当前位置：首页 > news >正文

深度学习_10_softmax_实战

news 2025/9/13 1:32:58

由于网上代码的画图功能是基于jupyter记事本，而我用的是pycham,这导致画图代码不兼容pycharm,所以删去部分代码，以便能更好的在pycharm上运行

完整代码：

import torch
from d2l import torch as d2l"创建训练集&创建检测集合"
batch_size = 256
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size)"创建模型w, b"
num_inputs = 784
num_outputs = 10W = torch.normal(0, 0.01, size=(num_inputs, num_outputs), requires_grad=True)
b = torch.zeros(num_outputs, requires_grad=True)"softmax"
def softmax(X):X_exp = torch.exp(X)partition = X_exp.sum(1, keepdim=True)return X_exp / partition  # 这里应用了广播机制"输出，即传入图片输出"
def net(X):return softmax(torch.matmul(X.reshape((-1, W.shape[0])), W) + b)"交叉熵损失"
def cross_entropy(y_hat, y):return - torch.log(y_hat[range(len(y_hat)), y])"显示预测与估计相对应下标数量"
def accuracy(y_hat, y):  #@save"""计算预测正确的数量"""if len(y_hat.shape) > 1 and y_hat.shape[1] > 1: # 确定长宽高都大于1y_hat = y_hat.argmax(axis=1) # 取出每行中最大值cmp = y_hat.type(y.dtype) == yreturn float(cmp.type(y.dtype).sum()) # 返回对应下标数量"利用优化后的模型计算精度"
def evaluate_accuracy(net, data_iter):  #@saveif isinstance(net, torch.nn.Module):net.eval()  # 将模型设置为评估模式metric = Accumulator(2)  # 正确预测数、预测总数with torch.no_grad():for X, y in data_iter:metric.add(accuracy(net(X), y), y.numel()) # 下标相同数量 / 总下标return metric[0] / metric[1]"加法器"
class Accumulator:  #@savedef __init__(self, n):self.data = [0.0] * ndef 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]"训练更新模型&返回训练损失与精度函数"
def train_epoch_ch3(net, train_iter, loss, updater):  #@save"""训练模型一个迭代周期（定义见第3章）"""# 将模型设置为训练模式if isinstance(net, torch.nn.Module):net.train()# 训练损失总和、训练准确度总和、样本数metric = Accumulator(3)for X, y in train_iter:# 计算梯度并更新参数y_hat = net(X)l = loss(y_hat, y)if isinstance(updater, torch.optim.Optimizer):# 使用PyTorch内置的优化器和损失函数updater.zero_grad()l.mean().backward()updater.step()else:# 使用定制的优化器和损失函数l.sum().backward()updater(X.shape[0])metric.add(float(l.sum()), accuracy(y_hat, y), y.numel())# 返回训练损失和训练精度return metric[0] / metric[2], metric[1] / metric[2]lr = 0.1"更新模型"
def updater(batch_size):return d2l.sgd([W, b], lr, batch_size)if __name__ == '__main__':num_epochs = 10cnt = 1for i in range(num_epochs):X, Y = train_epoch_ch3(net, train_iter, cross_entropy, updater)print("训练次数: " + str(cnt))cnt += 1print("训练损失: {:.4f}".format(X))print("训练精度: {:.4f}".format(Y))print(".................................")
#        print(W)
#        print(b)