def predict_with_model(config_path):
config = read_json(config_path)
set_deeppavlov_root(config)
reader_config = config['dataset_reader']
reader = get_model(reader_config['name'])()
data_path = expand_path(reader_config.get('data_path', ''))
read_params = {k: v for k, v in reader_config.items() if k not in ['name', 'data_path']}
data = reader.read(data_path, **read_params)
iterator_config = config['dataset_iterator']
iterator: MorphoTaggerDatasetIterator =\
from_params(iterator_config, data=data)
model = build_model_from_config(config, load_trained=True)
answers = [None] * len(iterator.test)
batch_size = config['predict'].get("batch_size", -1)
for indexes, (x, _) in iterator.gen_batches(
batch_size=batch_size, data_type="test", shuffle=False, return_indexes=True):
y = model(x)
for i, elem in zip(indexes, y):
answers[i] = elem
outfile = config['predict'].get("outfile")
if outfile is not None:
outfile = Path(outfile)
if not outfile.exists():
outfile.parent.mkdir(parents=True, exist_ok=True)
with open(outfile, "w", encoding="utf8") as fout:
for elem in answers:
fout.write(elem + "\n")
return answers
def get_default_agent():
model_config = read_json(model_config_path)
model = build_model_from_config(model_config)
skill = DefaultStatelessSkill(model)
agent = DefaultAgent([skill],
skills_processor=DefaultRichContentWrapper())
return agent
def from_params(params: Dict, mode: str = 'infer', **kwargs) -> Component:
"""Builds and returns the Component from corresponding dictionary of parameters."""
# what is passed in json:
config_params = {k: _resolve(v) for k, v in params.items()}
# get component by reference (if any)
if 'ref' in config_params:
try:
return _refs[config_params['ref']]
except KeyError:
e = ConfigError(
'Component with id "{id}" was referenced but not initialized'.
format(id=config_params['ref']))
log.exception(e)
raise e
elif 'config_path' in config_params:
from deeppavlov.core.commands.infer import build_model_from_config
deeppavlov_root = get_deeppavlov_root()
refs = _refs.copy()
_refs.clear()
config = read_json(expand_path(config_params['config_path']))
model = build_model_from_config(config)
set_deeppavlov_root({'deeppavlov_root': deeppavlov_root})
_refs.clear()
_refs.update(refs)
return model
elif 'class' in config_params:
cls = cls_from_str(config_params.pop('class'))
else:
cls_name = config_params.pop('name', None)
if not cls_name:
e = ConfigError(
'Component config has no `name` nor `ref` or `class` fields')
log.exception(e)
raise e
cls = get_model(cls_name)
# find the submodels params recursively
config_params = {k: _init_param(v, mode) for k, v in config_params.items()}
try:
spec = inspect.getfullargspec(cls)
if 'mode' in spec.args + spec.kwonlyargs or spec.varkw is not None:
kwargs['mode'] = mode
component = cls(**dict(config_params, **kwargs))
try:
_refs[config_params['id']] = component
except KeyError:
pass
except Exception:
log.exception("Exception in {}".format(cls))
raise
return component
def from_params(params: Dict, mode: str = 'infer', **kwargs) -> Component:
"""Builds and returns the Component from corresponding dictionary of parameters."""
