RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same

by

You get this error because your model is on the GPU, but your data is on the CPU. So, you need to send your input tensors to the GPU.

inputs, labels = data                         # this is what you had
inputs, labels = inputs.cuda(), labels.cuda() # add this line

Or like this, to stay consistent with the rest of your code:

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

inputs, labels = inputs.to(device), labels.to(device)

The same error will be raised if your input tensors are on the GPU but your model weights aren’t. In this case, you need to send your model weights to the GPU.

model = MyModel()

if torch.cuda.is_available():
    model.cuda()

See the documentation for cuda(), and its opposite, cpu().

More Related Contents:

  1. How to initialize weights in PyTorch?
  2. How do I initialize weights in PyTorch?
  3. How does Pytorch’s “Fold” and “Unfold” work?
  4. What does model.eval() do in pytorch?
  5. What’s the difference between torch.stack() and torch.cat() functions?
  6. PyTorch Binary Classification – same network structure, ‘simpler’ data, but worse performance?
  7. Will it lead to Overfitting / Curse of Dimensionality
  8. How to get the location of all text present in an image using OpenCV?
  9. Best way to save a trained model in PyTorch? [closed]
  10. What is a `”Python”` layer in caffe?
  11. How to apply gradient clipping in TensorFlow?
  12. How do I save a trained model in PyTorch?
  13. Keras Sequential model input layer
  14. Why do we need to call zero_grad() in PyTorch?
  15. Does Any one got “AttributeError: ‘str’ object has no attribute ‘decode’ ” , while Loading a Keras Saved Model
  16. PyTorch NotImplementedError in forward
  17. How can I use a pre-trained neural network with grayscale images?
  18. How to understand the term `tensor` in TensorFlow?
  19. Pytorch – RuntimeError: Trying to backward through the graph a second time, but the buffers have already been freed
  20. Removing then Inserting a New Middle Layer in a Keras Model
  21. Unbalanced data and weighted cross entropy
  22. What is the role of TimeDistributed layer in Keras?
  23. How to handle non-determinism when training on a GPU?
  24. keras: how to save the training history attribute of the history object
  25. How to construct a network with two inputs in PyTorch
  26. How to compute jaccard similarity from a pandas dataframe
  27. How to fix “ResourceExhaustedError: OOM when allocating tensor”
  28. How do I split a custom dataset into training and test datasets?
  29. RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! when resuming training
  30. Pytorch ValueError: optimizer got an empty parameter list

Leave a Comment