'learning_rate_0')
propeller.summary.scalar('lr', scheduled_lr)
predictions = [
logits,
]
train_hooks = [lr_step_hook]
return propeller.ModelSpec(loss=loss,
mode=mode,
metrics=metrics,
predictions=predictions,
train_hooks=train_hooks)
if __name__ == '__main__':
parser = propeller.ArgumentParser('DAN model with Paddle')
parser.add_argument('--do_predict', action='store_true')
parser.add_argument('--max_seqlen', type=int, default=128)
parser.add_argument('--data_dir', type=str, required=True)
parser.add_argument('--from_pretrained', type=str, required=True)
parser.add_argument('--warm_start_from', type=str)
parser.add_argument('--epoch', type=int, default=3)
parser.add_argument('--use_amp', action='store_true')
args = parser.parse_args()
P.enable_static()
if not os.path.exists(args.from_pretrained):
raise ValueError('--from_pretrained not found: %s' %
args.from_pretrained)
weight_decay=self.config.weight_decay,
scheduler="linear_warmup_decay",
)
propeller.summary.scalar('lr', scheduled_lr)
def metrics(self, predictions, labels):
predictions = L.argmax(predictions, axis=1)
labels = L.argmax(labels, axis=1)
#predictions = L.unsqueeze(predictions, axes=[1])
acc = propeller.metrics.Acc(labels, predictions)
#auc = propeller.metrics.Auc(labels, predictions)
return {'acc': acc}
if __name__ == '__main__':
parser = propeller.ArgumentParser('distill model with ERNIE')
parser.add_argument('--max_seqlen', type=int, default=128)
parser.add_argument('--vocab_file', type=str, required=True)
parser.add_argument('--teacher_vocab_file', type=str, required=True)
parser.add_argument('--teacher_max_seqlen', type=int, default=128)
parser.add_argument('--data_dir', type=str)
parser.add_argument('--server_batch_size', type=int, default=64)
parser.add_argument('--num_coroutine', type=int, default=1)
parser.add_argument('--teacher_host', type=str, required=True)
args = parser.parse_args()
run_config = propeller.parse_runconfig(args)
hparams = propeller.parse_hparam(args)
teacher_vocab = {
j.strip().split(b'\t')[0].decode('utf8'): i
for i, j in enumerate(open(args.teacher_vocab_file, 'rb'))
startup_prog=F.default_startup_program(),
weight_decay=self.config.weight_decay,
scheduler="linear_warmup_decay",)
propeller.summary.scalar('lr', scheduled_lr)
def metrics(self, predictions, labels):
predictions = L.argmax(predictions, axis=1)
labels = L.argmax(labels, axis=1)
#predictions = L.unsqueeze(predictions, axes=[1])
acc = propeller.metrics.Acc(labels, predictions)
#auc = propeller.metrics.Auc(labels, predictions)
return {'acc': acc}
if __name__ == '__main__':
parser = propeller.ArgumentParser('Distill model with Paddle')
parser.add_argument('--max_seqlen', type=int, default=128)
parser.add_argument('--vocab_file', type=str, required=True)
parser.add_argument('--unsupervise_data_dir', type=str, required=True)
parser.add_argument('--data_dir', type=str)
args = parser.parse_args()
run_config = propeller.parse_runconfig(args)
hparams = propeller.parse_hparam(args)
vocab = {j.strip().split(b'\t')[0].decode('utf8'): i for i, j in enumerate(open(args.vocab_file, 'rb'))}
unk_id = vocab['[UNK]']
char_tokenizer = utils.data.CharTokenizer(vocab.keys())
space_tokenizer = utils.data.SpaceTokenizer(vocab.keys())
supervise_feature_column = propeller.data.FeatureColumns([
import paddle.fluid.dygraph as FD
import paddle.fluid.layers as L
from propeller import log
import propeller.paddle as propeller
log.setLevel(logging.DEBUG)
logging.getLogger().setLevel(logging.DEBUG)
#from model.bert import BertConfig, BertModelLayer
from ernie.modeling_ernie import ErnieModel, ErnieModelForSequenceClassification
from ernie.tokenizing_ernie import ErnieTokenizer, ErnieTinyTokenizer
from ernie.optimization import AdamW, LinearDecay
if __name__ == '__main__':
parser = propeller.ArgumentParser('classify model with ERNIE')
parser.add_argument('--from_pretrained',
type=str,
required=True,
help='pretrained model directory or tag')
parser.add_argument(
'--max_seqlen',
type=int,
default=128,
help='max sentence length, should not greater than 512')
parser.add_argument('--bsz', type=int, default=32, help='batchsize')
parser.add_argument('--data_dir',
type=str,
required=True,
help='data directory includes train / develop data')
parser.add_argument(
return ds
def after(*features):
return utils.data.expand_dims(*features)
dataset = propeller.data.Dataset.from_generator_func(stdin_gen)
dataset = read_bio_data(dataset)
dataset = reseg_token_label(dataset)
dataset = convert_to_ids(dataset)
dataset = dataset.padded_batch(batch_size).map(after)
dataset.name = name
return dataset
if __name__ == '__main__':
parser = propeller.ArgumentParser('NER model with ERNIE')
parser.add_argument('--max_seqlen', type=int, default=128)
parser.add_argument('--data_dir', type=str, required=True)
parser.add_argument('--vocab_file', type=str, required=True)
parser.add_argument('--do_predict', action='store_true')
parser.add_argument('--use_sentence_piece_vocab', action='store_true')
parser.add_argument('--warm_start_from', type=str)
args = parser.parse_args()
run_config = propeller.parse_runconfig(args)
hparams = propeller.parse_hparam(args)
vocab = {
j.strip().split('\t')[0]: i
for i, j in enumerate(open(args.vocab_file, 'r', encoding='utf8'))
}
tokenizer = utils.data.CharTokenizer(
scheduled_lr, _ = optimization(
loss=loss,
warmup_steps=int(self.run_config.max_steps *
self.hparam['warmup_proportion']),
num_train_steps=self.run_config.max_steps,
learning_rate=self.hparam['learning_rate'],
train_program=F.default_main_program(),
startup_prog=F.default_startup_program(),
weight_decay=self.hparam['weight_decay'],
scheduler="linear_warmup_decay",
)
propeller.summary.scalar('lr', scheduled_lr)
if __name__ == '__main__':
parser = propeller.ArgumentParser('ranker model with ERNIE')
parser.add_argument('--do_predict', action='store_true')
parser.add_argument('--predict_model', type=str, default=None)
parser.add_argument('--max_seqlen', type=int, default=128)
parser.add_argument('--vocab_file', type=str, required=True)
parser.add_argument('--data_dir', type=str, required=True)
parser.add_argument('--warm_start_from', type=str)
parser.add_argument('--sentence_piece_model', type=str, default=None)
parser.add_argument('--word_dict', type=str, default=None)
args = parser.parse_args()
run_config = propeller.parse_runconfig(args)
hparams = propeller.parse_hparam(args)
vocab = {
j.strip().split(b'\t')[0].decode('utf8'): i
for i, j in enumerate(open(args.vocab_file, 'rb'))
