Is .data still useful in pytorch?

by

.data was an attribute of Variable (object representing Tensor with history tracking e.g. for automatic update), not Tensor. Actually, .data was giving access to the Variable‘s underlying Tensor.

However, since PyTorch version 0.4.0, Variable and Tensor have been merged (into an updated Tensor structure), so .data disappeared along the previous Variable object (well Variable is still there for backward-compatibility, but is deprecated).

Paragraph from Release Notes for version 0.4.0 (I recommend reading the whole section about Variable/Tensor updates):

What about .data?

.data was the primary way to get the underlying Tensor from a
Variable. After this merge, calling y = x.data still has similar
semantics. So y will be a Tensor that shares the same data with
x, is unrelated with the computation history of x, and has
requires_grad=False.

However, .data can be unsafe in some cases. Any changes on x.data
wouldn’t be tracked by autograd, and the computed gradients would be
incorrect if x is needed in a backward pass. A safer alternative is
to use x.detach(), which also returns a Tensor that shares data
with requires_grad=False, but will have its in-place changes
reported by autograd if x is needed in backward.

More Related Contents:

  1. Best way to save a trained model in PyTorch? [closed]
  2. How do I save a trained model in PyTorch?
  3. How to print the value of a Tensor object in TensorFlow?
  4. Understanding tensordot
  5. AttributeError: ‘Tensor’ object has no attribute ‘numpy’
  6. Why `torch.cuda.is_available()` returns False even after installing pytorch with cuda?
  7. Python and OpenSSL version reference issue on OS X
  8. How do I tell a Python script to use a particular version
  9. Heroku: slug size too large after installing Pytorch
  10. Checking a Python module version at runtime
  11. How to: Macports select python
  12. Python IDLE: Change Python Version
  13. PyTorch NotImplementedError in forward
  14. PyTorch: How to use DataLoaders for custom Datasets
  15. Pytorch – RuntimeError: Trying to backward through the graph a second time, but the buffers have already been freed
  16. How do I print the model summary in PyTorch?
  17. What’s the difference between reshape and view in pytorch?
  18. What’s the difference between torch.stack() and torch.cat() functions?
  19. ModuleNotFoundError: No module named ‘tools.nnwrap’
  20. How do I check if PyTorch is using the GPU?
  21. How to find which version of TensorFlow is installed in my system?
  22. Pytorch RuntimeError: The size of tensor a (4) must match the size of tensor b (3) at non-singleton dimension 0
  23. Pytorch: how to add L1 regularizer to activations?
  24. ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer`
  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