# limitations under the License.
from __future__ import print_function
import os
import time
import argparse
import numpy as np
import paddle.fluid as fluid
from paddle.fluid.dygraph.base import to_variable
import nets
import reader
from utils import ArgumentGroup
from benchmark import AverageMeter, ProgressMeter, Tools
parser = argparse.ArgumentParser(__doc__)
model_g = ArgumentGroup(parser, "model", "model configuration and paths.")
model_g.add_arg("checkpoints", str, "checkpoints", "Path to save checkpoints")
train_g = ArgumentGroup(parser, "training", "training options.")
train_g.add_arg("epoch", int, 10, "Number of epoches for training.")
train_g.add_arg("save_steps", int, 3000,
"The steps interval to save checkpoints.")
train_g.add_arg("validation_steps", int, 2000,
"The steps interval to evaluate model performance.")
train_g.add_arg("lr", float, 0.002, "The Learning rate value for training.")
train_g.add_arg("padding_size", int, 150,
"The padding size for input sequences.")
log_g = ArgumentGroup(parser, "logging", "logging related")
log_g.add_arg("skip_steps", int, 10, "The steps interval to print loss.")
log_g.add_arg("verbose", bool, False, "Whether to output verbose log")
# sys.path.append("../models/classification/")
from nets import textcnn_net_multi_label
import paddle
import paddle.fluid as fluid
from utils import ArgumentGroup, print_arguments, DataProcesser, DataReader, ConfigReader
from utils import init_checkpoint, check_version, logger
import random
import codecs
import logging
import math
np.random.seed(0)
random.seed(0)
parser = argparse.ArgumentParser(__doc__)
DEV_COUNT = 1
model_g = ArgumentGroup(parser, "model", "model configuration and paths.")
model_g.add_arg("init_checkpoint", str, None,
"Init checkpoint to resume training from.")
model_g.add_arg("checkpoints", str, "./checkpoints",
"Path to save checkpoints.")
model_g.add_arg("config_path", str, "./data/input/model.conf", "Model conf.")
model_g.add_arg("build_dict", bool, False, "Build dict.")
train_g = ArgumentGroup(parser, "training", "training options.")
train_g.add_arg("cpu_num", int, 3, "Number of Threads.")
train_g.add_arg("epoch", int, 100, "Number of epoches for training.")
train_g.add_arg("learning_rate", float, 0.1,
"Learning rate used to train with warmup.")
train_g.add_arg("save_steps", int, 1000,
"The steps interval to save checkpoints.")
train_g.add_arg("validation_steps", int, 100,
from nets import bilstm_net
from nets import gru_net
from nets import ernie_base_net
from nets import ernie_bilstm_net
from preprocess.ernie import task_reader
from models.representation.ernie import ErnieConfig
from models.representation.ernie import ernie_encoder, ernie_encoder_with_paddle_hub
from models.representation.ernie import ernie_pyreader
from models.model_check import check_cuda
from utils import ArgumentGroup
from utils import print_arguments
from utils import init_checkpoint
# yapf: disable
parser = argparse.ArgumentParser(__doc__)
model_g = ArgumentGroup(parser, "model", "model configuration and paths.")
model_g.add_arg("ernie_config_path", str, None, "Path to the json file for ernie model config.")
model_g.add_arg("senta_config_path", str, None, "Path to the json file for senta model config.")
model_g.add_arg("init_checkpoint", str, None, "Init checkpoint to resume training from.")
model_g.add_arg("checkpoints", str, "checkpoints", "Path to save checkpoints")
model_g.add_arg("model_type", str, "ernie_base", "Type of current ernie model")
model_g.add_arg("use_paddle_hub", bool, False, "Whether to load ERNIE using PaddleHub")
train_g = ArgumentGroup(parser, "training", "training options.")
train_g.add_arg("epoch", int, 10, "Number of epoches for training.")
train_g.add_arg("save_steps", int, 10000, "The steps interval to save checkpoints.")
train_g.add_arg("validation_steps", int, 1000, "The steps interval to evaluate model performance.")
train_g.add_arg("lr", float, 0.002, "The Learning rate value for training.")
log_g = ArgumentGroup(parser, "logging", "logging related")
log_g.add_arg("skip_steps", int, 10, "The steps interval to print loss.")
from nets import cnn_net
from nets import bilstm_net
from nets import gru_net
from models.model_check import check_cuda
import paddle
import paddle.fluid as fluid
import reader
from config import SentaConfig
from utils import ArgumentGroup, print_arguments
from utils import init_checkpoint
# yapf: disable
parser = argparse.ArgumentParser(__doc__)
model_g = ArgumentGroup(parser, "model", "model configuration and paths.")
model_g.add_arg("senta_config_path", str, None, "Path to the json file for senta model config.")
model_g.add_arg("init_checkpoint", str, None, "Init checkpoint to resume training from.")
model_g.add_arg("checkpoints", str, "checkpoints", "Path to save checkpoints")
train_g = ArgumentGroup(parser, "training", "training options.")
train_g.add_arg("epoch", int, 10, "Number of epoches for training.")
train_g.add_arg("save_steps", int, 10000, "The steps interval to save checkpoints.")
train_g.add_arg("validation_steps", int, 1000, "The steps interval to evaluate model performance.")
train_g.add_arg("lr", float, 0.002, "The Learning rate value for training.")
log_g = ArgumentGroup(parser, "logging", "logging related")
log_g.add_arg("skip_steps", int, 10, "The steps interval to print loss.")
log_g.add_arg("verbose", bool, False, "Whether to output verbose log")
data_g = ArgumentGroup(parser, "data", "Data paths, vocab paths and data processing options")