def util_batch_unbatch_docs_array(model: Model[List[Doc], Array2d],
in_data: List[Doc], out_data: Array2d):
with data_validation(True):
model.initialize(in_data, out_data)
Y_batched = model.predict(in_data).tolist()
Y_not_batched = [model.predict([u])[0] for u in in_data]
assert_almost_equal(Y_batched, Y_not_batched, decimal=4)
def util_batch_unbatch_docs_list(model: Model[List[Doc], List[Array2d]],
in_data: List[Doc], out_data: List[Array2d]):
with data_validation(True):
model.initialize(in_data, out_data)
Y_batched = model.predict(in_data)
Y_not_batched = [model.predict([u])[0] for u in in_data]
for i in range(len(Y_batched)):
assert_almost_equal(Y_batched[i], Y_not_batched[i], decimal=4)
def util_batch_unbatch_docs_ragged(model: Model[List[Doc], Ragged],
in_data: List[Doc], out_data: Ragged):
with data_validation(True):
model.initialize(in_data, out_data)
Y_batched = model.predict(in_data)
Y_not_batched = []
for u in in_data:
Y_not_batched.extend(model.predict([u]).data.tolist())
assert_almost_equal(Y_batched.data, Y_not_batched, decimal=4)
def debug_model(
config,
resolved_train_config,
nlp,
model: Model,
*,
print_settings: Optional[Dict[str, Any]] = None,
):
if not isinstance(model, Model):
msg.fail(
f"Requires a Thinc Model to be analysed, but found {type(model)} instead.",
exits=1,
)
if print_settings is None:
print_settings = {}
# STEP 0: Printing before training
msg.info(f"Analysing model with ID {model.id}")
if print_settings.get("print_before_training"):
msg.divider(f"STEP 0 - before training")
_print_model(model, print_settings)
# STEP 1: Initializing the model and printing again
X = _get_docs()
# The output vector might differ from the official type of the output layer
with data_validation(False):
try:
dot_names = [resolved_train_config["train_corpus"]]
with show_validation_error():
(train_corpus, ) = resolve_dot_names(config, dot_names)
nlp.initialize(lambda: train_corpus(nlp))
msg.info("Initialized the model with the training corpus.")
except ValueError:
try:
_set_output_dim(nO=7, model=model)
with show_validation_error():
nlp.initialize(
lambda: [Example.from_dict(x, {}) for x in X])
msg.info("Initialized the model with dummy data.")
except Exception:
msg.fail(
"Could not initialize the model: you'll have to provide a valid train_corpus argument in the config file.",
exits=1,
)
if print_settings.get("print_after_init"):
msg.divider(f"STEP 1 - after initialization")
_print_model(model, print_settings)
# STEP 2: Updating the model and printing again
optimizer = Adam(0.001)
set_dropout_rate(model, 0.2)
# ugly hack to deal with Tok2Vec listeners
tok2vec = None
if model.has_ref("tok2vec") and model.get_ref(
"tok2vec").name == "tok2vec-listener":
tok2vec = nlp.get_pipe("tok2vec")
goldY = None
for e in range(3):
if tok2vec:
tok2vec.update([Example.from_dict(x, {}) for x in X])
Y, get_dX = model.begin_update(X)
if goldY is None:
goldY = _simulate_gold(Y)
dY = get_gradient(goldY, Y, model.ops)
get_dX(dY)
model.finish_update(optimizer)
if print_settings.get("print_after_training"):
msg.divider(f"STEP 2 - after training")
_print_model(model, print_settings)
# STEP 3: the final prediction
prediction = model.predict(X)
if print_settings.get("print_prediction"):
msg.divider(f"STEP 3 - prediction")
msg.info(str(prediction))
msg.good(f"Succesfully ended analysis - model looks good.")
def debug_model(
config,
resolved_train_config,
nlp,
pipe,
*,
print_settings: Optional[Dict[str, Any]] = None,
):
if not hasattr(pipe, "model"):
msg.fail(
f"The component '{pipe}' does not specify an object that holds a Model.",
exits=1,
)
model = pipe.model
if not isinstance(model, Model):
msg.fail(
f"Requires a Thinc Model to be analysed, but found {type(model)} instead.",
exits=1,
)
if print_settings is None:
print_settings = {}
# STEP 0: Printing before training
msg.info(f"Analysing model with ID {model.id}")
if print_settings.get("print_before_training"):
msg.divider(f"STEP 0 - before training")
_print_model(model, print_settings)
# STEP 1: Initializing the model and printing again
with data_validation(False):
try:
dot_names = [resolved_train_config["train_corpus"]]
with show_validation_error():
(train_corpus, ) = resolve_dot_names(config, dot_names)
nlp.initialize(lambda: train_corpus(nlp))
msg.info("Initialized the model with the training corpus.")
examples = list(itertools.islice(train_corpus(nlp), 5))
except ValueError:
try:
_set_output_dim(nO=7, model=model)
with show_validation_error():
examples = [Example.from_dict(x, {}) for x in _get_docs()]
nlp.initialize(lambda: examples)
msg.info("Initialized the model with dummy data.")
except Exception:
msg.fail(
"Could not initialize the model: you'll have to provide a valid 'train_corpus' argument in the config file.",
exits=1,
)
if print_settings.get("print_after_init"):
msg.divider(f"STEP 1 - after initialization")
_print_model(model, print_settings)
# STEP 2: Updating the model and printing again
set_dropout_rate(model, 0.2)
# ugly hack to deal with Tok2Vec/Transformer listeners
upstream_component = None
if model.has_ref("tok2vec") and "tok2vec-listener" in model.get_ref(
"tok2vec").name:
upstream_component = nlp.get_pipe("tok2vec")
if (model.has_ref("tok2vec")
and "transformer-listener" in model.get_ref("tok2vec").name):
upstream_component = nlp.get_pipe("transformer")
for e in range(3):
if upstream_component:
upstream_component.update(examples)
pipe.update(examples)
if print_settings.get("print_after_training"):
msg.divider(f"STEP 2 - after training")
_print_model(model, print_settings)
# STEP 3: the final prediction
prediction = model.predict([ex.predicted for ex in examples])
if print_settings.get("print_prediction"):
msg.divider(f"STEP 3 - prediction")
msg.info(str(prediction))
msg.good(f"Succesfully ended analysis - model looks good.")