def test_basic(instances, sgd):
X, y = instances
nr_class = 3
model = LinearModel(nr_class)
yh, backprop = model.begin_update(X)
loss1 = ((yh - y) ** 2).sum()
backprop(yh - y, sgd)
yh, backprop = model.begin_update(X)
loss2 = ((yh - y) ** 2).sum()
assert loss2 < loss1
print(loss2, loss1)
def main():
train, dev = datasets.imdb()
train_X, train_y = zip(*train)
dev_X, dev_y = zip(*dev)
model = LinearModel(2)
train_y = to_categorical(train_y, nb_classes=2)
dev_y = to_categorical(dev_y, nb_classes=2)
nlp = spacy.load("en")
train_X = [
model.ops.asarray([tok.orth for tok in doc], dtype="uint64")
for doc in nlp.pipe(train_X)
]
dev_X = [
model.ops.asarray([tok.orth for tok in doc], dtype="uint64")
for doc in nlp.pipe(dev_X)
]
dev_X = preprocess(model.ops, dev_X)
with model.begin_training(train_X, train_y,
L2=1e-6) as (trainer, optimizer):
trainer.dropout = 0.0
trainer.batch_size = 512
trainer.nb_epoch = 3
trainer.each_epoch.append(lambda: print(model.evaluate(dev_X, dev_y)))
for X, y in trainer.iterate(train_X, train_y):
keys_vals_lens = preprocess(model.ops, X)
scores, backprop = model.begin_update(keys_vals_lens,
drop=trainer.dropout)
backprop(scores - y, optimizer)
with model.use_params(optimizer.averages):
print(model.evaluate(dev_X, dev_y))
def main():
train, dev = datasets.imdb()
train_X, train_y = zip(*train)
dev_X, dev_y = zip(*dev)
model = LinearModel(2)
train_y = to_categorical(train_y, nb_classes=2)
dev_y = to_categorical(dev_y, nb_classes=2)
nlp = spacy.load("en")
train_X = [
model.ops.asarray([tok.orth for tok in doc], dtype="uint64")
for doc in nlp.pipe(train_X)
]
dev_X = [
model.ops.asarray([tok.orth for tok in doc], dtype="uint64")
for doc in nlp.pipe(dev_X)
]
dev_X = preprocess(model.ops, dev_X)
with model.begin_training(train_X, train_y, L2=1e-6) as (trainer, optimizer):
trainer.dropout = 0.0
trainer.batch_size = 512
trainer.nb_epoch = 3
trainer.each_epoch.append(lambda: print(model.evaluate(dev_X, dev_y)))
for X, y in trainer.iterate(train_X, train_y):
keys_vals_lens = preprocess(model.ops, X)
scores, backprop = model.begin_update(keys_vals_lens, drop=trainer.dropout)
backprop(scores - y, optimizer)
with model.use_params(optimizer.averages):
print(model.evaluate(dev_X, dev_y))
def test_init():
model = LinearModel(3)
keys = numpy.ones((5, ), dtype="uint64")
values = numpy.ones((5, ), dtype="f")
lengths = numpy.zeros((2, ), dtype=numpy.int_)
lengths[0] = 3
lengths[1] = 2
scores, backprop = model.begin_update((keys, values, lengths))
assert scores.shape == (2, 3)
d_feats = backprop(scores)
assert d_feats is None