这是一个高位线性回归实验的代码，具体在动手学深度学习mxnet版的p66-p68页
%matplotlib inline
import d2lzh as d2l
from mxnet import autograd, gluon, init, nd
from mxnet.gluon import data as gdata, loss as gloss, nn
n_train, n_test, num_inputs = 20, 100, 200
true_w, true_b = nd.ones((num_inputs, 1)) * 0.01, 0.05
features = nd.random.normal(shape=(n_train + n_test, num_inputs))
labels = nd.dot(features, true_w) + true_b
labels += nd.random.normal(scale=0.01, shape=labels.shape)
train_features, test_features = features[:n_train, :], features[n_train:, :]
train_labels, test_labels = labels[:n_train], labels[n_train:]
def init_params():
w = nd.random.normal(scale=1, shape=(num_inputs, 1))
b = nd.zeros(shape=(1,))
w.attach_grad()
b.attach_grad()
return [w,b]
def l2_penalty(w):
return (w**2).sun() / 2
batch_size, num_epochs, lr = 1, 100, 0.003
net, loss = d2l.linreg, d2l.squared_loss
train_iter = gdata.DataLoader(gdata.ArrayDataset(train_features, train_labels), batch_size, shuffle=True, num_workers=0)
def fit_and_plot(lambd):
w, b = init_params()
train_ls, test_ls = [], []
for _ in range(num_epochs):
for X, y in train_iter():
with autograd.record():
#添加了L2范数惩罚项
l = loss(net(X, w, b), y) + lambd * l2_penalty(w)
l.backward()
d2l.sgd([w, b], lr, batch_size)
train_ls.append(loss(net(train_features, w, b), train_labels).mean().asscalar())
test_ls.append(loss(net(test_features, w, b), test_labels).mean().asscalar())
d2l.semilogy(range(1, num_epochs + 1), train_ls, 'epochs', 'loss', range(1, num_epochs + 1), test_ls, ['train', ' test'])
print('L2 norm of w:', w.norm().asscalar())
fit_and_plot(lambd=0)
这一些代码编译之后
出现是这个
TypeError Traceback (most recent call last)
in
----> 1 fit_and_plot(lambd=0)
in fit_and_plot(lambd)
7 train_ls, test_ls = [], []
8 for _ in range(num_epochs):
----> 9 for X, y in train_iter():
10 with autograd.record():
11 #添加了L2范数惩罚项
TypeError: 'DataLoader' object is not callable
想问问 各位大佬，谢谢了
