torch tensor에서 새로운 축을 만들고자 할 때 사용할 수 있는 방법
ex) torch.unsqueeze(input, dim=0)
https://pytorch.org/docs/stable/generated/torch.unsqueeze.html
torch.unsqueeze — PyTorch 2.1 documentation
Shortcuts
pytorch.org
numpy 에서도 비슷하게 사용가능
input[None, :]
input[:, None]
input[:, None, None]
https://stackoverflow.com/questions/37867354/in-numpy-what-does-selection-by-none-do
In numpy, what does selection by [:,None] do?
I'm taking the Udacity course on deep learning and I came across the following code: def reformat(dataset, labels): dataset = dataset.reshape((-1, image_size * image_size)).astype(np.float32) ...
stackoverflow.com
numpy에서는 다음 방법들로 축을 늘릴 수 있다.
np.expand_dims(input, axis)
input[:, np.newaxis]
input.reshape()
다른 접근법
np.tile()
np.stack()