def forward(self, X):
# 如果X不在内存上，将moving_mean和moving_var复制到X所在显存上
if self.moving_mean.context != X.context:
self.moving_mean = self.moving_mean.copyto(X.context)
self.moving_var = self.moving_var.copyto(X.context)
# 保存更新过的moving_mean和moving_var
Y, self.moving_mean, self.moving_var = batch_norm(X,
self.gamma.data(),
self.beta.data(),
self.moving_mean,
self.moving_var,
eps=1e-5,
momentum=0.9)
return Y
net = nn.Sequential()
net.add(nn.Conv2D(6, kernel_size=5), BatchNorm(6, num_dims=4),
nn.Activation('sigmoid'), nn.MaxPool2D(pool_size=2, strides=2),
nn.Conv2D(16, kernel_size=5), BatchNorm(16, num_dims=4),
nn.Activation('sigmoid'), nn.MaxPool2D(pool_size=2, strides=2),
nn.Dense(120), BatchNorm(120, num_dims=2), nn.Activation('sigmoid'),
nn.Dense(84), BatchNorm(84, num_dims=2), nn.Activation('sigmoid'),
nn.Dense(10))
lr, num_epochs, batch_size, ctx = 1.0, 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)
d2l.train_ch5(net, train_iter, test_iter, batch_size, trainer, ctx, num_epochs)
I = nd.sigmoid(nd.dot(X, W_xi)+nd.dot(H, W_hi)+b_i)
F = nd.sigmoid(nd.dot(X, W_xf)+nd.dot(H, W_hf)+b_f)
O = nd.sigmoid(nd.dot(X, W_xo)+nd.dot(H, W_ho)+b_o)
C_tilda = nd.tanh(nd.dot(X, W_xc)+nd.dot(H, W_hc)+b_c)
C = F*C+I*C_tilda
H = O*C.tanh()
Y = nd.dot(H, W_hq)+b_q
outputs.append(Y)
return outputs, (H, C)
if __name__ == "__main__":
(corpus_indices, char_to_idx, idx_to_char,
vocab_size) = d2l.load_data_jay_lyrics()
num_inputs, num_hiddens, num_outputs = vocab_size, 256, vocab_size
ctx = d2l.try_gpu()
num_epochs, num_steps, batch_size, lr, clipping_theta = 160, 35, 32, 1e2, 1e-2
pred_period, pred_len, prefixes = 40, 50, ['分开', '不分开']
# d2l.train_and_predict_rnn(lstm, get_params, init_lstm_state, num_hiddens,
# vocab_size, ctx, corpus_indices, idx_to_char,
# char_to_idx, False, num_epochs, num_steps, lr,
# clipping_theta, batch_size, pred_period, pred_len,
# prefixes)
lstm_layer = rnn.LSTM(num_hiddens)
model = d2l.RNNModel(lstm_layer, vocab_size)
d2l.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)
l = loss(outputs, y).sum()
l.backward()
trainer.step(batch_size)
train_l_sum += l.asscalar()
n += y.size
time_s = "time %.2f sec" % (time.time() - start)
if valid_iter is not None:
valid_loss = evaluate_loss(valid_iter, net, ctx)
epoch_s = ("epoch %d, train loss %f, valid loss %f, "
% (epoch + 1, train_l_sum / n, valid_loss))
else:
epoch_s = ("epoch %d, train loss %f, "
% (epoch + 1, train_l_sum / n))
print(epoch_s + time_s + ', lr ' + str(trainer.learning_rate))
ctx, num_epochs, lr, wd = d2l.try_gpu(), 1, 0.01, 1e-4
lr_period, lr_decay, net = 10, 0.1, get_net(ctx)
net.hybridize()
train(net, train_iter, valid_iter, num_epochs, lr, wd, ctx, lr_period,
lr_decay)
net = get_net(ctx)
net.hybridize()
train(net, train_valid_iter, None, num_epochs, lr, wd, ctx, lr_period,
lr_decay)
preds = []
for data, label in test_iter:
output_features = net.features(data.as_in_context(ctx))
output = nd.softmax(net.output_new(output_features))
preds.extend(output.asnumpy())
