DEV Community

Super Kai (Kazuya Ito)
Super Kai (Kazuya Ito)

Posted on • Edited on

float_power in PyTorch

#python #pytorch #floatpower #power

Buy Me a Coffee☕

*Memos:

float_power() can get the 0D or more D tensor of the zero or more powers of float or complex from two of the 0D or more D tensors of zero or more elements or the 0D or more D tensor of zero or more elements and a scalar as shown below:

*Memos:

  • float_power() can be used with torch or a tensor.
  • The 1st argument(input) with torch(Type:tensor or scalar of int, float, complex or bool) or using a tensor(Type:tensor of int, float, complex or bool)(Required). *torch must use a scalar without input=.
  • The 2nd argument with torch or the 1st argument with a tensor is exponent(Required-Type:tensor or scalar of int, float, complex or bool).
  • There is out argument with torch(Optional-Default:None-Type:tensor): *Memos:
    • out= must be used.
    • My post explains out argument.
  • The combination of a scalar(input or a tensor) and a scalar(exponent) cannot be used. 
import torch tensor1 = torch.tensor(-3.) tensor2 = torch.tensor([-4., -3., -2., -1., 0., 1., 2., 3.]) torch.float_power(input=tensor1, exponent=tensor2) tensor1.float_power(exponent=tensor2) # tensor([1.2346e-02, -3.7037e-02, 1.1111e-01, -3.3333e-01, # 1.0000e+00, -3.0000e+00, 9.0000e+00, -2.7000e+01], # dtype=torch.float64)  torch.float_power(-3., exponent=tensor2) # tensor([1.2346e-02, -3.7037e-02, 1.1111e-01, -3.3333e-01, # 1.0000e+00, -3.0000e+00, 9.0000e+00, -2.7000e+01], # dtype=torch.float64)  torch.float_power(input=tensor1, exponent=-3.) # tensor(-0.0370, dtype=torch.float64)  tensor1 = torch.tensor([-3., 1., -2., 3., 5., -5., 0., -4.]) tensor2 = torch.tensor([-4., -3., -2., -1., 0., 1., 2., 3.]) torch.float_power(input=tensor1, exponent=tensor2) # tensor([1.2346e-02, 1.0000e+00, 2.5000e-01, 3.3333e-01, # 1.0000e+00, -5.0000e+00, 0.0000e+00, -6.4000e+01], # dtype=torch.float64)  torch.float_power(-3., exponent=tensor2) # tensor([1.2346e-02, -3.7037e-02, 1.1111e-01, -3.3333e-01, # 1.0000e+00, -3.0000e+00, 9.0000e+00, -2.7000e+01], # dtype=torch.float64)  torch.float_power(input=tensor1, exponent=-3.) # tensor([-0.0370, 1.0000, -0.1250, 0.0370, # 0.0080, -0.0080, inf, -0.0156], dtype=torch.float64)  tensor1 = torch.tensor([[-3., 1., -2., 3.], [5., -5., 0., -4.]]) tensor2 = torch.tensor([0., 1., 2., 3.]) torch.float_power(input=tensor1, exponent=tensor2) # tensor([[1., 1., 4., 27.], [1., -5., 0., -64.]], # dtype=torch.float64)  torch.float_power(-3., exponent=tensor2) # tensor([1., -3., 9., -27.], dtype=torch.float64)  torch.float_power(input=tensor1, exponent=-3.) # tensor([[-0.0370, 1.0000, -0.1250, 0.0370], # [0.0080, -0.0080, inf, -0.0156]], # dtype=torch.float64)  tensor1 = torch.tensor([[[-3., 1.], [-2., 3.]], [[5., -5.], [0., -4.]]]) tensor2 = torch.tensor([2., 3.]) torch.float_power(input=tensor1, exponent=tensor2) # tensor([[[9., 1.], [4., 27.]], # [[25., -125.], [0., -64.]]], dtype=torch.float64)  torch.float_power(-3., exponent=tensor2) # tensor([9., -27.], dtype=torch.float64)  torch.float_power(input=tensor1, exponent=-3.) # tensor([[[-0.0370, 1.0000], [-0.1250, 0.0370]], # [[0.0080, -0.0080], [inf, -0.0156]]], # dtype=torch.float64)  tensor1 = torch.tensor([[[-3, 1], [-2, 3]], [[5, -5], [0, -4]]]) tensor2 = torch.tensor([2, 3]) torch.float_power(input=tensor1, exponent=tensor2) # tensor([[[9., 1.], [4., 27.]], # [[25., -125.], [0., -64.]]], dtype=torch.float64)  torch.float_power(-3, exponent=tensor2) # tensor([9., -27.], dtype=torch.float64)  torch.float_power(input=tensor1, exponent=-3) # tensor([[[-0.0370, 1.0000], [-0.1250, 0.0370]], # [[0.0080, -0.0080], [inf, -0.0156]]], # dtype=torch.float64)  tensor1 = torch.tensor([[[-3.+0.j, 1.+0.j], [-2.+0.j, 3.+0.j]], [[5.+0.j, -5.+0.j], [0.+0.j, -4.+0.j]]]) tensor2 = torch.tensor([2.+0.j, 3.+0.j]) torch.float_power(input=tensor1, exponent=tensor2) # tensor([[[9.0000-2.2044e-15j, 1.0000+0.0000e+00j], # [4.0000-9.7972e-16j, 27.0000+0.0000e+00j]], # [[25.0000+0.0000e+00j, -125.0000+4.5924e-14j], # [0.0000-0.0000e+00j, -64.0000+2.3513e-14j]]], # dtype=torch.complex128)  torch.float_power(-3.+0.j, exponent=tensor2) # tensor([9.0000-2.2044e-15j, -27.0000+9.9196e-15j], # dtype=torch.complex128)  torch.float_power(input=tensor1, exponent=-3.+0.j) # tensor([[[-0.0370-1.3607e-17j, 1.0000+0.0000e+00j], # [-0.1250-4.5924e-17j, 0.0370+0.0000e+00j]], # [[0.0080+0.0000e+00j, -0.0080-2.9392e-18j], # [inf+nanj, -0.0156-5.7405e-18j]]], # dtype=torch.complex128)  tensor1 = torch.tensor([[[True, False], [True, False]], [[False, True], [False, True]]]) tensor2 = torch.tensor([True, False]) torch.float_power(input=tensor1, exponent=tensor2) # tensor([[[1., 1.], [1., 1.]], # [[0., 1.], [0., 1.]]], dtype=torch.float64)  torch.float_power(True, exponent=tensor2) # tensor([1., 1.], dtype=torch.float64)  torch.float_power(input=tensor1, exponent=True) # tensor([[[1., 0.], [1., 0.]], # [[0., 1.], [0., 1.]]], dtype=torch.float64)
Enter fullscreen mode Exit fullscreen mode

Top comments (0)