def test_case_1(self):
args = {
"epochs": 3,
"batch_size": 8,
"validate": True,
"use_cuda": True,
"pickle_path": "./save/",
"save_best_dev": True,
"model_name": "default_model_name.pkl",
"loss": Loss(None),
"optimizer": Optimizer("Adam", lr=0.001, weight_decay=0),
"vocab_size": 20,
"word_emb_dim": 100,
"rnn_hidden_units": 100,
"num_classes": 3
}
trainer = SeqLabelTrainer()
train_data = [
[[1, 2, 3, 4, 5, 6], [1, 0, 1, 0, 1, 2]],
[[2, 3, 4, 5, 1, 6], [0, 1, 0, 1, 0, 2]],
[[1, 4, 1, 4, 1, 6], [1, 0, 1, 0, 1, 2]],
[[1, 2, 3, 4, 5, 6], [1, 0, 1, 0, 1, 2]],
[[2, 3, 4, 5, 1, 6], [0, 1, 0, 1, 0, 2]],
[[1, 4, 1, 4, 1, 6], [1, 0, 1, 0, 1, 2]],
]
dev_data = train_data
model = SeqLabeling(args)
trainer.train(network=model, train_data=train_data, dev_data=dev_data)
def test_case_1(self):
args = {
"epochs": 3,
"batch_size": 2,
"validate": False,
"use_cuda": False,
"pickle_path": "./save/",
"save_best_dev": True,
"model_name": "default_model_name.pkl",
"loss": Loss("cross_entropy"),
"optimizer": Optimizer("Adam", lr=0.001, weight_decay=0),
"vocab_size": 10,
"word_emb_dim": 100,
"rnn_hidden_units": 100,
"num_classes": 5,
"evaluator": SeqLabelEvaluator()
}
trainer = SeqLabelTrainer(**args)
train_data = [
[['a', 'b', 'c', 'd', 'e'], ['a', '@', 'c', 'd', 'e']],
[['a', '@', 'c', 'd', 'e'], ['a', '@', 'c', 'd', 'e']],
[['a', 'b', '#', 'd', 'e'], ['a', '@', 'c', 'd', 'e']],
[['a', 'b', 'c', '?', 'e'], ['a', '@', 'c', 'd', 'e']],
[['a', 'b', 'c', 'd', '$'], ['a', '@', 'c', 'd', 'e']],
[['!', 'b', 'c', 'd', 'e'], ['a', '@', 'c', 'd', 'e']],
]
vocab = {
'a': 0,
'b': 1,
'c': 2,
'd': 3,
'e': 4,
'!': 5,
'@': 6,
'#': 7,
'$': 8,
'?': 9
}
label_vocab = {'a': 0, '@': 1, 'c': 2, 'd': 3, 'e': 4}
data_set = DataSet()
for example in train_data:
text, label = example[0], example[1]
x = TextField(text, False)
x_len = LabelField(len(text), is_target=False)
y = TextField(label, is_target=False)
ins = Instance(word_seq=x, truth=y, word_seq_origin_len=x_len)
data_set.append(ins)
data_set.index_field("word_seq", vocab)
data_set.index_field("truth", label_vocab)
model = SeqLabeling(args)
trainer.train(network=model, train_data=data_set, dev_data=data_set)
# If this can run, everything is OK.
os.system("rm -rf save")
print("pickle path deleted")
def __init__(self,
train_data,
model,
n_epochs=3,
batch_size=32,
print_every=-1,
validate_every=-1,
dev_data=None,
use_cuda=False,
save_path="./save",
optimizer=Optimizer("Adam", lr=0.01, weight_decay=0),
need_check_code=True,
**kwargs):
super(Trainer, self).__init__()
self.train_data = train_data
self.dev_data = dev_data # If None, No validation.