def forward(self, X):
anchors, cls_preds, bbox_preds = [None] * 5, [None] * 5, [None] * 5
for i in range(5):
# getattr(self, 'blk_%d' % i)即访问self.blk_i
X, anchors[i], cls_preds[i], bbox_preds[i] = blk_forward(
X, getattr(self, 'blk_%d' % i), sizes[i], ratios[i],
getattr(self, 'cls_%d' % i), getattr(self, 'bbox_%d' % i))
# reshape函数中的0表示保持批量大小不变
return (nd.concat(*anchors, dim=1), concat_preds(cls_preds).reshape(
(0, -1, self.num_classes + 1)), concat_preds(bbox_preds))
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
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
# In[ ]:
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)
# In[ ]:
d2l.plt.imsave('../img/neural-style-1.png', postprocess(output).asnumpy())
# In[ ]:
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)
train_l_sum += l.asscalar()
train_acc_sum += (y_hat.argmax(axis=1) == y).sum().asscalar()
n += y.size
time_s = "time %.2f sec" % (time.time() - start)
if valid_iter is not None:
valid_acc = d2l.evaluate_accuracy(valid_iter, net, ctx)
epoch_s = (
"epoch %d, loss %f, train acc %f, valid acc %f, " %
(epoch + 1, train_l_sum / n, train_acc_sum / n, valid_acc))
else:
epoch_s = ("epoch %d, loss %f, train acc %f, " %
(epoch + 1, train_l_sum / n, train_acc_sum / n))
print(epoch_s + time_s + ', lr ' + str(trainer.learning_rate))
ctx, num_epochs, lr, wd = d2l.try_gpu(), 1, 0.1, 5e-4
lr_period, lr_decay, net = 80, 0.1, get_net(ctx)
net.hybridize()
train(net, train_iter, valid_iter, num_epochs, lr, wd, ctx, lr_period,
lr_decay)
net, preds = get_net(ctx), []
net.hybridize()
train(net, train_valid_iter, None, num_epochs, lr, wd, ctx, lr_period,
lr_decay)
for X, _ in test_iter:
y_hat = net(X.as_in_context(ctx))
preds.extend(y_hat.argmax(axis=1).astype(int).asnumpy())
sorted_ids = list(range(1, len(test_ds) + 1))
sorted_ids.sort(key=lambda x: str(x))
'fashion-mnist')):
root = os.path.expanduser(root) # 展开用户路径'~'
transformer = []
if resize:
transformer += [gdata.vision.transforms.Resize(resize)]
transformer += [gdata.vision.transforms.ToTensor()]
transformer = gdata.vision.transforms.Compose(transformer)
mnist_train = gdata.vision.FashionMNIST(root=root, train=True)
mnist_test = gdata.vision.FashionMNIST(root=root, train=False)
num_workers = 0 if sys.platform.startswith('win32') else 4
train_iter = gdata.DataLoader(mnist_train.transform_first(transformer),
batch_size,
shuffle=True,
num_workers=num_workers)
test_iter = gdata.DataLoader(mnist_test.transform_first(transformer),
batch_size,
shuffle=False,
num_workers=num_workers)
return train_iter, test_iter
batch_size = 128
# 如出现“out of memory”的报错信息，可减小batch_size或resize
# 将batch_size减小到64后，一个epoch要运行一刻钟
# resize不能随便减小
train_iter, test_iter = load_data_fashion_mnist(batch_size, resize=224)
lr, num_epochs, ctx = 0.01, 5, d2l.try_gpu()
net.initialize(force_reinit=True, ctx=ctx, init=init.Xavier())
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': lr})
d2l.train_ch5(net, train_iter, test_iter, batch_size, trainer, ctx, num_epochs)