y_hat = net(X)
l = loss(y_hat, y).sum()
l.backward()
if trainer is None:
d2l.sgd(params, lr, batch_size)
else:
trainer.step(batch_size)
y = y.astype('float32')
train_l_sum += l.asscalar()
train_acc_sum += (y_hat.argmax(axis=1) == y).sum().asscalar()
n += y.size
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))
train_ch3(net, train_iter, test_iter, cross_entropy, num_epochs, batch_size,
[W, b], lr)
for X, y in test_iter:
break
true_labels = d2l.get_fashion_mnist_labels(y.asnumpy())
pred_labels = d2l.get_fashion_mnist_labels(net(X).argmax(axis=1).asnumpy())
titles = [
truelabel + '\n' + predlabel
for truelabel, predlabel in zip(true_labels, pred_labels)
]
d2l.show_fashion_mnist(X[0:9], titles[0:9])
import sys
sys.path.insert(0, '..')
import d2l
from mxnet.gluon import data as gdata
import sys
import time
mnist_train = gdata.vision.FashionMNIST(train=True)
mnist_test = gdata.vision.FashionMNIST(train=False)
feature, label = mnist_train[0]
X, y = mnist_train[0:9]
d2l.show_fashion_mnist(X, d2l.get_fashion_mnist_labels(y))
batch_size = 256
transformer = gdata.vision.transforms.ToTensor()
if sys.platform.startswith('win'):
# 0 means no additional processes are needed to speed up the reading of
# data
num_workers = 0
else:
num_workers = 4
train_iter = gdata.DataLoader(mnist_train.transform_first(transformer),
batch_size,
shuffle=True,
num_workers=num_workers)