# what is passed in json:
config_params = {k: _resolve(v) for k, v in params.items()}
# get component by reference (if any)
if 'ref' in config_params:
try:
return _refs[config_params['ref']]
except KeyError:
e = ConfigError('Component with id "{id}" was referenced but not initialized'
.format(id=config_params['ref']))
log.exception(e)
raise e
elif 'config_path' in config_params:
from deeppavlov.core.commands.infer import build_model_from_config
deeppavlov_root = get_deeppavlov_root()
refs = _refs.copy()
_refs.clear()
config = read_json(expand_path(config_params['config_path']))
model = build_model_from_config(config, as_component=True)
set_deeppavlov_root({'deeppavlov_root': deeppavlov_root})
_refs.clear()
_refs.update(refs)
return model
elif 'class' in config_params:
cls = cls_from_str(config_params.pop('class'))
else:
cls_name = config_params.pop('name', None)
if not cls_name:
e = ConfigError('Component config has no `name` nor `ref` or `class` fields')
log.exception(e)
raise e
cls = get_model(cls_name)
# find the submodels params recursively
config_params = {k: _init_param(v, mode) for k, v in config_params.items()}
try:
spec = inspect.getfullargspec(cls)
if 'mode' in spec.args+spec.kwonlyargs or spec.varkw is not None:
kwargs['mode'] = mode
component = cls(**dict(config_params, **kwargs))
try:
_refs[config_params['id']] = component
except KeyError:
pass
except Exception:
log.exception("Exception in {}".format(cls))
raise
return component
def make_agent() -> EcommerceAgent:
"""Make an agent
Returns:
agent: created Ecommerce agent
"""
config_path = find_config('ecommerce_bot')
skill = build_model_from_config(config_path, as_component=True)
agent = EcommerceAgent(skills=[skill])
return agent
def predict_with_model(config_path: [Path, str]) -> List[List[str]]:
"""Returns predictions of morphotagging model given in config :config_path:.
Args:
config_path: a path to config
Returns:
a list of morphological analyses for each sentence. Each analysis is either a list of tags
or a list of full CONLL-U descriptions.
"""
config = read_json(config_path)
set_deeppavlov_root(config)
reader_config = config['dataset_reader']
reader = get_model(reader_config['name'])()
data_path = expand_path(reader_config.get('data_path', ''))
read_params = {
k: v
for k, v in reader_config.items() if k not in ['name', 'data_path']
}
data: Dict = reader.read(data_path, **read_params)
iterator_config = config['dataset_iterator']
iterator: MorphoTaggerDatasetIterator = from_params(iterator_config,
data=data)
model = build_model_from_config(config, load_trained=True)
answers = [None] * len(iterator.test)
batch_size = config['predict'].get("batch_size", -1)
for indexes, (x, _) in iterator.gen_batches(batch_size=batch_size,
data_type="test",
shuffle=False,
return_indexes=True):
y = model(x)
for i, elem in zip(indexes, y):
answers[i] = elem
outfile = config['predict'].get("outfile")
if outfile is not None:
outfile = Path(outfile)
if not outfile.exists():
outfile.parent.mkdir(parents=True, exist_ok=True)
with open(outfile, "w", encoding="utf8") as fout:
for elem in answers:
fout.write(elem + "\n")
return answers
def init_agent():
demo = build_model_from_config(json.load(open('skill.demo.json')),
as_component=True)
open_account = build_model_from_config(json.load(
open('skill.open_account.json')),
as_component=True)
sms_inform = build_model_from_config(json.load(
open('skill.sms_inform.json')),
as_component=True)
tarifs = build_model_from_config(json.load(open('skill.tarifs.json')),
as_component=True)
faq = build_model_from_config(json.load(open('skill.faq.json')),
as_component=True)
classifier = build_model_from_config(json.load(
open('intent_classifier.json')),
as_component=True)
hello = RandomResponseSkill(responses=[
'Я Demo-Бот:) Чем могу помочь? Я умею рассказывать про открытие и резервирование счетов, тарифы на услуги и продуты, подключение SMS-информирование и отвечать на FAQ-вопросы.',
'Чем Вам помочь? Я умею рассказывать про открытие и резервирование счетов, тарифы на услуги и продуты, подключение SMS-информирование и отвечать на FAQ-вопросы.'
