seanbenhur

import random
import itertools
import os
import shutil
import tempfile 
import argparse

import numpy as np
import torch
from tqdm import trange

seanbenhur

import pandas as pd
from easynmt import EasyNMT

#read csv
split_0 = pd.read_csv("/content/drive/MyDrive/datasets/Image-Captioning-ACL/splits_0")
#turn that into list
split_0_captions = split_0['caption'].tolist()

#load the mbart50 english to many model
model = EasyNMT('mbart50_en2m')

seanbenhur

import time
import json
import multiprocessing
from multiprocessing import Pool


txt_path = "tamil_dataset.txt"
json_path = "tamil_final_dataset.json"

seanbenhur

import re
import wandb
from datasets import load_dataset, concatenate_datasets
from functools import partial
import logging 

logger = logging.getLogger(__name__)


def load_hf_format_dataset(file_path,split):

seanbenhur

from waitress import serve
import io
from flask import Flask, request,jsonify
from PIL import Image
import base64
from spacymodels.activeorpassive.model import find_passive_or_active
import spacy
import pandas as pd
import torch
import numpy as np

seanbenhur

for i, data in enumerate(test_dataloader, 0):
    x0, x1 = data
    concat = torch.cat((x0, x1), 0)
    output1, output2 = model(x0.to(device), x1.to(device))
    eucledian_distance = F.pairwise_distance(output1, output2)
    if label == torch.FloatTensor([[0]]):
        label = "Original Pair Of Signature"
    else:
        label = "Forged Pair Of Signature"

seanbenhur

def convert_annot_to_yolov5(x_min, y_min, x_max, y_max, img):
    """
    Convert annotations into required yolov5 formamt
    x_center, y_center, width, height
    """
    w = x_max - x_min
    h = y_max - y_min
    imgheight,imgwidth = img.shape[0], img.shape[1]
    #x,y,w,h = a['hbox']   //for each tag in gtboxes object
    """

seanbenhur

[verbose]: Creating arXiv submission AutoTeX object
[verbose]: *** Using TeX Live 2020 ***
[verbose]: Calling arXiv submission AutoTeX process
[verbose]: TeX/AutoTeX.pm: admin_timeout = minion
[verbose]: <Copyright-logo.txt> is of type 'unknown'.
[verbose]: <Copyright-lppl.txt> is of type 'unknown'.
[verbose]: <Copyright.txt> is of type 'unknown'.
[verbose]: <Makefile> is of type 'unknown'.
[verbose]: <README.md> is of type 'unknown'.

seanbenhur

import argparse
from transformers import AutoTokenizer
import torch
import numpy as np
from collections import Counter
import pandas as pd
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F

seanbenhur

import numpy as np
from transformers import AutoConfig, AutoModelWithHeads
from transformers import TrainingArguments, Trainer, EvalPrediction


config = AutoConfig.from_pretrained(
    "distilbert-base-uncased",
    num_labels=2,
)
model = AutoModelWithHeads.from_pretrained(