def test_simple_model_roundtrip_bytes_serializable_attrs():
fwd = lambda model, X, is_train: (X, lambda dY: dY)
attr = SerializableAttr()
assert attr.value == "foo"
assert attr.to_bytes() == b"foo"
model = Model("test", fwd, attrs={"test": attr})
model.initialize()
@serialize_attr.register(SerializableAttr)
def serialize_attr_custom(_, value, name, model):
return value.to_bytes()
@deserialize_attr.register(SerializableAttr)
def deserialize_attr_custom(_, value, name, model):
return SerializableAttr().from_bytes(value)
model_bytes = model.to_bytes()
model = model.from_bytes(model_bytes)
assert "test" in model.attrs
assert model.attrs["test"].value == "foo from bytes"
def train_model(
model: Model,
*,
train: Sequence[Tuple[str, str]],
test: Sequence[Tuple[str, str]],
n_iter: int,
batch_size: int | thinc.types.Generator = 32,
learn_rate: float | List[float] | thinc.types.Generator = 0.001,
) -> Model:
"""
Args:
model
train
test
n_iter
batch_size
learn_rate
"""
# binarize language labels
# NOTE: thinc seems to require type "float32" arrays for training labels
# errors otherwise... :/
lb = sklearn.preprocessing.LabelBinarizer()
lb.fit([lang for _, lang in train])
# THIS NEXT LINE IS CRITICAL: we need to save the training class labels
# but don't want to keep this label binarizer around; so, add it to the model
model.layers[-1].attrs["classes"] = lb.classes_
Y_train = lb.transform([lang for _, lang in train]).astype("float32")
Y_test = lb.transform([lang for _, lang in test])
# make sure data is on the right device?
# Y_train = self.model.ops.asarray(Y_train)
# Y_test = self.model.ops.asarray(Y_test)
X_train = [text for text, _ in train]
X_test = [text for text, _ in test]
losser = thinc.api.CategoricalCrossentropy(normalize=True)
optimizer = thinc.api.Adam(learn_rate)
model.initialize(X=X_train[:10], Y=Y_train[:10])
print(f"{'epoch':>5} {'loss':>8} {'score':>8}")
# iterate over epochs
for n in range(n_iter):
loss = 0.0
# iterate over batches
batches = model.ops.multibatch(batch_size,
X_train,
Y_train,
shuffle=True)
for X, Y in tqdm(batches, leave=False):
Yh, backprop = model.begin_update(X)
dYh, loss_batch = losser(Yh, Y)
loss += loss_batch
backprop(dYh)
model.finish_update(optimizer)
optimizer.step_schedules()
if optimizer.averages:
with model.use_params(optimizer.averages):
score = evaluate_model(model,
X_test=X_test,
Y_test=Y_test,
batch_size=1000)
else:
score = evaluate_model(model,
X_test=X_test,
Y_test=Y_test,
batch_size=1000)
print(f"{n:>5} {loss:>8.3f} {score:>8.3f}")
if optimizer.averages:
with model.use_params(optimizer.averages):
pred_langs = models.get_model_preds(
model, X_test, model.layers[-1].attrs["classes"])
else:
pred_langs = models.get_model_preds(model, X_test,
model.layers[-1].attrs["classes"])
true_langs = list(lb.inverse_transform(Y_test))
print(sklearn.metrics.classification_report(true_langs, pred_langs))
return model