Deep Learning with PyTorch

Matrix (2-D tensors)

Most of the structured data is represented in the form of tables or matrices. We will use a dataset called Boston House Prices, which is readily available in the Python scikit-learn machine learning library. The dataset is a numpy array consisting of 506 samples or rows and 13 features representing each sample. Torch provides a utility function called from_numpy(), which converts a numpy array into a torch tensor. The shape of the resulting tensor is 506 rows x 13 columns:

boston_tensor = torch.from_numpy(boston.data)boston_tensor.size()Output: torch.Size([506, 13])boston_tensor[:2]Output:Columns 0 to 7    0.0063 18.0000 2.3100 0.0000 0.5380 6.5750 65.2000 4.0900 0.0273 0.0000 7.0700 0.0000 0.4690 6.4210 78.9000 4.9671 ...