ivan-alles
ivan-alles
Need this as well.
Have the same problem with a binary classifier with the fully connected output layer of size (B, 1), when I select this layer as the target, in combination with BinaryClassifierOutputTarget....
Looks like the dimension of the input is not an integer. Is input int self._localizer.predict(input) a numpy array (it should be)?
The model for prediction differs from the model for training, but I cannot explain this in just a couple of words.
I need this too, to computing elements of a rotation matrix.
What is the rough expected number of downloaded videos? I managed to download about 18500 train and 450 test videos. And I have seen a lot of failed downloads too.
I also always had problems with gridsample on MacOS. It is so annoying that you cannot control whether an operation is executed on ANE or CPU or on GPU!