In this view x.view(-1) is a weird flatten layer but missing the squeeze (i.e. adding a dimension of 1). Adding this squeeze or removing it is usually important for the code to actually run.
Simply put, torch.Tensor.view() which is inspired by numpy.ndarray.reshape() or numpy.reshape(), creates a new view of the tensor, as long as the new shape is compatible with the shape of the original tensor.
python - What does view () do in PyTorch? - Stack Overflow
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 ...
Make your own Street View collections when you take your camera on a drive, ride, or walk. Your recorded video is converted into Street View when you publish it. Data about your location is used to geotag and position your recording on the map. Connections between individual 360 photos appear 4 days or longer from completed publishing.
Why doesn't the auto increment of the identity column work when trying to insert using the view and how can I fix it? Scenario is: The different users of the database should only be able to work with their own rows in that table. Therefore I am trying to use the view as a kind of security by checking the username. Is there any better solution?