TENSORS

Tensor初始化：

1. Directly from data：

   Tensors can be created directly from data. The data type is automatically inferred.

   data = [[1, 2],[3, 4]]
   x_data = torch.tensor(data)

2. From a NumPy array Tensors can be created from NumPy arrays

   np_array = np.array(data)
   x_np = torch.from_numpy(np_array)

3. Attributes of a Tensor 

   Tensor attributes describe their shape, datatype, and the device on which they are stored.

4. tensor operations, including arithmetic, linear algebra, matrix manipulation (transposing, indexing, slicing), sampling and more are comprehensively describedhttps://pytorch.org/docs/stable/torch.html

5. Bridge with NumPy

   t = torch.ones(5)

   n = t.numpy()

   n = np.ones(5)
   t = torch.from_numpy(n)