seanie12

import argparse
import os
import pickle

import numpy as np
import torch
import torch.nn as nn
from sklearn.metrics import accuracy_score
from torch.utils.data import DataLoader, Dataset
from tqdm import tqdm

seanie12

import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence
from torch_scatter import scatter_max
from pytorch_transformers import BertModel, BertTokenizer


def return_mask_lengths(ids):

seanie12

import linecache
import subprocess

import torch
from torch.utils.data import Dataset, DataLoader


class EEGDataset(Dataset):
    def __init__(self, filename):
        self.filename = filename

seanie12

import os
import random
from tqdm import tqdm
import numpy as np


def batch_loader(iterable, batch_size, shuffle=False):
    length = len(iterable)
    if shuffle:
        random.shuffle(iterable)

seanie12

class RLTrainer(CatTrainer):
    def __init__(self, args):
        super(RLTrainer, self).__init__(args)
        self.qa_model = BiDAF(embedding_size=100,
                              vocab_size=self.vocab_size,
                              hidden_size=args.qa_hidden_size,
                              drop_prob=0.2)

        state_dict = torch.load(args.qa_file, map_location="cpu")
        self.qa_model.load_state_dict(state_dict)

seanie12

import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
from pytorch_pretrained_bert import BertModel

from torch.nn.utils.rnn import pack_padded_sequence, pad_packed_sequence
from torch_scatter import scatter_max

seanie12

import torch
import torch.nn as nn
import torch.nn.functional as F
import math
from pytorch_pretrained_bert import BertModel

dropout = 0.1


def mask_logits(inputs, mask):

seanie12

#! /bin/bash

set -e

OUTPUT=$1

mkdir -p $OUTPUT

wget https://s3.us-east-2.amazonaws.com/mrqa/release/v2/dev/SQuAD.jsonl.gz -O $OUTPUT/SQuAD.jsonl.gz
wget https://s3.us-east-2.amazonaws.com/mrqa/release/v2/dev/NewsQA.jsonl.gz -O $OUTPUT/NewsQA.jsonl.gz

seanie12

import torch
import torch.nn as nn
import torch.nn.functional as F
from pytorch_pretrained_bert import BertModel
from torch.nn.utils.rnn import pad_packed_sequence, pack_padded_sequence
from torch_scatter import scatter_max
import numpy as np
from torch.distributions.categorical import Categorical

INF = 1e12

seanie12

# old files
train_src_file = "./squad/para-train.txt"
train_trg_file = "./squad/tgt-train.txt"
dev_src_file = "./squad/para-dev.txt"
dev_trg_file = "./squad/tgt-dev.txt"
test_src_file = "./squad/para-test.txt"
test_trg_file = "./squad/tgt-test.txt"
embedding = "./data/embedding.pkl"
word2idx_file = "./data/word2idx.pkl"