1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153
| import matplotlib.pyplot as plt import torch from IPython import display from d2l import torch as d2l
num_inputs = 784 num_outputs = 10 W = torch.normal(0, 0.01, size=(num_inputs, num_outputs), requires_grad=True) b = torch.zeros(num_outputs, requires_grad=True)
def softmax(X): X_exp = torch.exp(X) partition = X_exp.sum(1, keepdim=True) return X_exp / partition
def net(X): return softmax(torch.matmul(X.reshape((-1, W.shape[0])), W) + b)
def cross_entropy(y_hat, y): return - torch.log(y_hat[range(len(y_hat)), y])
def accuracy(y_hat, y): if len(y_hat.shape) > 1 and y_hat.shape[1] > 1: y_hat = y_hat.argmax(axis=1) cmp = y_hat.type(y.dtype) == y return float(cmp.type(y.dtype).sum())
def evaluate_accuracy(net, data_iter): if isinstance(net, torch.nn.Module): net.eval() metric = Accumulator(2) with torch.no_grad(): for X, y in data_iter: metric.add(accuracy(net(X), y), y.numel()) return metric[0] / metric[1]
class Accumulator: def __init__(self, n): self.data = [0.0] * n
def add(self, *args): self.data = [a + float(b) for a, b in zip(self.data, args)]
def reset(self): self.data = [0.0] * len(self.data)
def __getitem__(self, idx): return self.data[idx]
class Animator: def __init__(self, xlabel=None, ylabel=None, legend=None, xlim=None, ylim=None, xscale='linear', yscale='linear', fmts=('-', 'm--', 'g-.', 'r:'), nrows=1, ncols=1, figsize=(3.5, 2.5)): if legend is None: legend = [] d2l.use_svg_display() self.fig, self.axes = d2l.plt.subplots(nrows, ncols, figsize=figsize) if nrows * ncols == 1: self.axes = [self.axes, ] self.config_axes = lambda: d2l.set_axes( self.axes[0], xlabel, ylabel, xlim, ylim, xscale, yscale, legend) self.X, self.Y, self.fmts = None, None, fmts
def add(self, x, y): if not hasattr(y, "__len__"): y = [y] n = len(y) if not hasattr(x, "__len__"): x = [x] * n if not self.X: self.X = [[] for _ in range(n)] if not self.Y: self.Y = [[] for _ in range(n)] for i, (a, b) in enumerate(zip(x, y)): if a is not None and b is not None: self.X[i].append(a) self.Y[i].append(b) self.axes[0].cla() for x, y, fmt in zip(self.X, self.Y, self.fmts): self.axes[0].plot(x, y, fmt) self.config_axes() display.display(self.fig) display.clear_output(wait=True)
def train_epoch_ch3(net, train_iter, loss, updater): if isinstance(net, torch.nn.Module): net.train() metric = Accumulator(3) for X, y in train_iter: y_hat = net(X) l = loss(y_hat, y) if isinstance(updater, torch.optim.Optimizer): updater.zero_grad() l.mean().backward() updater.step() else: l.sum().backward() updater(X.shape[0]) metric.add(float(l.sum()), accuracy(y_hat, y), y.numel()) return metric[0] / metric[2], metric[1] / metric[2]
def train_ch3(net, train_iter, test_iter, loss, num_epochs, updater): animator = Animator(xlabel='epoch', xlim=[1, num_epochs], ylim=[0.3, 0.9], legend=['train loss', 'train acc', 'test acc']) for epoch in range(num_epochs): train_metrics = train_epoch_ch3(net, train_iter, loss, updater) test_acc = evaluate_accuracy(net, test_iter) animator.add(epoch + 1, train_metrics + (test_acc,)) train_loss, train_acc = train_metrics assert train_loss < 0.5 assert 0.7 < train_acc <= 1 assert 0.7 < test_acc <= 1
def predict_ch3(net, test_iter, n=6): for X, y in test_iter: break trues = d2l.get_fashion_mnist_labels(y) preds = d2l.get_fashion_mnist_labels(net(X).argmax(axis=1)) titles = [true + '\n' + pred for true, pred in zip(trues, preds)] d2l.show_images(X[0:n].reshape((n, 28, 28)), 1, n, titles=titles[0:n])
lr = 0.1 def updater(batch_size): return d2l.sgd([W, b], lr, batch_size)
def main(): batch_size = 256 train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)
X = torch.tensor([[1.0, 2.0, 3.0], [4.0, 5.0, 6.0]]) print(X.sum(0, keepdim=True), X.sum(1, keepdim=True))
X = torch.normal(0, 1, (2, 5)) X_prob = softmax(X) print(X_prob, X_prob.sum(1))
y = torch.tensor([0, 2]) y_hat = torch.tensor([[0.1, 0.3, 0.6], [0.3, 0.2, 0.5]]) print(y_hat[[0, 1], y]) print(cross_entropy(y_hat, y)) print(accuracy(y_hat, y) / len(y))
print(evaluate_accuracy(net, test_iter))
num_epochs = 10 train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, updater)
predict_ch3(net, test_iter) plt.show()
if __name__ == '__main__': main()
|