What’s the difference between reshape and view in pytorch?

by

torch.view has existed for a long time. It will return a tensor with the new shape. The returned tensor will share the underling data with the original tensor.
See the documentation here.

On the other hand, it seems that torch.reshape has been introduced recently in version 0.4. According to the document, this method will

Returns a tensor with the same data and number of elements as input, but with the specified shape. When possible, the returned tensor will be a view of input. Otherwise, it will be a copy. Contiguous inputs and inputs with compatible strides can be reshaped without copying, but you should not depend on the copying vs. viewing behavior.

It means that torch.reshape may return a copy or a view of the original tensor. You can not count on that to return a view or a copy. According to the developer:

if you need a copy use clone() if you need the same storage use view(). The semantics of reshape() are that it may or may not share the storage and you don’t know beforehand.

Another difference is that reshape() can operate on both contiguous and non-contiguous tensor while view() can only operate on contiguous tensor. Also see here about the meaning of contiguous.

More Related Contents:

  1. Best way to save a trained model in PyTorch? [closed]
  2. Why `torch.cuda.is_available()` returns False even after installing pytorch with cuda?
  3. How do I save a trained model in PyTorch?
  4. How to initialize weights in PyTorch?
  5. How do I initialize weights in PyTorch?
  6. What does model.train() do in PyTorch?
  7. How does Pytorch’s “Fold” and “Unfold” work?
  8. Heroku: slug size too large after installing Pytorch
  9. What does model.eval() do in pytorch?
  10. PyTorch NotImplementedError in forward
  11. Pytorch – Inferring linear layer in_features
  12. PyTorch: How to use DataLoaders for custom Datasets
  13. Pytorch – RuntimeError: Trying to backward through the graph a second time, but the buffers have already been freed
  14. How do I print the model summary in PyTorch?
  15. What’s the difference between torch.stack() and torch.cat() functions?
  16. ModuleNotFoundError: No module named ‘tools.nnwrap’
  17. How do I check if PyTorch is using the GPU?
  18. How do I visualize a net in Pytorch?
  19. Pytorch RuntimeError: The size of tensor a (4) must match the size of tensor b (3) at non-singleton dimension 0
  20. Is .data still useful in pytorch?
  21. Pytorch: how to add L1 regularizer to activations?
  22. How to construct a network with two inputs in PyTorch
  23. RuntimeError: Input type (torch.FloatTensor) and weight type (torch.cuda.FloatTensor) should be the same
  24. How can I fix this strange error: “RuntimeError: CUDA error: out of memory”?
  25. Data Augmentation in PyTorch
  26. How do I split a custom dataset into training and test datasets?
  27. RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! when resuming training
  28. Install PyTorch from requirements.txt
  29. Pytorch ValueError: optimizer got an empty parameter list
  30. PyTorch Binary Classification – same network structure, ‘simpler’ data, but worse performance?

Leave a Comment