],
confidence=0.5)
knn_clf = build_model_from_config(json.load(open('knn_classifier.json')),
as_component=True)
intents = ['OTHER', 'OPEN_ACCOUNT', 'SMS_INFORM', 'RATES', 'FAQ']
filter = IntentFilter(intents, knn_clf, default_intent=0, always_open=[0])
agent = Agent([hello, demo, sms_inform, tarifs, faq],
skills_selector=HighestConfidenceSelector(),
skills_filter=filter)
return agent
def init_model(model_config_path):
model_config = read_json(model_config_path)
model = build_model_from_config(model_config)
return model
def __init__(self, config_path, download=False): if download == True: deep_download(config_path) self.model = build_model_from_config(config_path)
def from_params(params: Dict, mode='infer', **kwargs) -> Component:
# what is passed in json:
config_params = {k: _resolve(v) for k, v in params.items()}
# get component by reference (if any)
if 'ref' in config_params:
try:
return _refs[config_params['ref']]
except KeyError:
e = ConfigError('Component with id "{id}" was referenced but not initialized'
.format(id=config_params['ref']))
log.exception(e)
raise e
elif 'config_path' in config_params:
from deeppavlov.core.commands.infer import build_model_from_config
deeppavlov_root = get_deeppavlov_root()
refs = _refs.copy()
_refs.clear()
config = read_json(expand_path(config_params['config_path']))
model = build_model_from_config(config, as_component=True)
set_deeppavlov_root({'deeppavlov_root': deeppavlov_root})
_refs.clear()
_refs.update(refs)
return model
elif 'class' in config_params:
c = config_params.pop('class')
try:
module_name, cls_name = c.split(':')
cls = getattr(importlib.import_module(module_name), cls_name)
except ValueError:
e = ConfigError('Expected class description in a `module.submodules:ClassName` form, but got `{}`'
.format(c))
log.exception(e)
raise e
else:
cls_name = config_params.pop('name', None)
if not cls_name:
e = ConfigError('Component config has no `name` nor `ref` or `class` fields')
log.exception(e)
raise e
try:
cls = REGISTRY[cls_name]
except KeyError:
e = ConfigError('Class {} is not registered.'.format(cls_name))
log.exception(e)
raise e
# find the submodels params recursively
config_params = {k: _init_param(v, mode) for k, v in config_params.items()}
try:
spec = inspect.getfullargspec(cls)
if 'mode' in spec.args+spec.kwonlyargs or spec.varkw is not None:
kwargs['mode'] = mode
component = cls(**dict(config_params, **kwargs))
try:
_refs[config_params['id']] = component
except KeyError:
pass
except Exception:
log.exception("Exception in {}".format(cls))
raise
return component
def init_model(model_config_path):
config = read_json(model_config_path)
model = build_model_from_config(config)
model_name = type(model.get_main_component()).__name__
return model, model_name
def train_evaluate_model_from_config(config: [str, Path, dict], to_train: bool = True, to_validate: bool = True) -> None:
"""Make training and evaluation of the model described in corresponding configuration file."""
if isinstance(config, (str, Path)):
config = read_json(config)
set_deeppavlov_root(config)
import_packages(config.get('metadata', {}).get('imports', []))
dataset_config = config.get('dataset', None)
if dataset_config:
config.pop('dataset')
ds_type = dataset_config['type']
if ds_type == 'classification':
reader = {'name': 'basic_classification_reader'}
iterator = {'name': 'basic_classification_iterator'}
config['dataset_reader'] = {**dataset_config, **reader}
config['dataset_iterator'] = {**dataset_config, **iterator}
else:
raise Exception("Unsupported dataset type: {}".format(ds_type))
data = []
reader_config = config.get('dataset_reader', None)
if reader_config:
reader_config = config['dataset_reader']
if 'class' in reader_config:
c = reader_config.pop('class')
try:
module_name, cls_name = c.split(':')
reader = getattr(importlib.import_module(module_name), cls_name)()
except ValueError:
e = ConfigError('Expected class description in a `module.submodules:ClassName` form, but got `{}`'
.format(c))
log.exception(e)
raise e
else:
reader = get_model(reader_config.pop('name'))()
data_path = reader_config.pop('data_path', '')
if isinstance(data_path, list):
data_path = [expand_path(x) for x in data_path]
else:
data_path = expand_path(data_path)
data = reader.read(data_path, **reader_config)
else:
log.warning("No dataset reader is provided in the JSON config.")