self.model = model
self.n_epochs = int(n_epochs)
self.batch_size = int(batch_size)
self.use_cuda = bool(use_cuda)
self.save_path = save_path
self.print_every = int(print_every)
self.validate_every = int(validate_every)
self._best_accuracy = 0
if need_check_code:
_check_code(dataset=train_data, model=model, dev_data=dev_data)
model_name = model.__class__.__name__
assert hasattr(
self.model,
'get_loss'), "model {} has to have a 'get_loss' function.".format(
model_name)
self.loss_func = self.model.get_loss
if isinstance(optimizer, torch.optim.Optimizer):
self.optimizer = optimizer
else:
self.optimizer = optimizer.construct_from_pytorch(
self.model.parameters())
assert hasattr(
self.model,
'evaluate'), "model {} has to have a 'evaluate' function.".format(
model_name)
self.evaluator = self.model.evaluate
if self.dev_data is not None:
self.tester = Tester(model=self.model,
data=self.dev_data,
batch_size=self.batch_size,
use_cuda=self.use_cuda)
for k, v in kwargs.items():
setattr(self, k, v)
self.step = 0
self.start_time = None # start timestamp
def train():
train_args, model_args = ConfigSection(), ConfigSection()
ConfigLoader.load_config(config_dir, {"text_class": train_args})
# load dataset
print("Loading data...")
ds_loader = ClassDatasetLoader(train_data_dir)
data = ds_loader.load()
print(data[0])
# pre-process data
pre = ClassPreprocess()
data_train = pre.run(data, pickle_path=save_dir)
print("vocabulary size:", pre.vocab_size)
print("number of classes:", pre.num_classes)
model_args["num_classes"] = pre.num_classes
model_args["vocab_size"] = pre.vocab_size
# construct model
print("Building model...")
model = CNNText(model_args)
# ConfigSaver().save_config(config_dir, {"text_class_model": model_args})
# train
print("Training...")
# 1
# trainer = ClassificationTrainer(train_args)
# 2
trainer = ClassificationTrainer(epochs=train_args["epochs"],
batch_size=train_args["batch_size"],
validate=train_args["validate"],
use_cuda=train_args["use_cuda"],
pickle_path=save_dir,
save_best_dev=train_args["save_best_dev"],
model_name=model_name,
loss=Loss("cross_entropy"),
optimizer=Optimizer("SGD",
lr=0.001,
momentum=0.9))
trainer.train(model, data_train)
print("Training finished!")
saver = ModelSaver(os.path.join(save_dir, model_name))
saver.save_pytorch(model)
print("Model saved!")
def train():
train_args, model_args = ConfigSection(), ConfigSection()
ConfigLoader.load_config(config_dir, {"text_class": train_args})
# load dataset
print("Loading data...")
data = TextClassifyDataSet(load_func=ClassDataSetLoader.load)
data.load(train_data_dir)
print("vocabulary size:", len(data.word_vocab))
print("number of classes:", len(data.label_vocab))
save_pickle(data.word_vocab, save_dir, "word2id.pkl")
save_pickle(data.label_vocab, save_dir, "label2id.pkl")
model_args["num_classes"] = len(data.label_vocab)
model_args["vocab_size"] = len(data.word_vocab)
# construct model
print("Building model...")
model = CNNText(model_args)
# train
print("Training...")
trainer = ClassificationTrainer(epochs=train_args["epochs"],
batch_size=train_args["batch_size"],
validate=train_args["validate"],
use_cuda=train_args["use_cuda"],
pickle_path=save_dir,
save_best_dev=train_args["save_best_dev"],
model_name=model_name,
loss=Loss("cross_entropy"),
optimizer=Optimizer("SGD", lr=0.001, momentum=0.9))
trainer.train(model, data)
print("Training finished!")
saver = ModelSaver(os.path.join(save_dir, model_name))
saver.save_pytorch(model)
print("Model saved!")
def __init__(self, **kwargs):
"""
:param kwargs: dict of (key, value), or dict-like object. key is str.
The base trainer requires the following keys:
- epochs: int, the number of epochs in training
- validate: bool, whether or not to validate on dev set
- batch_size: int
- pickle_path: str, the path to pickle files for pre-processing
"""
super(BaseTrainer, self).__init__()
"""
"default_args" provides default value for important settings.
The initialization arguments "kwargs" with the same key (name) will override the default value.
"kwargs" must have the same type as "default_args" on corresponding keys.
Otherwise, error will raise.
"""
default_args = {
"epochs": 3,
"batch_size": 8,
"validate": True,
"use_cuda": True,
"pickle_path": "./save/",
"save_best_dev": True,
"model_name": "default_model_name.pkl",
"print_every_step": 1,
"loss": Loss(None), # used to pass type check
"optimizer": Optimizer("Adam", lr=0.001, weight_decay=0)
}
"""
"required_args" is the collection of arguments that users must pass to Trainer explicitly.
