Python params.Params方法代码示例

# 需要导入模块: from allennlp.common import params [as 别名]
# 或者: from allennlp.common.params import Params [as 别名]
def test_from_params_extend_config(self):

        vocab_dir = self.TEST_DIR / "vocab_save"
        original_vocab = Vocabulary(non_padded_namespaces=["tokens"])
        original_vocab.add_token_to_namespace("a", namespace="tokens")
        original_vocab.save_to_files(vocab_dir)

        text_field = TextField(
            [Token(t) for t in ["a", "b"]], {"tokens": SingleIdTokenIndexer("tokens")}
        )
        instances = Batch([Instance({"text": text_field})])

        # If you ask to extend vocab from `directory`, instances must be passed
        # in Vocabulary constructor, or else there is nothing to extend to.
        params = Params({"type": "extend", "directory": vocab_dir})
        with pytest.raises(ConfigurationError):
            _ = Vocabulary.from_params(params)

        # If you ask to extend vocab, `directory` key must be present in params,
        # or else there is nothing to extend from.
        params = Params({"type": "extend"})
        with pytest.raises(ConfigurationError):
            _ = Vocabulary.from_params(params, instances=instances) 

# 需要导入模块: from allennlp.common import params [as 别名]
# 或者: from allennlp.common.params import Params [as 别名]
def test_max_vocab_size_partial_dict(self):
        indexers = {
            "tokens": SingleIdTokenIndexer(),
            "token_characters": TokenCharactersIndexer(min_padding_length=3),
        }
        instance = Instance(
            {
                "text": TextField(
                    [Token(w) for w in "Abc def ghi jkl mno pqr stu vwx yz".split(" ")], indexers
                )
            }
        )
        dataset = Batch([instance])
        params = Params({"max_vocab_size": {"tokens": 1}})

        vocab = Vocabulary.from_params(params=params, instances=dataset)
        assert len(vocab.get_index_to_token_vocabulary("tokens").values()) == 3  # 1 + 2
        assert len(vocab.get_index_to_token_vocabulary("token_characters").values()) == 28  # 26 + 2 

# 需要导入模块: from allennlp.common import params [as 别名]
# 或者: from allennlp.common.params import Params [as 别名]
def test_custom_padding_oov_tokens(self):
        vocab = Vocabulary(oov_token="[UNK]")
        assert vocab._oov_token == "[UNK]"
        assert vocab._padding_token == "@@PADDING@@"

        vocab = Vocabulary(padding_token="[PAD]")
        assert vocab._oov_token == "@@UNKNOWN@@"
        assert vocab._padding_token == "[PAD]"

        vocab_dir = self.TEST_DIR / "vocab_save"
        vocab = Vocabulary(oov_token="<UNK>")
        vocab.add_tokens_to_namespace(["a0", "a1", "a2"], namespace="a")
        vocab.save_to_files(vocab_dir)

        params = Params({"type": "from_files", "directory": vocab_dir, "oov_token": "<UNK>"})
        vocab = Vocabulary.from_params(params)

        with pytest.raises(AssertionError) as excinfo:
            vocab = Vocabulary.from_params(Params({"type": "from_files", "directory": vocab_dir}))

        assert "OOV token not found!" in str(excinfo.value) 

# 需要导入模块: from allennlp.common import params [as 别名]
# 或者: from allennlp.common.params import Params [as 别名]
def test_from_params(self):
        params = Params({"type": "pretrained", "weights_file_path": self.temp_file})
        initializer = Initializer.from_params(params)
        assert initializer.weights
        assert initializer.parameter_name_overrides == {}

        name_overrides = {"a": "b", "c": "d"}
        params = Params(
            {
                "type": "pretrained",
                "weights_file_path": self.temp_file,
                "parameter_name_overrides": name_overrides,
            }
        )
        initializer = Initializer.from_params(params)
        assert initializer.weights
        assert initializer.parameter_name_overrides == name_overrides 

# 需要导入模块: from allennlp.common import params [as 别名]
# 或者: from allennlp.common.params import Params [as 别名]
def test_exponential_works_properly(self):
        scheduler = LearningRateScheduler.from_params(
            optimizer=Optimizer.from_params(
                model_parameters=self.model.named_parameters(),
                params=Params({"type": "sgd", "lr": 1.0}),
            ),
            params=Params({"type": "exponential", "gamma": 0.5}),
        )
        optimizer = scheduler.lr_scheduler.optimizer
        optimizer.step()  # to avoid a pytorch warning
        # Initial learning rate should be unchanged for first epoch.
        assert optimizer.param_groups[0]["lr"] == 1.0
        scheduler.step()
        assert optimizer.param_groups[0]["lr"] == 0.5
        scheduler.step()
        assert optimizer.param_groups[0]["lr"] == 0.5 ** 2
        scheduler.step()
        assert optimizer.param_groups[0]["lr"] == 0.5 ** 3 

