File size: 11,340 Bytes
a43ef32 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 |
"""
Copyright (c) 2022, salesforce.com, inc.
All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
For full license text, see the LICENSE file in the repo root or https://opensource.org/licenses/BSD-3-Clause
"""
# coding=utf-8
__author__ = "aagrawal"
# This code is based on the code written by Tsung-Yi Lin for MSCOCO Python API available at the following link:
# (https://github.com/tylin/coco-caption/blob/master/pycocoevalcap/eval.py).
import sys
import re
class VQAEval:
def __init__(self, vqa=None, vqaRes=None, n=2):
self.n = n
self.accuracy = {}
self.evalQA = {}
self.evalQuesType = {}
self.evalAnsType = {}
self.vqa = vqa
self.vqaRes = vqaRes
if vqa is not None:
self.params = {"question_id": vqa.getQuesIds()}
self.contractions = {
"aint": "ain't",
"arent": "aren't",
"cant": "can't",
"couldve": "could've",
"couldnt": "couldn't",
"couldn'tve": "couldn't've",
"couldnt've": "couldn't've",
"didnt": "didn't",
"doesnt": "doesn't",
"dont": "don't",
"hadnt": "hadn't",
"hadnt've": "hadn't've",
"hadn'tve": "hadn't've",
"hasnt": "hasn't",
"havent": "haven't",
"hed": "he'd",
"hed've": "he'd've",
"he'dve": "he'd've",
"hes": "he's",
"howd": "how'd",
"howll": "how'll",
"hows": "how's",
"Id've": "I'd've",
"I'dve": "I'd've",
"Im": "I'm",
"Ive": "I've",
"isnt": "isn't",
"itd": "it'd",
"itd've": "it'd've",
"it'dve": "it'd've",
"itll": "it'll",
"let's": "let's",
"maam": "ma'am",
"mightnt": "mightn't",
"mightnt've": "mightn't've",
"mightn'tve": "mightn't've",
"mightve": "might've",
"mustnt": "mustn't",
"mustve": "must've",
"neednt": "needn't",
"notve": "not've",
"oclock": "o'clock",
"oughtnt": "oughtn't",
"ow's'at": "'ow's'at",
"'ows'at": "'ow's'at",
"'ow'sat": "'ow's'at",
"shant": "shan't",
"shed've": "she'd've",
"she'dve": "she'd've",
"she's": "she's",
"shouldve": "should've",
"shouldnt": "shouldn't",
"shouldnt've": "shouldn't've",
"shouldn'tve": "shouldn't've",
"somebody'd": "somebodyd",
"somebodyd've": "somebody'd've",
"somebody'dve": "somebody'd've",
"somebodyll": "somebody'll",
"somebodys": "somebody's",
"someoned": "someone'd",
"someoned've": "someone'd've",
"someone'dve": "someone'd've",
"someonell": "someone'll",
"someones": "someone's",
"somethingd": "something'd",
"somethingd've": "something'd've",
"something'dve": "something'd've",
"somethingll": "something'll",
"thats": "that's",
"thered": "there'd",
"thered've": "there'd've",
"there'dve": "there'd've",
"therere": "there're",
"theres": "there's",
"theyd": "they'd",
"theyd've": "they'd've",
"they'dve": "they'd've",
"theyll": "they'll",
"theyre": "they're",
"theyve": "they've",
"twas": "'twas",
"wasnt": "wasn't",
"wed've": "we'd've",
"we'dve": "we'd've",
"weve": "we've",
"werent": "weren't",
"whatll": "what'll",
"whatre": "what're",
"whats": "what's",
"whatve": "what've",
"whens": "when's",
"whered": "where'd",
"wheres": "where's",
"whereve": "where've",
"whod": "who'd",
"whod've": "who'd've",
"who'dve": "who'd've",
"wholl": "who'll",
"whos": "who's",
"whove": "who've",
"whyll": "why'll",
"whyre": "why're",
"whys": "why's",
"wont": "won't",
"wouldve": "would've",
"wouldnt": "wouldn't",
"wouldnt've": "wouldn't've",
"wouldn'tve": "wouldn't've",
"yall": "y'all",
"yall'll": "y'all'll",
"y'allll": "y'all'll",
"yall'd've": "y'all'd've",
"y'alld've": "y'all'd've",
"y'all'dve": "y'all'd've",
"youd": "you'd",
"youd've": "you'd've",
"you'dve": "you'd've",
"youll": "you'll",
"youre": "you're",
"youve": "you've",
}
self.manualMap = {
"none": "0",
"zero": "0",
"one": "1",
"two": "2",
"three": "3",
"four": "4",
"five": "5",
"six": "6",
"seven": "7",
"eight": "8",
"nine": "9",
"ten": "10",
}
self.articles = ["a", "an", "the"]
self.periodStrip = re.compile("(?!<=\d)(\.)(?!\d)")
self.commaStrip = re.compile("(\d)(,)(\d)")
self.punct = [
";",
r"/",
"[",
"]",
'"',
"{",
"}",
"(",
")",
"=",
"+",
"\\",
"_",
