def __init__(self,
data_config,
model_config="embc:16|embt:16|conv:48|l1:16|do:0.1|oc:BI"):
super(Model, self).__init__()
no_chars = data_config["num_tokens"]
config = utils.parse_model_params(model_config)
conv_filters = config["conv"]
dropout_rate = config.get("do", 0)
self.output_scheme = output_tags.get_scheme(config["oc"])
self.ch_embeddings = nn.Embedding(no_chars,
config["embc"],
padding_idx=0)
self.ch_type_embeddings = nn.Embedding(
char_type.get_total_char_types(),
config["embt"],
)
emb_dim = config["embc"] + config["embt"]
self.id_conv = IteratedDilatedConvolutions(emb_dim, conv_filters,
dropout_rate)
self.linear1 = nn.Linear(conv_filters, config['l1'])
self.linear2 = nn.Linear(config['l1'], self.output_scheme.num_tags)
self.model_params = model_config
def __init__(self, data_config, model_config="embc:16|embt:8|embs:8|cells:32|l1:16|bi:1|oc:BI"):
super(Model, self).__init__()
no_chars = data_config['num_char_tokens']
log.info("no. characters: %d" % no_chars)
no_syllables = data_config['num_tokens']
log.info("no. syllables: %d" % no_syllables)
config = utils.parse_model_params(model_config)
self.output_scheme = output_tags.get_scheme(config["oc"])
self.ch_type_embeddings = nn.Embedding(
char_type.get_total_char_types(),
config["embt"],
)
self.ch_embeddings = nn.Embedding(
no_chars,
config["embc"],
padding_idx=0
)
self.sy_embeddings = nn.Embedding(
no_syllables,
config["embs"],
padding_idx=0
)
if config["crf"]:
self.crf = CRF(self.output_scheme.num_tags, batch_first=True)
emb_dim = config["embc"] + config["embs"] + config["embt"]
num_cells, num_lstm_output, bi_direction = utils.compute_lstm_output_dim(
config["cells"],
config["bi"]
)
self.dropout = nn.Dropout(config["do"])
self.lstm = nn.LSTM(emb_dim, num_cells, bidirectional=bi_direction, batch_first=True)
self.linear1 = nn.Linear(num_lstm_output, config["l1"])
self.linear2 = nn.Linear(config["l1"], self.output_scheme.num_tags)
self.model_params = model_config
def __init__(self, data_config, model_config="embc:16|embt:8|embs:8|conv:16|l1:16|do:0.0|oc:BI"):
super(Model, self).__init__()
no_chars = data_config['num_char_tokens']
log.info("no. characters: %d" % no_chars)
no_syllables = data_config['num_tokens']
log.info("no. syllables: %d" % no_syllables)
config = utils.parse_model_params(model_config)
conv_filters = config['conv']
dropout_rate = config.get("do", 0)
self.output_scheme = output_tags.get_scheme(config["oc"])
self.ch_type_embeddings = nn.Embedding(
char_type.get_total_char_types(),
config["embt"],
)
self.ch_embeddings = nn.Embedding(
no_chars,
config["embc"],
padding_idx=0
)
self.sy_embeddings = nn.Embedding(
no_syllables,
config["embs"],
padding_idx=0
)
emb_dim = config["embc"] + config["embs"] + config["embt"]
self.dropout= torch.nn.Dropout(p=dropout_rate)
self.conv1 = ConvolutionLayer(emb_dim, conv_filters, 3)
self.conv2 = ConvolutionLayer(conv_filters, conv_filters, 3, dilation=1)
self.linear1 = nn.Linear(conv_filters, config['l1'])
self.linear2 = nn.Linear(config['l1'], self.output_scheme.num_tags)
self.model_params = model_config
def __init__(
self,
data_config,
model_config="embc:16|embt:8|embs:8|conv:16|l1:16|do:0.0|oc:BI"):
super(Model, self).__init__()
no_chars = data_config['num_char_tokens']
log.info("no. characters: %d" % no_chars)
no_syllables = data_config['num_tokens']
log.info("no. syllables: %d" % no_syllables)
config = utils.parse_model_params(model_config)
conv_filters = config["conv"]
dropout_rate = config.get("do", 0)
self.output_scheme = output_tags.get_scheme(config["oc"])
self.ch_type_embeddings = nn.Embedding(
char_type.get_total_char_types(),
config["embt"],
)
self.ch_embeddings = nn.Embedding(no_chars,
config["embc"],
padding_idx=0)
self.sy_embeddings = prepare_embedding(data_config, config)
if "crf" in config:
self.crf = CRF(self.output_scheme.num_tags, batch_first=True)
emb_dim = config["embc"] + config[
"embt"] + self.sy_embeddings.weight.shape[1]
self.id_conv = IteratedDilatedConvolutions(emb_dim, conv_filters,
dropout_rate)
self.linear1 = nn.Linear(conv_filters, config['l1'])
self.linear2 = nn.Linear(config['l1'], self.output_scheme.num_tags)
self.model_params = model_config