# 需要导入模块: from allennlp.common import params [as 别名]
# 或者: from allennlp.common.params import Params [as 别名]
def setup_method(self):
        super().setup_method()
        self.instances = SequenceTaggingDatasetReader().read(
            self.FIXTURES_ROOT / "data" / "sequence_tagging.tsv"
        )
        self.vocab = Vocabulary.from_instances(self.instances)
        self.model_params = Params(
            {
                "text_field_embedder": {
                    "token_embedders": {
                        "tokens": {"type": "embedding", "embedding_dim": 5, "sparse": True}
                    }
                },
                "encoder": {"type": "lstm", "input_size": 5, "hidden_size": 7, "num_layers": 2},
            }
        )
        self.model = SimpleTagger.from_params(vocab=self.vocab, params=self.model_params) 

# 需要导入模块: from allennlp.common import params [as 别名]
# 或者: from allennlp.common.params import Params [as 别名]
def test_registered_subclass(self):
        """
        Tests that registering Checkpointer subclasses works correctly.
        """

        @Checkpointer.register("checkpointer_subclass")
        class CheckpointerSubclass(Checkpointer):
            def __init__(self, x: int, y: int) -> None:
                super().__init__()
                self.x = x
                self.y = y

        sub_inst = Checkpointer.from_params(
            Params({"type": "checkpointer_subclass", "x": 1, "y": 3})
        )
        assert sub_inst.__class__ == CheckpointerSubclass
        assert sub_inst.x == 1 and sub_inst.y == 3 

# 需要导入模块: from allennlp.common import params [as 别名]
# 或者: from allennlp.common.params import Params [as 别名]
def test_all_datasets_read_for_vocab(self, caplog):
        params = Params(
            {
                "dataset_reader": {"type": "train-util-test-reader"},
                "train_data_path": "path-to-training-file",
                "validation_data_path": "path-to-validation-file",
                "test_data_path": "path-to-test-file",
            }
        )
        _ = make_vocab_from_params(params, str(self.TEST_DIR))
        log_messages = "\n".join([rec.message for rec in caplog.records])
        assert "...train-util-test-reader reading from path-to-training-file" in log_messages
        assert "...train-util-test-reader reading from path-to-validation-file" in log_messages
        assert "...train-util-test-reader reading from path-to-test-file" in log_messages
        assert "Reading training data" in log_messages
        assert "Reading validation data" in log_messages
        assert "Reading test data" in log_messages 

# 需要导入模块: from allennlp.common import params [as 别名]
# 或者: from allennlp.common.params import Params [as 别名]
def test_from_params_extend_config(self):

        vocab_dir = self.TEST_DIR / u'vocab_save'
        original_vocab = Vocabulary(non_padded_namespaces=[u"tokens"])
        original_vocab.add_token_to_namespace(u"a", namespace=u"tokens")
        original_vocab.save_to_files(vocab_dir)

        text_field = TextField([Token(t) for t in [u"a", u"b"]],
                               {u"tokens": SingleIdTokenIndexer(u"tokens")})
        instances = Batch([Instance({u"text": text_field})])

        # If you ask to extend vocab from `directory_path`, instances must be passed
        # in Vocabulary constructor, or else there is nothing to extend to.
        params = Params({u"directory_path": vocab_dir, u"extend": True})
        with pytest.raises(ConfigurationError):
            _ = Vocabulary.from_params(params)

        # If you ask to extend vocab, `directory_path` key must be present in params,
        # or else there is nothing to extend from.
        params = Params({u"extend": True})
        with pytest.raises(ConfigurationError):
            _ = Vocabulary.from_params(params, instances) 

# 需要导入模块: from allennlp.common import params [as 别名]
# 或者: from allennlp.common.params import Params [as 别名]
def test_registrability(self):

        class MyVocabulary(object):
            @classmethod
            def from_params(cls, params, instances=None):
                # pylint: disable=unused-argument
                return MyVocabulary()