iterator_config = config['dataset_iterator']
iterator: Union[DataLearningIterator, DataFittingIterator] = from_params(iterator_config,
data=data)
train_config = {
'metrics': ['accuracy'],
'validate_best': to_validate,
'test_best': True,
'show_examples': False
}
try:
train_config.update(config['train'])
except KeyError:
log.warning('Train config is missing. Populating with default values')
metrics_functions = list(zip(train_config['metrics'], get_metrics_by_names(train_config['metrics'])))
if to_train:
model = fit_chainer(config, iterator)
if callable(getattr(model, 'train_on_batch', None)):
_train_batches(model, iterator, train_config, metrics_functions)
elif callable(getattr(model, 'fit_batches', None)):
_fit_batches(model, iterator, train_config)
elif callable(getattr(model, 'fit', None)):
_fit(model, iterator, train_config)
elif not isinstance(model, Chainer):
log.warning('Nothing to train')
if train_config['validate_best'] or train_config['test_best']:
# try:
# model_config['load_path'] = model_config['save_path']
# except KeyError:
# log.warning('No "save_path" parameter for the model, so "load_path" will not be renewed')
model = build_model_from_config(config, load_trained=True)
log.info('Testing the best saved model')
if train_config['validate_best']:
report = {
'valid': _test_model(model, metrics_functions, iterator,
train_config.get('batch_size', -1), 'valid',
show_examples=train_config['show_examples'])
}
print(json.dumps(report, ensure_ascii=False))
if train_config['test_best']:
report = {
'test': _test_model(model, metrics_functions, iterator,
train_config.get('batch_size', -1), 'test',
show_examples=train_config['show_examples'])
}
print(json.dumps(report, ensure_ascii=False))
def interact_model_by_telegram(config_path, token):
config = read_json(config_path)
model = build_model_from_config(config)
init_bot_for_model(token, model)
def init_model(model_config_path):
model_config = read_json(model_config_path)
model = build_model_from_config(model_config)
return model
def train_evaluate_model_from_config(
config: [str, Path, dict],
iterator=None,
to_train=True,
to_validate=True) -> Dict[str, Dict[str, float]]:
"""Make training and evaluation of the model described in corresponding configuration file."""
if isinstance(config, (str, Path)):
config = read_json(config)
set_deeppavlov_root(config)
import_packages(config.get('metadata', {}).get('imports', []))
if iterator is None:
data = read_data_by_config(config)
iterator = get_iterator_from_config(config, data)
train_config = {
'metrics': ['accuracy'],
'validate_best': to_validate,
'test_best': True,
'show_examples': False
}
try:
train_config.update(config['train'])
except KeyError:
log.warning('Train config is missing. Populating with default values')
in_y = config['chainer'].get('in_y', ['y'])
if isinstance(in_y, str):
in_y = [in_y]
if isinstance(config['chainer']['out'], str):
config['chainer']['out'] = [config['chainer']['out']]
metrics_functions = _parse_metrics(train_config['metrics'], in_y,
config['chainer']['out'])
if to_train:
model = fit_chainer(config, iterator)
if callable(getattr(model, 'train_on_batch', None)):
_train_batches(model, iterator, train_config, metrics_functions)
elif callable(getattr(model, 'fit_batches', None)):
_fit_batches(model, iterator, train_config)
elif callable(getattr(model, 'fit', None)):
_fit(model, iterator, train_config)
elif not isinstance(model, Chainer):
log.warning('Nothing to train')
model.destroy()
res = {}
if train_config['validate_best'] or train_config['test_best']:
# try:
# model_config['load_path'] = model_config['save_path']
# except KeyError:
# log.warning('No "save_path" parameter for the model, so "load_path" will not be renewed')
model = build_model_from_config(config, load_trained=True)
log.info('Testing the best saved model')
if train_config['validate_best']:
report = {
'valid':
_test_model(model,
metrics_functions,
iterator,
train_config.get('batch_size', -1),
'valid',
show_examples=train_config['show_examples'])
}
res['valid'] = report['valid']['metrics']
print(json.dumps(report, ensure_ascii=False))
if train_config['test_best']:
report = {
'test':
_test_model(model,
metrics_functions,
iterator,
train_config.get('batch_size', -1),
'test',
show_examples=train_config['show_examples'])
}
res['test'] = report['test']['metrics']
print(json.dumps(report, ensure_ascii=False))
model.destroy()
return res
from deeppavlov.core.commands.infer import build_model_from_config
import thulac as thu
model = build_model_from_config(
"E:/GithubSpace/DeepPavlov/deeppavlov/configs/ner/wzh_single_ner_config.json"
)
