tag:www.digitalocean.com,2005:/community/tags/pytorch.atom DigitalOcean Community | PyTorch tutorials, questions and resources 2022-09-27T15:09:29.964Z <![CDATA[How to remove this error([W NNPACK.cpp:51] Could not initialize NNPACK! Reason: Unsupported hardware.)]]> tag:www.digitalocean.com,2005:/community/questions/how-to-remove-this-error-w-nnpack-cpp-51-could-not-initialize-nnpack-reason-unsupported-hardware 2022-09-07T16:36:16.392Z TinyGreenBlueUrchin 2022-09-07T16:36:16.392Z <![CDATA[How to use the PyTorch torch.max()]]> tag:www.digitalocean.com,2005:/community/tutorials/pytorch-torch-max 2022-08-03T20:14:25.240Z All the maximum elements of the Tensor. - `max_indices` -> Indices corresponding to the maximum elements. ```python max_elements, max_indices = torch.max(input_tensor, dim) ``` This will return a Tensor, which has the maximum elements along the dimension `dim`. Let's now look at some examples. ```python p = torch.randn([2, 3]) print(p) # Get the maximum along dim = 0 (axis = 0) max_elements, max_idxs = torch.max(p, dim=0) print(max_elements) print(max_idxs) ``` **Output** ```python tensor([[-0.0665, 2.7976, 0.9753], [ 0.0688, -1.0376, 1.4443]]) tensor([0.0688, 2.7976, 1.4443]) tensor([1, 0, 1]) ``` As you can see, we find the maximum along the dimension 0 (maximum along columns). Also, we get the indices corresponding to the elements. For example,`0.0688` has the index `1` along column 0 Similarly, if you want to find the maximum along the rows, use `dim=1`. ```python # Get the maximum along dim = 1 (axis = 1) max_elements, max_idxs = torch.max(p, dim=1) print(max_elements) print(max_idxs) ``` **Output** ```python tensor([2.7976, 1.4443]) tensor([1, 2]) ``` Indeed, we get the maximum elements along the row, and the corresponding index (along the row). --- ## Using torch.max() for comparison We can also use `torch.max()` to get the maximum values between two Tensors. ```python output_tensor = torch.max(a, b) ``` Here, `a` and `b` must have the same dimensions, or must be "broadcastable" Tensors. Here is a simple example to compare two Tensors having the same dimensions. ```python p = torch.randn([2, 3]) q = torch.randn([2, 3]) print("p =", p) print("q =",q) # Compare elements of p and q and get the maximum max_elements = torch.max(p, q) print(max_elements) ``` **Output** ```python p = tensor([[-0.0665, 2.7976, 0.9753], [ 0.0688, -1.0376, 1.4443]]) q = tensor([[-0.0678, 0.2042, 0.8254], [-0.1530, 0.0581, -0.3694]]) tensor([[-0.0665, 2.7976, 0.9753], [ 0.0688, 0.0581, 1.4443]]) ``` Indeed, we get the output tensor having maximum elements between `p` and `q`. --- ## Conclusion In this article, we learned about using the torch.max() function, to find out the maximum element of a Tensor. We also used this function to compare two tensors and get the maximum among them. For similar articles, do go through our content on our [PyTorch tutorials](/community/tutorials/pytorch)! Stay tuned for more! ## References - [PyTorch Official Documentation](https://pytorch.org/docs/stable/torch.html#torch.max) on torch.max() ---]]> Vijaykrishna Ram 2022-08-03T20:14:25.240Z