This is used to warn users of essential settings in the training.
Specially, "required_args" does not have default value, so they have nothing to do with "default_args".
"""
required_args = {
"task" # one of ("seq_label", "text_classify")
}
for req_key in required_args:
if req_key not in kwargs:
logger.error("Trainer lacks argument {}".format(req_key))
raise ValueError("Trainer lacks argument {}".format(req_key))
self._task = kwargs["task"]
for key in default_args:
if key in kwargs:
if isinstance(kwargs[key], type(default_args[key])):
default_args[key] = kwargs[key]
else:
msg = "Argument %s type mismatch: expected %s while get %s" % (
key, type(default_args[key]), type(kwargs[key]))
logger.error(msg)
raise ValueError(msg)
else:
# BaseTrainer doesn't care about extra arguments
pass
print(default_args)
self.n_epochs = default_args["epochs"]
self.batch_size = default_args["batch_size"]
self.pickle_path = default_args["pickle_path"]
self.validate = default_args["validate"]
self.save_best_dev = default_args["save_best_dev"]
self.use_cuda = default_args["use_cuda"]
self.model_name = default_args["model_name"]
self.print_every_step = default_args["print_every_step"]
self._model = None
self._loss_func = default_args["loss"].get(
) # return a pytorch loss function or None
self._optimizer = None
self._optimizer_proto = default_args["optimizer"]
self._summary_writer = SummaryWriter(self.pickle_path +
'tensorboard_logs')
self._graph_summaried = False
self._best_accuracy = 0.0
def test_training():
# Config Loader
trainer_args = ConfigSection()
model_args = ConfigSection()
ConfigLoader().load_config(config_dir, {
"test_seq_label_trainer": trainer_args, "test_seq_label_model": model_args})
data_set = TokenizeDataSetLoader().load(data_path)
word_vocab = Vocabulary()
label_vocab = Vocabulary()
data_set.update_vocab(word_seq=word_vocab, label_seq=label_vocab)
data_set.index_field("word_seq", word_vocab).index_field("label_seq", label_vocab)
data_set.set_origin_len("word_seq")
data_set.rename_field("label_seq", "truth").set_target(truth=False)
data_train, data_dev = data_set.split(0.3, shuffle=True)
model_args["vocab_size"] = len(word_vocab)
model_args["num_classes"] = len(label_vocab)
save_pickle(word_vocab, pickle_path, "word2id.pkl")
save_pickle(label_vocab, pickle_path, "label2id.pkl")
trainer = SeqLabelTrainer(
epochs=trainer_args["epochs"],
batch_size=trainer_args["batch_size"],
validate=False,
use_cuda=False,
pickle_path=pickle_path,
save_best_dev=trainer_args["save_best_dev"],
model_name=model_name,
optimizer=Optimizer("SGD", lr=0.01, momentum=0.9),
)
# Model
model = SeqLabeling(model_args)
# Start training
trainer.train(model, data_train, data_dev)
# Saver
saver = ModelSaver(os.path.join(pickle_path, model_name))
saver.save_pytorch(model)
del model, trainer
# Define the same model
model = SeqLabeling(model_args)
# Dump trained parameters into the model
ModelLoader.load_pytorch(model, os.path.join(pickle_path, model_name))
# Load test configuration
tester_args = ConfigSection()
ConfigLoader().load_config(config_dir, {"test_seq_label_tester": tester_args})
# Tester
tester = SeqLabelTester(batch_size=4,
use_cuda=False,
pickle_path=pickle_path,
model_name="seq_label_in_test.pkl",
evaluator=SeqLabelEvaluator()
)
# Start testing with validation data
data_dev.set_target(truth=True)
tester.test(model, data_dev)
# construct model
model_args = {
'num_classes': n_classes,
'vocab_size': vocab_size
}
model = ClassificationModel(num_classes=n_classes, vocab_size=vocab_size)
# construct trainer
train_args = {
"epochs": 3,
"batch_size": 16,
"pickle_path": data_dir,
"validate": False,
"save_best_dev": False,
"model_saved_path": None,
"use_cuda": True,
"loss": Loss("cross_entropy"),
"optimizer": Optimizer("Adam", lr=0.001)
}
trainer = ClassificationTrainer(**train_args)