thu1 = thu.thulac(seg_only=True, user_dict="user_DIY_words.txt")
s0 = thu1.cut("双十一期间全场包邮买100立减30", text=True)
# s0 = s0.split(" ")
# print(s0)
# ss = str(input("请输入： "))
# s0 = thu1.cut(ss, text=True)
# print(s0.split(" "))
for i in range(50):
# print(model(input("请输入： ")))
s1 = input("请输入： ")
s2 = thu1.cut(s1, text=True)
print(model([s2.split(" ")]))
# print(model([input("请输入： ")]))
# 训练语句如下，要手动把迭代器送进去 因为配置文件没读取器
# from deeppavlov.core.common.params import from_params
# train_evaluate_model_from_config("E:/GithubSpace/DeepPavlov/deeppavlov/configs/ner/wzh_single_ner_config.json",
# from_params({"name": "wzh_ner_iterator"}))
def interact_model_by_telegram(config_path, token):
config = read_json(config_path)
model = build_model_from_config(config)
init_bot_for_model(token, model)
def train_model_from_config(config_path: str):
config = read_json(config_path)
set_deeppavlov_root(config)
reader_config = config['dataset_reader']
reader = get_model(reader_config['name'])()
data_path = expand_path(reader_config.get('data_path', ''))
data = reader.read(data_path)
dataset_config = config['dataset']
dataset: Dataset = from_params(dataset_config, data=data)
if 'chainer' in config:
model = fit_chainer(config, dataset)
else:
vocabs = {}
for vocab_param_name, vocab_config in config.get('vocabs', {}).items():
v: Estimator = from_params(vocab_config, mode='train')
vocabs[vocab_param_name] = _fit(v, dataset)
model_config = config['model']
model = from_params(model_config, vocabs=vocabs, mode='train')
train_config = {
'metrics': ['accuracy'],
'validate_best': True,
'test_best': True
}
try:
train_config.update(config['train'])
except KeyError:
log.warning('Train config is missing. Populating with default values')
metrics_functions = list(
zip(train_config['metrics'],
get_metrics_by_names(train_config['metrics'])))
if callable(getattr(model, 'train_on_batch', None)):
_train_batches(model, dataset, train_config, metrics_functions)
elif callable(getattr(model, 'fit', None)):
_fit(model, dataset, train_config)
elif not isinstance(model, Chainer):
log.warning('Nothing to train')
if train_config['validate_best'] or train_config['test_best']:
# try:
# model_config['load_path'] = model_config['save_path']
# except KeyError:
# log.warning('No "save_path" parameter for the model, so "load_path" will not be renewed')
model = build_model_from_config(config, load_trained=True)
log.info('Testing the best saved model')
if train_config['validate_best']:
report = {
'valid':
_test_model(model, metrics_functions, dataset,
train_config.get('batch_size', -1), 'valid')
}
print(json.dumps(report, ensure_ascii=False))
if train_config['test_best']:
report = {
'test':
_test_model(model, metrics_functions, dataset,
train_config.get('batch_size', -1), 'test')
}
print(json.dumps(report, ensure_ascii=False))
'save_path': 'dstc2/resto.sqlite',
'primary_keys': ['name'],
'table_name': 'mytable'
}
""" Adding vocab and database components to pipe """
db_config['chainer']['pipe'] = []
db_config['chainer']['pipe'].append(vocab_comp_config)
db_config['chainer']['pipe'].append(db_comp_config)
""" Adding database to bot component config """
bot_with_db_comp_config['database'] = '#restaurant_database'
""" Adding bot component to pipe """
db_config['chainer']['pipe'].append(bot_with_db_comp_config)
json.dump(db_config, open("gobot/db_config.json", 'wt'))
"""
Model training and building
"""
""" Train gobot_dstc2_db model """
# train_evaluate_model_from_config("gobot/db_config.json")
""" build model """
model = build_model_from_config(db_config)
"""
Dialogue system
"""
" starting new dialog, if the cell is running, please do not run other cells in parallel -- there is a possibility of a hangup"
model.reset()
utterance = ""
while utterance != 'exit':
print(">> " + model([utterance])[0])
utterance = input(':: ')
from flask import Flask
from redis import Redis
from deeppavlov.core.commands.infer import build_model_from_config
from deeppavlov.core.common.file import read_json
CONFIG_PATH = '/home/DeepPavlov/deeppavlov/configs/seq2seq_go_bot/bot_kvret_infer.json'
model = build_model_from_config(read_json(CONFIG_PATH))
utterance = ""
while utterance != 'exit':
print(">> " + model([utterance])[0])
utterance = input(':: ')
if __name__ == "__main__":
app.run(host="0.0.0.0", debug=True)
def from_params(params: Dict, **kwargs) -> Component:
# what is passed in json:
config_params = {k: _resolve(v) for k, v in params.items()}
# get component by reference (if any)
if 'ref' in config_params:
try:
return _refs[config_params['ref']]
except KeyError:
e = ConfigError(
'Component with id "{id}" was referenced but not initialized'.
