def train(net, lr, num_epochs):
ctx = d2l.try_gpu()
net.initialize(ctx=ctx, force_reinit=True)
trainer = gluon.Trainer(net.collect_params(), 'adam',
{'learning_rate': lr})
for epoch in range(num_epochs):
start, l_sum, n = time.time(), 0.0, 0
for batch in data_iter:
center, context_negative, mask, label = [
data.as_in_context(ctx) for data in batch
]
with autograd.record():
pred = skip_gram(center, context_negative, net[0], net[1])
# 使用掩码变量mask来避免填充项对损失函数计算的影响
l = (loss(pred.reshape(label.shape), label, mask) *
mask.shape[1] / mask.sum(axis=1))
l.backward()
trainer.step(batch_size)
l_sum += l.sum().asscalar()
n += l.size
print('epoch %d, loss %.2f, time %.2fs' %
(epoch + 1, l_sum / n, time.time() - start))
blk = nn.Sequential()
blk.add(nn.BatchNorm(), nn.Activation('relu'),
nn.Conv2D(num_channels, kernel_size=1),
nn.AvgPool2D(pool_size=2, strides=2))
return blk
net = nn.Sequential()
net.add(nn.Conv2D(64, kernel_size=7, strides=2, padding=3),
nn.BatchNorm(), nn.Activation('relu'),
nn.MaxPool2D(pool_size=3, strides=2, padding=1))
num_channels, growth_rate = 64, 32
num_convs_in_dense_blocks = [4, 4, 4, 4]
for i, num_convs in enumerate(num_convs_in_dense_blocks):
net.add(DenseBlock(num_convs, growth_rate))
num_channels += num_convs * growth_rate
if i != len(num_convs_in_dense_blocks) - 1:
num_channels //= 2
net.add(transition_block(num_channels))
net.add(nn.BatchNorm(), nn.Activation('relu'), nn.GlobalAvgPool2D(),
nn.Dense(10))
lr, num_epochs, batch_size, ctx = 0.1, 5, 256, d2l.try_gpu()
net.initialize(ctx=ctx, init=init.Xavier())
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': lr})
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=96)
d2l.train_ch5(net, train_iter, test_iter, batch_size, trainer, ctx, num_epochs)
def predict_rnn_gluon(prefix, num_chars, model, vocab_size, ctx, idx_to_char,
char_to_idx):
# 使用model的成员函数来初始化隐藏状态
state = model.begin_state(batch_size=1, ctx=ctx)
output = [char_to_idx[prefix[0]]]
for t in range(num_chars + len(prefix) - 1):
X = nd.array([output[-1]], ctx=ctx).reshape((1, 1))
(Y, state) = model(X, state) # 前向计算不需要传入模型参数
if t < len(prefix) - 1:
output.append(char_to_idx[prefix[t + 1]])
else:
output.append(int(Y.argmax(axis=1).asscalar()))
return ''.join([idx_to_char[i] for i in output])
ctx = d2l.try_gpu()
model = RNNModel(rnn_layer, vocab_size)
model.initialize(force_reinit=True, ctx=ctx)
predict_rnn_gluon('分开', 10, model, vocab_size, ctx, idx_to_char, char_to_idx)
def train_and_predict_rnn_gluon(model, num_hiddens, vocab_size, ctx,
corpus_indices, idx_to_char, char_to_idx,
num_epochs, num_steps, lr, clipping_theta,
batch_size, pred_period, pred_len, prefixes):
loss = gloss.SoftmaxCrossEntropyLoss()
model.initialize(ctx=ctx, force_reinit=True, init=init.Normal(0.01))
trainer = gluon.Trainer(model.collect_params(), 'sgd', {
'learning_rate': lr,
'momentum': 0,
'wd': 0
return (nd.concat(*anchors, dim=1), concat_preds(cls_preds).reshape(
(0, -1, self.num_classes + 1)), concat_preds(bbox_preds))
net = TinySSD(num_classes=1)
net.initialize()
X = nd.zeros((32, 3, 256, 256))
anchors, cls_preds, bbox_preds = net(X)
print('output anchors:', anchors.shape)
print('output class preds:', cls_preds.shape)
print('output bbox preds:', bbox_preds.shape)
batch_size = 32
train_iter, _ = d2l.load_data_pikachu(batch_size)
ctx, net = d2l.try_gpu(), TinySSD(num_classes=1)
net.initialize(init=init.Xavier(), ctx=ctx)
trainer = gluon.Trainer(net.collect_params(), 'sgd', {
'learning_rate': 0.2,
'wd': 5e-4
})
cls_loss = gloss.SoftmaxCrossEntropyLoss()
bbox_loss = gloss.L1Loss()
def calc_loss(cls_preds, cls_labels, bbox_preds, bbox_labels, bbox_masks):
cls = cls_loss(cls_preds, cls_labels)
bbox = bbox_loss(bbox_preds * bbox_masks, bbox_labels * bbox_masks)
return cls + bbox
contents_Y_hat, styles_Y_hat = extract_features(
X, content_layers, style_layers)
contents_l, styles_l, tv_l, l = compute_loss(
X, contents_Y_hat, styles_Y_hat, contents_Y, styles_Y_gram)
l.backward()
trainer.step(1)
nd.waitall()
if i % 50 == 0 and i != 0:
print('epoch %3d, content loss %.2f, style loss %.2f, '
'TV loss %.2f, %.2f sec'
% (i, nd.add_n(*contents_l).asscalar(),
nd.add_n(*styles_l).asscalar(), tv_l.asscalar(),
time.time() - start))
if i % lr_decay_epoch == 0 and i != 0:
trainer.set_learning_rate(trainer.learning_rate * 0.1)
print('change lr to %.1e' % trainer.learning_rate)
return X
ctx, image_shape = d2l.try_gpu(), (225, 150)
net.collect_params().reset_ctx(ctx)
content_X, contents_Y = get_contents(image_shape, ctx)
_, styles_Y = get_styles(image_shape, ctx)
output = train(content_X, contents_Y, styles_Y, ctx, 0.01, 500, 200)
d2l.plt.imsave('./d2l/img/neural-style-1.png', postprocess(output).asnumpy())
image_shape = (450, 300)
_, content_Y = get_contents(image_shape, ctx)
_, style_Y = get_styles(image_shape, ctx)
X = preprocess(postprocess(output) * 255, image_shape)
output = train(X, content_Y, style_Y, ctx, 0.01, 300, 100)
d2l.plt.imsave('./d2l/img/neural-style-2.png', postprocess(output).asnumpy())
def predict_sentiment(net, vocab, sentence):
sentence = nd.array(vocab.to_indices(sentence), ctx=d2l.try_gpu())
label = nd.argmax(net(sentence.reshape((1, -1))), axis=1)
return 'positive' if label.asscalar() == 1 else 'negative'