PyTorch torch.count_nonzero Function
PyTorch torch Reference Manual
torch.count_nonzerois a function in PyTorch used to return the number of non-zero elements in a tensor.
Function Definition
torch.count_nonzero(input, dim)
Usage Example
Example
import torch
x = torch.tensor([1, 0, 2, 0, 3, 0, 0, 4])
# Return the number of non-zero elements
print("Number of non-zero elements:", torch.count_nonzero(x))
# Number of non-zero elements along dim=0
y = torch.tensor([[1, 0, 2], [0, 3, 0], [4, 0, 5]])
print("Number of non-zero elements:", torch.count_nonzero(y))
print("Number of non-zero elements along dim=0:", torch.count_nonzero(y, dim=0))
print("Number of non-zero elements along dim=1:", torch.count_nonzero(y, dim=1))
x = torch.tensor([1, 0, 2, 0, 3, 0, 0, 4])
# Return the number of non-zero elements
print("Number of non-zero elements:", torch.count_nonzero(x))
# Number of non-zero elements along dim=0
y = torch.tensor([[1, 0, 2], [0, 3, 0], [4, 0, 5]])
print("Number of non-zero elements:", torch.count_nonzero(y))
print("Number of non-zero elements along dim=0:", torch.count_nonzero(y, dim=0))
print("Number of non-zero elements along dim=1:", torch.count_nonzero(y, dim=1))
The output result is:
非零元素数量: tensor(4) 非零元素数量: tensor(5) dim=0 非零元素数量: tensor([2, 1, 2]) dim=1 非零元素数量: tensor([2, 1, 2])
Other Extensions