# start training
trainer.train(model, train_data=train_set, dev_data=dev_set)
# predict using model
data_infer = [x[0] for x in data]
infer = ClassificationInfer(data_dir)
labels_pred = infer.predict(model.cpu(), data_infer)
print(labels_pred)
def train_and_test():
# Config Loader
trainer_args = ConfigSection()
model_args = ConfigSection()
ConfigLoader("config.cfg").load_config(config_dir, {
"test_seq_label_trainer": trainer_args,
"test_seq_label_model": model_args
})
# Data Loader
pos_loader = POSDatasetLoader(data_path)
train_data = pos_loader.load_lines()
# Preprocessor
p = SeqLabelPreprocess()
data_train, data_dev = p.run(train_data,
pickle_path=pickle_path,
train_dev_split=0.5)
model_args["vocab_size"] = p.vocab_size
model_args["num_classes"] = p.num_classes
# Trainer: two definition styles
# 1
# trainer = SeqLabelTrainer(trainer_args.data)
# 2
trainer = SeqLabelTrainer(
epochs=trainer_args["epochs"],
batch_size=trainer_args["batch_size"],
validate=trainer_args["validate"],
use_cuda=trainer_args["use_cuda"],
pickle_path=pickle_path,
save_best_dev=trainer_args["save_best_dev"],
model_name=model_name,
optimizer=Optimizer("SGD", lr=0.01, momentum=0.9),
)
# Model
model = SeqLabeling(model_args)
# Start training
trainer.train(model, data_train, data_dev)
print("Training finished!")
# Saver
saver = ModelSaver(os.path.join(pickle_path, model_name))
saver.save_pytorch(model)
print("Model saved!")
del model, trainer, pos_loader
# Define the same model
model = SeqLabeling(model_args)
# Dump trained parameters into the model
ModelLoader.load_pytorch(model, os.path.join(pickle_path, model_name))
print("model loaded!")
# Load test configuration
tester_args = ConfigSection()
ConfigLoader("config.cfg").load_config(
config_dir, {"test_seq_label_tester": tester_args})
# Tester
tester = SeqLabelTester(save_output=False,
save_loss=False,
save_best_dev=False,
batch_size=4,
use_cuda=False,
pickle_path=pickle_path,
model_name="seq_label_in_test.pkl",
print_every_step=1)
# Start testing with validation data
tester.test(model, data_dev)
# print test results
print(tester.show_metrics())
print("model tested!")
def train_and_test():
# Config Loader
trainer_args = ConfigSection()
model_args = ConfigSection()
ConfigLoader().load_config(config_dir, {
"test_seq_label_trainer": trainer_args,
"test_seq_label_model": model_args
})
data_set = SeqLabelDataSet()
data_set.load(data_path)
train_set, dev_set = data_set.split(0.3, shuffle=True)
model_args["vocab_size"] = len(data_set.word_vocab)
model_args["num_classes"] = len(data_set.label_vocab)
save_pickle(data_set.word_vocab, pickle_path, "word2id.pkl")
save_pickle(data_set.label_vocab, pickle_path, "label2id.pkl")
trainer = SeqLabelTrainer(
epochs=trainer_args["epochs"],
batch_size=trainer_args["batch_size"],
validate=False,
use_cuda=trainer_args["use_cuda"],
pickle_path=pickle_path,
save_best_dev=trainer_args["save_best_dev"],
model_name=model_name,
optimizer=Optimizer("SGD", lr=0.01, momentum=0.9),
)
# Model
model = SeqLabeling(model_args)
# Start training
trainer.train(model, train_set, dev_set)
print("Training finished!")
# Saver
saver = ModelSaver(os.path.join(pickle_path, model_name))
saver.save_pytorch(model)
print("Model saved!")
del model, trainer
change_field_is_target(dev_set, "truth", True)
# Define the same model
model = SeqLabeling(model_args)
# Dump trained parameters into the model
ModelLoader.load_pytorch(model, os.path.join(pickle_path, model_name))
print("model loaded!")
# Load test configuration
tester_args = ConfigSection()
ConfigLoader().load_config(config_dir,
{"test_seq_label_tester": tester_args})
# Tester
tester = SeqLabelTester(batch_size=4,
use_cuda=False,
pickle_path=pickle_path,
model_name="seq_label_in_test.pkl",
evaluator=SeqLabelEvaluator())
# Start testing with validation data
tester.test(model, dev_set)
print("model tested!")