"-",
">",
"<",
"@",
"`",
",",
"?",
"!",
]
def evaluate(self, quesIds=None):
if quesIds == None:
quesIds = [quesId for quesId in self.params["question_id"]]
gts = {}
res = {}
for quesId in quesIds:
gts[quesId] = self.vqa.qa[quesId]
res[quesId] = self.vqaRes.qa[quesId]
# =================================================
# Compute accuracy
# =================================================
accQA = []
accQuesType = {}
accAnsType = {}
print("computing accuracy")
step = 0
for quesId in quesIds:
resAns = res[quesId]["answer"]
resAns = resAns.replace("\n", " ")
resAns = resAns.replace("\t", " ")
resAns = resAns.strip()
resAns = self.processPunctuation(resAns)
resAns = self.processDigitArticle(resAns)
gtAcc = []
gtAnswers = [ans["answer"] for ans in gts[quesId]["answers"]]
if len(set(gtAnswers)) > 1:
for ansDic in gts[quesId]["answers"]:
ansDic["answer"] = self.processPunctuation(ansDic["answer"])
for gtAnsDatum in gts[quesId]["answers"]:
otherGTAns = [
item for item in gts[quesId]["answers"] if item != gtAnsDatum
]
matchingAns = [item for item in otherGTAns if item["answer"] == resAns]
acc = min(1, float(len(matchingAns)) / 3)
gtAcc.append(acc)
quesType = gts[quesId]["question_type"]
ansType = gts[quesId]["answer_type"]
avgGTAcc = float(sum(gtAcc)) / len(gtAcc)
accQA.append(avgGTAcc)
if quesType not in accQuesType:
accQuesType[quesType] = []
accQuesType[quesType].append(avgGTAcc)
if ansType not in accAnsType:
accAnsType[ansType] = []
accAnsType[ansType].append(avgGTAcc)
self.setEvalQA(quesId, avgGTAcc)
self.setEvalQuesType(quesId, quesType, avgGTAcc)
self.setEvalAnsType(quesId, ansType, avgGTAcc)
if step % 100 == 0:
self.updateProgress(step / float(len(quesIds)))
step = step + 1
self.setAccuracy(accQA, accQuesType, accAnsType)
print("Done computing accuracy")
def processPunctuation(self, inText):
outText = inText
for p in self.punct:
if (p + " " in inText or " " + p in inText) or (
re.search(self.commaStrip, inText) != None
):
outText = outText.replace(p, "")
else:
outText = outText.replace(p, " ")
outText = self.periodStrip.sub("", outText, re.UNICODE)
return outText
def processDigitArticle(self, inText):
outText = []
tempText = inText.lower().split()
for word in tempText:
word = self.manualMap.setdefault(word, word)
if word not in self.articles:
outText.append(word)
else:
pass
for wordId, word in enumerate(outText):
if word in self.contractions:
outText[wordId] = self.contractions[word]
outText = " ".join(outText)
return outText
def setAccuracy(self, accQA, accQuesType, accAnsType):
self.accuracy["overall"] = round(100 * float(sum(accQA)) / len(accQA), self.n)
self.accuracy["perQuestionType"] = {
quesType: round(
100 * float(sum(accQuesType[quesType])) / len(accQuesType[quesType]),
self.n,
)
for quesType in accQuesType
}
self.accuracy["perAnswerType"] = {
ansType: round(
100 * float(sum(accAnsType[ansType])) / len(accAnsType[ansType]), self.n
)
for ansType in accAnsType
}
def setEvalQA(self, quesId, acc):
self.evalQA[quesId] = round(100 * acc, self.n)
def setEvalQuesType(self, quesId, quesType, acc):
if quesType not in self.evalQuesType:
self.evalQuesType[quesType] = {}
self.evalQuesType[quesType][quesId] = round(100 * acc, self.n)
def setEvalAnsType(self, quesId, ansType, acc):
if ansType not in self.evalAnsType:
self.evalAnsType[ansType] = {}
self.evalAnsType[ansType][quesId] = round(100 * acc, self.n)
def updateProgress(self, progress):
barLength = 20
status = ""
if isinstance(progress, int):
progress = float(progress)
if not isinstance(progress, float):
progress = 0
status = "error: progress var must be float\r\n"
if progress < 0:
progress = 0
status = "Halt...\r\n"
if progress >= 1:
progress = 1
status = "Done...\r\n"
block = int(round(barLength * progress))
text = "\rFinshed Percent: [{0}] {1}% {2}".format(
"#" * block + "-" * (barLength - block), int(progress * 100), status
)
sys.stdout.write(text)
sys.stdout.flush()
|