Deep Learning with PyTorch

Creating a custom PyTorch dataset class for the pre-convoluted features and loader

We have already seen how to create a PyTorch dataset. It should be a subclass of the torch.utils.data dataset class and should implement the __getitem__(self, index) and __len__(self) methods, which return the length of the data in the dataset. In the following code, we implement a custom dataset for the pre-convoluted features:

class FeaturesDataset(Dataset):        def __init__(self,featlst,labellst):        self.featlst = featlst        self.labellst = labellst            def __getitem__(self,index):        return (self.featlst[index],self.labellst[index])        def __len__(self):        return len(self.labellst)

Once the custom dataset class is created, creating a data loader for the pre-convoluted features ...