format(id=config_params['ref']))
log.exception(e)
raise e
elif 'config_path' in config_params:
from deeppavlov.core.commands.infer import build_model_from_config
deeppavlov_root = get_deeppavlov_root()
config = read_json(expand_path(config_params['config_path']))
model = build_model_from_config(config, as_component=True)
set_deeppavlov_root({'deeppavlov_root': deeppavlov_root})
return model
elif 'class' in config_params:
c = config_params.pop('class')
try:
module_name, cls_name = c.split(':')
cls = getattr(importlib.import_module(module_name), cls_name)
except ValueError:
e = ConfigError(
'Expected class description in a `module.submodules:ClassName` form, but got `{}`'
.format(c))
log.exception(e)
raise e
else:
cls_name = config_params.pop('name', None)
if not cls_name:
e = ConfigError(
'Component config has no `name` nor `ref` or `class` fields')
log.exception(e)
raise e
try:
cls = REGISTRY[cls_name]
except KeyError:
e = ConfigError('Class {} is not registered.'.format(cls_name))
log.exception(e)
raise e
# find the submodels params recursively
for param_name, subcls_params in config_params.items():
if isinstance(subcls_params, dict):
if not {'ref', 'name', 'class', 'config_path'
}.intersection(subcls_params):
"This parameter is passed as dict to the class constructor."
" The user didn't intent it to be a component."
for k, v in subcls_params.items():
subcls_params[k] = _resolve(v)
continue
config_params[param_name] = from_params(subcls_params,
vocabs=kwargs['vocabs'],
mode=kwargs['mode'])
try:
component = cls(**dict(config_params, **kwargs))
try:
_refs[config_params['id']] = component
except KeyError:
pass
except Exception:
log.exception("Exception in {}".format(cls))
raise
return component
def train_evaluate_model_from_config(config: [str, Path, dict],
to_train=True,
to_validate=True) -> None:
if isinstance(config, (str, Path)):
config = read_json(config)
set_deeppavlov_root(config)
import_packages(config.get('metadata', {}).get('imports', []))
dataset_config = config.get('dataset', None)
if dataset_config:
config.pop('dataset')
ds_type = dataset_config['type']
if ds_type == 'classification':
reader = {'name': 'basic_classification_reader'}
iterator = {'name': 'basic_classification_iterator'}
config['dataset_reader'] = {**dataset_config, **reader}
config['dataset_iterator'] = {**dataset_config, **iterator}
else:
raise Exception("Unsupported dataset type: {}".format(ds_type))
data = []
reader_config = config.get('dataset_reader', None)
if reader_config:
reader_config = config['dataset_reader']
if 'class' in reader_config:
c = reader_config.pop('class')
try:
module_name, cls_name = c.split(':')
reader = getattr(importlib.import_module(module_name),
cls_name)()
except ValueError:
e = ConfigError(
'Expected class description in a `module.submodules:ClassName` form, but got `{}`'
.format(c))
log.exception(e)
raise e
else:
reader = get_model(reader_config.pop('name'))()
data_path = expand_path(reader_config.pop('data_path', ''))
data = reader.read(data_path, **reader_config)
else:
log.warning("No dataset reader is provided in the JSON config.")
