PyTorch NotImplementedError in forward

Question

import torch
import torch.nn as nn

device = torch.device('cuda' if torch.cuda.is_available() else 
'cpu')

class Model(nn.Module):
    def __init__(self):
        super(Model, self).__init__()
        self.layer = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=3, stride=1, padding=1),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2), # 16x16x650
            nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1), # 32x16x650
            nn.ReLU(),
            nn.Dropout2d(0.5),
            nn.Conv2d(32, 64, kernel_size=3, stride=1, padding=1), # 64x16x650
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2), # 64x8x325
            nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
            nn.ReLU()) # 64x8x325

        self.fc = nn.Sequential(
            nn.Linear(64*8*325, 128),
            nn.ReLU(),
            nn.Linear(128, 256),
            nn.ReLU(),
            nn.Linear(256, 1),
        )

        def forward(self, x):
            out = self.layer1(x)
            out = self.layer2(out)
            out = out.reshape(out.size(0), -1)
            out = self.fc(out)
            return out

# HYPERPARAMETER
learning_rate = 0.0001 
num_epochs = 15

import data

def main():
    model = Model().to(device)

    criterion = nn.CrossEntropyLoss()
    optimizer = torch.optim.Adam(model.parameters(), 
lr=learning_rate)

    total_step = len(data.train_loader)
    for epoch in range(num_epochs):
        for i, (images, labels) in enumerate(data.train_loader):
            images = images.to(device)
            labels = labels.to(device)

            outputs = model(images)
            loss = criterion(outputs, labels)

            optimizer.zero_grad()
            loss.backward()
            optimizer.step()

        if (i + 1) % 100 == 0:
            print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
                  .format(epoch + 1, num_epochs, i + 1, total_step, loss.item()))

    model.eval()
    with torch.no_grad():
        correct = 0
        total = 0
        for images, labels in data.test_loader:
            images = images.to(device)
            labels = labels.to(device)
            outputs = model(images)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()

        print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))

if __name__ == '__main__':
    main()

Error:

File "/home/rladhkstn8/Desktop/SWID/tmp/pycharm_project_853/model.py", line 82, in <module>
    main()
  File "/home/rladhkstn8/Desktop/SWID/tmp/pycharm_project_853/model.py", line 56, in main
    outputs = model(images)
  File "/home/rladhkstn8/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in __call__
    result = self.forward(*input, **kwargs)
  File "/home/rladhkstn8/anaconda3/lib/python3.6/site-packages/torch/nn/modules/module.py", line 83, in forward
    raise NotImplementedError
NotImplementedError

I do not know where the problem is. I know that NotImplementedError should be implemented, but it happens when there is unimplemented code.

Solution 1

please look carefully at the indentation of your __init__ function: your forward is part of __init__ not part of your module.

Solution 2

This error happens when you don't implement the required method from super class, in my case, i had typo on the function name forward. I recommend you check your code indentation.

Comments

[codecubed]

This can also happen if you try to call forward on a ModuleList instead of Sequential

[Sameen]

I don't understand what you mean. A code example would have been helpful.

[pydrink]

@samisnotinsane If you were to hold a ruler vertical from where you have defined __init__ and let it run vertical down your code, forward should be defined where that ruler hits its line. Instead, yours is indented one tab in from the ruler, i.e. there is a space of one tab between the ruler and forward. You have indented def forward with two tabs instead of one like def __init__. This means that you've defined forward within __init__, when it is its own method, independent of __init__.