randint and randperm in PyTorch

Buy Me a Coffee☕

*Memos:

• You can use manual_seed() with randint() and randperm(). *My post explains manual_seed().
• My post explains rand() and rand_like().
• My post explains randn() and randn_like().
• My post explains normal().

randint() can create the 0D or more D tensor of the zero or more random integers(Default) or floating-point numbers between low and high-1(low<=x<=high-1) as shown below:

*Memos:

• randint() can be used with torch but not with a tensor.
• The 1st argument with torch is low(Optional-Default:0-Type:int): *Memos:
  • It must be lower than high.
  • The 0D or more D tensor of one integer works.
• The 2nd argument with torch is high(Required-Type:int): *Memos:
  • It must be greater than low.
  • The 0D or more D tensor of one integer works.
• The 3rd argument with torch is size(Required-Type:tuple of int, list of int or size()).
• There is dtype argument with torch(Optional-Default:None-Type:dtype): *Memos:
  • If it's None, it's torch.int64.
  • dtype= must be used.
  • My post explains dtype argument.
• There is device argument with torch(Optional-Default:None-Type:str, int or device()): *Memos:
  • If it's None, get_default_device() is used. *My post explains get_default_device() and set_default_device().
  • device= must be used.
  • My post explains device argument.
• There is requires_grad argument with torch(Optional-Default:False-Type:bool): *Memos:
  • requires_grad= must be used.
  • My post explains requires_grad argument.
• There is out argument with torch(Optional-Default:None-Type:tensor): *Memos:
  • out= must be used.
  • My post explains out argument.

import torch torch.randint(high=10, size=()) torch.randint(high=10, size=torch.tensor(8).size()) # tensor(7)  torch.randint(high=10, size=(3,)) torch.randint(high=10, size=torch.tensor([8, 3, 6]).size()) # tensor([7, 4, 8])  torch.randint(high=10, size=(3, 2)) torch.randint(high=10, size=torch.tensor([[8, 3], [6, 0], [2, 9]]).size()) # tensor([[8, 9], [6, 5], [5, 2]])  torch.randint(high=10, size=(3, 2, 4)) # tensor([[[1, 5, 9, 0], [4, 6, 7, 2]], # [[5, 2, 1, 5], [9, 3, 2, 6]], # [[9, 3, 6, 4], [0, 4, 7, 5]]])  torch.randint(low=10, high=20, size=(3,)) # tensor([17, 12, 10])  torch.randint(low=10, high=20, size=(3, 2)) # tensor([[14, 18], [10, 19], [15, 16]])  torch.randint(low=10, high=20, size=(3, 2, 4)) # tensor([[[16, 14, 11, 19], [19, 15, 18, 13]], # [[14, 10, 11, 13], [16, 11, 10, 16]], # [[17, 12, 17, 10], [13, 16, 11, 10]]])  torch.randint(low=-5, high=5, size=(3,)) # tensor([-1, 2, -3])  torch.randint(low=-5, high=5, size=(3, 2)) # tensor([[-5, 4], [ 1, -1], [-4, -3]])  torch.randint(low=-5, high=5, size=(3, 2, 4)) # tensor([[[-2, 0, 1, -5], [4, -5, -3, 1]], # [[-4, -1, -1, -1], [-3, 2, -4, -1]], # [[4, -1, -5, -3], [2, -3, -2, 2]]])  torch.randint(low=-5, high=5, size=(3, 2, 4), dtype=torch.float32) torch.randint(low=torch.tensor(-5), high=torch.tensor([5]), size=(3, 2, 4), dtype=torch.float32) # tensor([[[-4., 1., -1., -3.], [-3., -5., -4., 1.]], # [[-5., 3., 3., 1.], [-1., 4., -5., 2.]], # [[-2., -4., -5., 3.], [4., 1., -3., 3.]]])  torch.randint(high=1, size=(0,)) torch.randint(low=0, high=1, size=(0,)) torch.randint(low=10, high=20, size=(0,)) # tensor([], dtype=torch.int64) 

randperm() can create the 1D tensor of zero or more random integers(Default) or floating-point numbers between 0 and n-1(0<=x<=n-1) as shown below:

*Memos:

• randperm() can be used with torch but not with a tensor.
• The 1st argument with torch is n(Required-Type:int): *Memos:
  • It must be greater than or equal to 1.
  • The 0D or more D tensor of one integer works.
• There is dtype argument with torch(Optional-Default:None-Type:dtype): *Memos:
  • If it's None, it's torch.int64.
  • dtype= must be used.
  • My post explains dtype argument.
• There is device argument with torch(Optional-Default:None-Type:str, int or device()): *Memos:
  • If it's None, get_default_device() is used. *My post explains get_default_device() and set_default_device().
  • device= must be used.
  • My post explains device argument.
• There is requires_grad argument with torch(Optional-Default:False-Type:bool): *Memos:
  • requires_grad= must be used.
  • My post explains requires_grad argument.
• There is out argument with torch(Optional-Default:None-Type:tensor): *Memos:
  • out= must be used.
  • My post explains out argument.

import torch torch.randperm(n=0) # tensor([], dtype=torch.int64)  torch.randperm(n=5) # tensor([3, 0, 4, 2, 1])  torch.randperm(n=10) # tensor([8, 6, 9, 2, 1, 3, 5, 0, 7, 4])  torch.randperm(n=10, dtype=torch.float32) torch.randperm(n=torch.tensor([[10]]), dtype=torch.float32) # tensor([7., 4., 2., 1., 8., 3., 0., 6., 9., 5.])