FionaDong的博客

4. Implementation of Softmax Regression from Scratch Just as we implemented linear regression from scratch, softmax regression is similarly fundamental. We will work with the Fashion-MNIST dataset, which has 10 classes. import torch from torch import nn, o

3. The Image Classification Dataset import torch import torchvision from torchvision import transforms from torch.utils import data import matplotlib.pyplot as plt %matplotlib inline 3.1 Reading the Dataset Download and read the Fashion-MNIST dataset int

2. Concise Implementation of Linear Regression 2.1 Generating the Dataset Generate the same dataset as in Linear Regression Implementation from Scratch: import numpy as np import torch from torch.utils import data from torch import nn def synthetic_data(w

1. Linear Regression Implementation from Scratch 1.1 Generating the Dataset To keep things simple, we will construct an artificial dataset according to a linear model with additive noise. Our task will be to recover this model’s parameters using the finite

2. Automatic Differentiation import torch 2.1 Backward for Non-Scalar Variables # Same as `x = torch.arange(4.0, requires_grad=True)` x = torch.arange(4.0) x.requires_grad_(True) # The default value is None print(x.grad) None y = 2 * torch.dot(x, x) y.b

1. Data Manipulation import torch 1.1 Getting started torch.arange() x = torch.arange(12) print(x.shape) print(x.numel()) torch.Size([12]) 12 X = x.reshape(3, 4) print(X.shape) X = x.reshape(3, 4)... torch.Size([3, 4]) torch.zeros/ones/rand/tensor() x