data_dir = d2l.download_extract('ctr')
train_data = d2l.CTRDataset(os.path.join(data_dir, 'train.csv'))
test_data = d2l.CTRDataset(os.path.join(data_dir, 'test.csv'),
feat_mapper=train_data.feat_mapper,
defaults=train_data.defaults)
train_iter = gluon.data.DataLoader(
train_data,
shuffle=True,
last_batch='rollover',
batch_size=batch_size,
# num_workers=d2l.get_dataloader_workers())
num_workers=1)
test_iter = gluon.data.DataLoader(
test_data,
shuffle=False,
last_batch='rollover',
batch_size=batch_size,
# num_workers=d2l.get_dataloader_workers())
num_workers=1)
# %%
devices = d2l.try_all_gpus()
net = FM(train_data.field_dims, num_factors=20)
net.initialize(init.Xavier(), ctx=devices)
lr, num_epochs, optimizer = 0.02, 30, 'adam'
trainer = gluon.Trainer(net.collect_params(), optimizer, {'learning_rate': lr})
loss = gluon.loss.SigmoidBinaryCrossEntropyLoss()
d2l.train_ch13(net, train_iter, test_iter, loss, trainer, num_epochs, devices)
# %%
embed_size, num_hiddens, devices = 100, 200, d2l.try_all_gpus()
net = DecomposableAttention(vocab, embed_size, num_hiddens)
net.initialize(init.Xavier(), ctx=devices)
#download glove.6B.100d before running below line
glove_embedding = d2l.TokenEmbedding('glove.6B.100d.txt')
embeds = glove_embedding[vocab.idx_to_token]
net.embedding.weight.set_data(embeds)
#@save
def split_batch_multi_inputs(X, y, devices):
"""Split multi-input `X` and `y` into multiple devices."""
X = list(zip(*[gluon.utils.split_and_load(
feature, devices, even_split=False) for feature in X]))
return (X, gluon.utils.split_and_load(y, devices, even_split=False))
lr, num_epochs = 0.001, 4
trainer = gluon.Trainer(net.collect_params(), 'adam', {'learning_rate': lr})
loss = gluon.loss.SoftmaxCrossEntropyLoss()
d2l.train_ch13(net, train_iter, test_iter, loss, trainer, num_epochs, devices,
split_batch_multi_inputs)
#@save
def predict_snli(net, vocab, premise, hypothesis):
premise = np.array(vocab[premise], ctx=d2l.try_gpu())
hypothesis = np.array(vocab[hypothesis], ctx=d2l.try_gpu())
label = np.argmax(net([premise.reshape((1, -1)),
hypothesis.reshape((1, -1))]), axis=1)
return 'entailment' if label == 0 else 'contradiction' if label == 1 \
else 'neutral'
predict_snli(net, vocab, ['he', 'is', 'good', '.'], ['he', 'is', 'bad', '.'])