d2lzh-pytorch.zip下载可用

import collections import math import os import random import sys import tarfile import time import zipfile from tqdm import tqdm from IPython import display from matplotlib import pyplot as plt import torch from torch import nn import torch.nn.functional as F import torchvision import torchvision.transforms as transforms import torchtext import torchtext.vocab as Vocab import numpy as np VOC_CLASSES = ['background', 'aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog', 'horse', 'motorbike', 'person', 'potted plant', 'sheep', 'sofa', 'train', 'tv/monitor'] VOC_COLORMAP = [[0, 0, 0], [128, 0, 0], [0, 128, 0], [128, 128, 0], [0, 0, 128], [128, 0, 128], [0, 128, 128], [128, 128, 128], [64, 0, 0], [192, 0, 0], [64, 128, 0], [192, 128, 0], [64, 0, 128], [192, 0, 128], [64, 128, 128], [192, 128, 128], [0, 64, 0], [128, 64, 0], [0, 192, 0], [128, 192, 0], [0, 64, 128]] # ###################### 3.2 ############################ def set_figsize(figsize=(3.5, 2.5)): use_svg_display() # 设置图的尺寸 plt.rcParams['figure.figsize'] = figsize def use_svg_display(): """Use svg format to display plot in jupyter""" display.set_matplotlib_formats('svg') def data_iter(batch_size, features, labels): num_examples = len(features) indices = list(range(num_examples)) random.shuffle(indices) # 样本的读取顺序是随机的 for i in range(0, num_examples, batch_size): j = torch.LongTensor(indices[i: min(i + batch_size, num_examples)]) # 最后一次可能不足一个batch yield features.index_select(0, j), labels.index_select(0, j) def linreg(X, w, b): return torch.mm(X, w) + b def squared_loss(y_hat, y): # 注意这里返回的是向量, 另外, pytorch里的MSELoss并没有除以 2 return ((y_hat - y.view(y_hat.size())) ** 2) / 2 def sgd(params, lr, batch_size): # 为了和原书保持一致，这里除以了batch_size，但是应该是不用除的，因为一般用PyTorch计算loss时就默认已经 # 沿batch维求了平均了。 for param in params: param.data -= lr * param.grad / batch_size # 注意这里更改param时用的param.data # ######################3##### 3.5 ############################# def get_fashion_mnist_labels(labels): text_labels = ['t-shirt', 'trouser', 'pullover', 'dress', 'coat', 'sandal', 'shirt', 'sneaker', 'bag', 'ankle boot'] return [text_labels[int(i)] for i in labels] def show_fashion_mnist(images, labels): use_svg_display() # 这里的_表示我们忽略（不使用）的变量 _, figs = plt.subplots(1, len(images), figsize=(12, 12)) for f, img, lbl in zip(figs, images, labels): f.imshow(img.view((28, 28)).numpy()) f.set_title(lbl) f.axes.get_xaxis().set_visible(False) f.axes.get_yaxis().set_visible(False) # plt.show() # 5.6 修改 # def load_data_fashion_mnist(batch_size, root='~/Datasets/FashionMNIST'): # """Download the fashion mnist dataset and then load into memory.""" # transform = transforms.ToTensor() # mnist_train = torchvision.datasets.FashionMNIST(root=root, train=True, download=True, transform=transform) # mnist_test = torchvision.datasets.FashionMNIST(root=root, train=False, download=True, transform=transform) # if sys.platform.startswith('win'): # num_workers = 0 # 0表示不用额外的进程来加速读取数据 # else: # num_workers = 4 # train_iter = torch.utils.data.DataLoader(mnist_train, batch_size=batch_size, shuffle=True, num_workers=num_workers) # test_iter = torch.utils.data.DataLoader(mnist_test, batch_size=batch_size, shuffle=False, num_workers=num_workers) # return train_iter, test_iter # ########################### 3.6 ############################### # (3.13节修改) # def evaluate_accuracy(data_iter, net): # acc_sum, n = 0.0, 0 # for X, y in data_iter: # acc_sum += (net(X).argmax(dim=1) == y).float().sum().item() # n += y.shape[0] # return acc_sum / n def train_ch3(net, train_iter, test_iter, loss, num_epochs, batch_size, params=None, lr=None, optimizer=None): for epoch in range(num_epochs): train_l_sum, train_acc_sum, n = 0.0, 0.0, 0 for X, y in train_iter: y_hat = net(X) l = loss(y_hat, y).sum() # 梯度清零 if optimizer is not None: optimizer.zero_grad() elif params is not None and params[0].grad is not None: for param in params: param.grad.data.zero_() l.backward() if optimizer is None: sgd(params, lr, batch_size) else: optimizer.step() # “softmax回归的简洁实现”一节将用到 train_l_sum += l.item() train_acc_sum += (y_hat.argmax(dim=1) == y).sum().item() n += y.shape[0] test_acc = evaluate_accuracy(test_iter, net) print('epoch %d, loss %.4f, train acc %.3f, test acc %.3f' % (epoch + 1, train_l_sum / n, train_acc_sum / n, test_acc)) # ########################### 3.7 #####################################3 class FlattenLayer(torch.nn.Module): def __init__(self): super(FlattenLayer, self).__init__() def forward(self, x): # x shape: (batch, *, *, ...) return x.view(x.shape[0], -1) # ########################### 3.11 ############################### def semilogy(x_vals, y_vals, x_label, y_label, x2_vals=None, y2_vals=None, legend=None, figsize=(3.5, 2.5)): set_figsize(figsize) plt.xlabel(x_label) plt.ylabel(y_label) plt.semilogy(x_vals, y_vals) if x2_vals and y2_vals: plt.semilogy(x2_vals, y2_vals, linestyle=':') plt.legend(legend) # plt.show() # ############################# 3.13 ############################## # 5.5 修改 # def evaluate_accuracy(data_iter, net): # acc_sum, n = 0.0, 0 # for X, y in data_iter: # if isinstance(net, torch.nn.Module): # net.eval() # 评估模式, 这会关闭dropout # acc_sum += (net(X).argmax(dim=1) == y).float().sum().item() # net.train() # 改回训练模式 # else: # 自定义的模型 # if('is_training' in net.__code__.co_varnames): # 如果有is_training这个参数 # # 将is_training设置成False # acc_sum += (net(X, is_training=False).argmax(dim=1) == y).float().sum().item() # else: # acc_sum += (net(X).argmax(dim=1) == y).float().sum().item() # n += y.shape[0] # return acc_sum / n # ########################### 5.1 ######################### def corr2d(X, K): h, w = K.shape Y = torch.zeros((X.shape[0] - h + 1, X.shape[1] - w + 1)) for i in range(Y.shape[0]): for j in range(Y.shape[1]): Y[i, j] = (X[i: i + h, j: j + w] * K).sum() return Y # ############################ 5.5 ######################### def evaluate_accuracy(data_iter, net, device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')): acc_sum, n = 0.0, 0 with torch.no_grad(): for X, y in data_iter: if isinstance(net, torch.nn.Module): net.eval() # 评估模式, 这会关闭dropout acc_sum += (net(X.to(device)).argmax(dim=1) == y.to(device)).float().sum().cpu().item() net.train() # 改回训练模式 else: # 自定义的模型, 3.13节之后不会用到, 不考虑GPU if('is_training' in net.__code__.co_varnames): # 如果有is_training这个参数 # 将is_training设置成False acc_sum +