transpose, cross product, matrix product, element wise multiplication etc... Tensor (continued) • Attributes of a tensor 't': • t= torch.randn(1) • requires_grad - making a trainable parameter •By default

�e���� kj�SW���I�������������t��rP�l ������ bVt���Oho�1�3��/�40�kj��u���� Large-scale CelebFaces Attributes (CelebA) Dataset �774���221���.,����0�,����0�45�/,�7���,1,����721 ���������) ���(�����)�����)��

different data types for model and data will cause errors. Tensors – PyTorch v.s. NumPy ● Similar attributes PyTorch NumPy x.shape x.shape x.dtype x.dtype ref: https://github.com/wkentaro/pytorch-for-numpy-users