YouTipBeginner's Tutorial -- It's not just technology you're learning, but also dreams!
\n\n- \n
- Home \n
- HTML \n
- JavaScript \n
- CSS \n
- Vue \n
- React \n
- Python3 \n
- Java \n
- C \n
- C++ \n
- C# \n
- AI \n
- Go \n
- SQL \n
- Linux \n
- VS Code \n
- Bootstrap \n
- Git \n
- Local Bookmarks \n
- \n
- Vue3 Tutorial \n
- Vue2 Tutorial \n
- \n
- Bootstrap3 \n
- Bootstrap4 \n
- Bootstrap5 \n
- \n
- Machine Learning \n
- PyTorch \n
- TensorFlow \n
- Sklearn \n
- NLP \n
- AI Agent \n
- Ollama \n
- Coding Plan \n
PyTorch torch.count_nonzero Function
\n\n\n
torch.count_nonzero is a function in PyTorch used to return the number of non-zero elements in a tensor.
Function Definition
\n\ntorch.count_nonzero(input, dim)\n\n\n
Example Usage
\n\nExample
\n\nimport torch\n\nx = torch.tensor([1,0,2,0,3,0,0,4])\n\n# Returns the number of non-zero elements\n\nprint("Number of non-zero elements:", torch.count_nonzero(x))\n\n# Counts non-zero elements along dim=0\n\ny = torch.tensor([[1,0,2],[0,3,0],[4,0,5]])\n\nprint("Number of non-zero elements:", torch.count_nonzero(y))\n\nprint("dim=0 Number of non-zero elements:", torch.count_nonzero(y, dim=0))\n\nprint("dim=1 Number of non-zero elements:", torch.count_nonzero(y, dim=1))\nThe output result is:
\n\nNumber of non-zero elements: tensor(4)Number of non-zero elements: tensor(5) dim=0 Number of non-zero elements: tensor([2, 1, 2]) dim=1 Number of non-zero elements: tensor([2, 1, 2])\n\n\n