                MyVocabulary = Vocabulary.register(u'my-vocabulary')(MyVocabulary)

        params = Params({u'type': u'my-vocabulary'})

        instance = Instance(fields={})

        vocab = Vocabulary.from_params(params=params, instances=[instance])

        assert isinstance(vocab, MyVocabulary) 

# 需要导入模块: from allennlp.common import params [as 别名]
# 或者: from allennlp.common.params import Params [as 别名]
def setUp(self):
        super(TestOptimizer, self).setUp()
        self.instances = SequenceTaggingDatasetReader().read(self.FIXTURES_ROOT / u'data' / u'sequence_tagging.tsv')
        vocab = Vocabulary.from_instances(self.instances)
        self.model_params = Params({
                u"text_field_embedder": {
                        u"tokens": {
                                u"type": u"embedding",
                                u"embedding_dim": 5
                                }
                        },
                u"encoder": {
                        u"type": u"lstm",
                        u"input_size": 5,
                        u"hidden_size": 7,
                        u"num_layers": 2
                        }
                })
        self.model = SimpleTagger.from_params(vocab=vocab, params=self.model_params) 

# 需要导入模块: from allennlp.common import params [as 别名]
# 或者: from allennlp.common.params import Params [as 别名]
def setUp(self):
        super(TestTrainer, self).setUp()
        self.instances = SequenceTaggingDatasetReader().read(self.FIXTURES_ROOT / u'data' / u'sequence_tagging.tsv')
        vocab = Vocabulary.from_instances(self.instances)
        self.vocab = vocab
        self.model_params = Params({
                u"text_field_embedder": {
                        u"tokens": {
                                u"type": u"embedding",
                                u"embedding_dim": 5
                                }
                        },
                u"encoder": {
                        u"type": u"lstm",
                        u"input_size": 5,
                        u"hidden_size": 7,
                        u"num_layers": 2
                        }
                })
        self.model = SimpleTagger.from_params(vocab=self.vocab, params=self.model_params)
        self.optimizer = torch.optim.SGD(self.model.parameters(), 0.01)
        self.iterator = BasicIterator(batch_size=2)
        self.iterator.index_with(vocab) 

# 需要导入模块: from allennlp.common import params [as 别名]
# 或者: from allennlp.common.params import Params [as 别名]
def remove_pretrained_embedding_params(params: Params):
    if isinstance(params, Params):  # The model could possibly be a string, for example.
        keys = params.keys()
        if "pretrained_file" in keys:
            del params["pretrained_file"]
        for value in params.values():
            if isinstance(value, Params):
                remove_pretrained_embedding_params(value) 

# 需要导入模块: from allennlp.common import params [as 别名]
# 或者: from allennlp.common.params import Params [as 别名]
def prepare_environment(params: Params):
    """
    Sets random seeds for reproducible experiments. This may not work as expected
    if you use this from within a python project in which you have already imported Pytorch.
    If you use the scripts/run_model.py entry point to training models with this library,
    your experiments should be reasonably reproducible. If you are using this from your own
    project, you will want to call this function before importing Pytorch. Complete determinism
    is very difficult to achieve with libraries doing optimized linear algebra due to massively
    parallel execution, which is exacerbated by using GPUs.

    # Parameters

    params: `Params`
        A `Params` object or dict holding the json parameters.
    """
    seed = params.pop_int("random_seed", 13370)
    numpy_seed = params.pop_int("numpy_seed", 1337)
    torch_seed = params.pop_int("pytorch_seed", 133)

    if seed is not None:
        random.seed(seed)
    if numpy_seed is not None:
        numpy.random.seed(numpy_seed)
    if torch_seed is not None:
        torch.manual_seed(torch_seed)
        # Seed all GPUs with the same seed if available.
        if torch.cuda.is_available():
            torch.cuda.manual_seed_all(torch_seed)

    log_pytorch_version_info() 

# 需要导入模块: from allennlp.common import params [as 别名]
# 或者: from allennlp.common.params import Params [as 别名]
def test_stacked_bidirectional_lstm_can_build_from_params(self):
        params = Params(
            {
                "type": "stacked_bidirectional_lstm",
                "input_size": 5,
                "hidden_size": 9,
                "num_layers": 3,
            }
        )
        encoder = Seq2SeqEncoder.from_params(params)

        assert encoder.get_input_dim() == 5
        assert encoder.get_output_dim() == 18
        assert encoder.is_bidirectional