can I combine these two networks now and how can I optimise these networks together? Insights will be appreciated.

Edit: My second model is:

# define second model architecture
next_model = nn.Sequential(
    nn.Linear(164, 64),
    nn.ReLU(),
    nn.Linear(64, 1),
    nn.Sigmoid()
)

# print model architecture
print(next_model)

And my classifier is trained as:

for epoch in range(2):  # loop over the dataset multiple times

    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # get the inputs; data is a list of [inputs, labels]
        inputs, labels = data

        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.item()
        if i % 2000 == 1999:    # print every 2000 mini-batches
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

print('Finished Training')

Answer

If the two models do not need any adapting to be done at the first’s model output, you can simply use a nn.Sequential:

>>> network = nn.Sequential(model, next_model)

And use it the same way as you did with model:

>>> output = network(X.float())

Which will correspond to next_model(model(X.float())).

Advertisement

Answer