iterator_config = config['dataset_iterator']
iterator: Union[DataLearningIterator,
DataFittingIterator] = from_params(iterator_config,
data=data)
train_config = {
'metrics': ['accuracy'],
'validate_best': to_validate,
'test_best': True
}
try:
train_config.update(config['train'])
except KeyError:
log.warning('Train config is missing. Populating with default values')
metrics_functions = list(
zip(train_config['metrics'],
get_metrics_by_names(train_config['metrics'])))
if to_train:
model = fit_chainer(config, iterator)
if callable(getattr(model, 'train_on_batch', None)):
_train_batches(model, iterator, train_config, metrics_functions)
elif callable(getattr(model, 'fit_batches', None)):
_fit_batches(model, iterator, train_config)
elif callable(getattr(model, 'fit', None)):
_fit(model, iterator, train_config)
elif not isinstance(model, Chainer):
log.warning('Nothing to train')
if train_config['validate_best'] or train_config['test_best']:
# try:
# model_config['load_path'] = model_config['save_path']
# except KeyError:
# log.warning('No "save_path" parameter for the model, so "load_path" will not be renewed')
model = build_model_from_config(config, load_trained=True)
log.info('Testing the best saved model')
if train_config['validate_best']:
report = {
'valid':
_test_model(model, metrics_functions, iterator,
train_config.get('batch_size', -1), 'valid')
}
print(json.dumps(report, ensure_ascii=False))
if train_config['test_best']:
report = {
'test':
_test_model(model, metrics_functions, iterator,
train_config.get('batch_size', -1), 'test')
}
print(json.dumps(report, ensure_ascii=False))
def train_model_from_config(config_path: str) -> None:
config = read_json(config_path)
set_deeppavlov_root(config)
dataset_config = config.get('dataset', None)
if dataset_config:
config.pop('dataset')
ds_type = dataset_config['type']
if ds_type == 'classification':
reader = {'name': 'basic_classification_reader'}
iterator = {'name': 'basic_classification_iterator'}
config['dataset_reader'] = {**dataset_config, **reader}
config['dataset_iterator'] = {**dataset_config, **iterator}
else:
raise Exception("Unsupported dataset type: {}".format(ds_type))
reader_config = config['dataset_reader']
reader = get_model(reader_config['name'])()
data_path = expand_path(reader_config.get('data_path', ''))
kwargs = {
k: v
for k, v in reader_config.items() if k not in ['name', 'data_path']
}
data = reader.read(data_path, **kwargs)
iterator_config = config['dataset_iterator']
iterator: BasicDatasetIterator = from_params(iterator_config, data=data)
if 'chainer' in config:
model = fit_chainer(config, iterator)
else:
vocabs = config.get('vocabs', {})
for vocab_param_name, vocab_config in vocabs.items():
v: Estimator = from_params(vocab_config, mode='train')
vocabs[vocab_param_name] = _fit(v, iterator)
model_config = config['model']
model = from_params(model_config, vocabs=vocabs, mode='train')
train_config = {
'metrics': ['accuracy'],
'validate_best': True,
'test_best': True
}
try:
train_config.update(config['train'])
except KeyError:
log.warning('Train config is missing. Populating with default values')
metrics_functions = list(
zip(train_config['metrics'],
get_metrics_by_names(train_config['metrics'])))
if callable(getattr(model, 'train_on_batch', None)):
_train_batches(model, iterator, train_config, metrics_functions)
elif callable(getattr(model, 'fit', None)):
_fit(model, iterator, train_config)
elif not isinstance(model, Chainer):
log.warning('Nothing to train')
if train_config['validate_best'] or train_config['test_best']:
# try:
# model_config['load_path'] = model_config['save_path']
# except KeyError:
# log.warning('No "save_path" parameter for the model, so "load_path" will not be renewed')
model = build_model_from_config(config, load_trained=True)
log.info('Testing the best saved model')
if train_config['validate_best']:
report = {
'valid':
_test_model(model, metrics_functions, iterator,
train_config.get('batch_size', -1), 'valid')
}
print(json.dumps(report, ensure_ascii=False))
if train_config['test_best']:
report = {
'test':
_test_model(model, metrics_functions, iterator,
train_config.get('batch_size', -1), 'test')
}
print(json.dumps(report, ensure_ascii=False))
