File size: 10,265 Bytes
143d7a9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
326
327
328
329
330
331
332
333
334
335
# Copyright (c) Facebook, Inc. and its affiliates.
import re

from tqdm import tqdm


class EvalAIAnswerProcessor:
    """
    Processes an answer similar to Eval AI
        copied from
        https://github.com/facebookresearch/mmf/blob/c46b3b3391275b4181567db80943473a89ab98ab/pythia/tasks/processors.py#L897
    """

    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",
    }

    NUMBER_MAP = {
        "none": "0",
        "zero": "0",
        "one": "1",
        "two": "2",
        "three": "3",
        "four": "4",
        "five": "5",
        "six": "6",
        "seven": "7",
        "eight": "8",
        "nine": "9",
        "ten": "10",
    }
    ARTICLES = ["a", "an", "the"]
    PERIOD_STRIP = re.compile(r"(?!<=\d)(\.)(?!\d)")
    COMMA_STRIP = re.compile(r"(?<=\d)(\,)+(?=\d)")
    PUNCTUATIONS = [
        ";",
        r"/",
        "[",
        "]",
        '"',
        "{",
        "}",
        "(",
        ")",
        "=",
        "+",
        "\\",
        "_",
        "-",
        ">",
        "<",
        "@",
        "`",
        ",",
        "?",
        "!",
    ]

    def __init__(self, *args, **kwargs):
        pass

    def word_tokenize(self, word):
        word = word.lower()
        word = word.replace(",", "").replace("?", "").replace("'s", " 's")
        return word.strip()

    def process_punctuation(self, in_text):
        out_text = in_text
        for p in self.PUNCTUATIONS:
            if (p + " " in in_text or " " + p in in_text) or (
                re.search(self.COMMA_STRIP, in_text) is not None
            ):
                out_text = out_text.replace(p, "")
            else:
                out_text = out_text.replace(p, " ")
        out_text = self.PERIOD_STRIP.sub("", out_text, re.UNICODE)
        return out_text

    def process_digit_article(self, in_text):
        out_text = []
        temp_text = in_text.lower().split()
        for word in temp_text:
            word = self.NUMBER_MAP.setdefault(word, word)
            if word not in self.ARTICLES:
                out_text.append(word)
            else:
                pass
        for word_id, word in enumerate(out_text):
            if word in self.CONTRACTIONS:
                out_text[word_id] = self.CONTRACTIONS[word]
        out_text = " ".join(out_text)
        return out_text

    def __call__(self, item):
        item = self.word_tokenize(item)
        item = item.replace("\n", " ").replace("\t", " ").strip()
        item = self.process_punctuation(item)
        item = self.process_digit_article(item)
        return item


class TextVQAAccuracyEvaluator:
    def __init__(self):
        self.answer_processor = EvalAIAnswerProcessor()

    def _compute_answer_scores(self, raw_answers):
        """
        compute the accuracy (soft score) of human answers
        """
        answers = [self.answer_processor(a) for a in raw_answers]
        assert len(answers) == 10
        gt_answers = list(enumerate(answers))
        unique_answers = set(answers)
        unique_answer_scores = {}

        for unique_answer in unique_answers:
            accs = []
            for gt_answer in gt_answers:
                other_answers = [item for item in gt_answers if item != gt_answer]
                matching_answers = [
                    item for item in other_answers if item[1] == unique_answer
                ]
                acc = min(1, float(len(matching_answers)) / 3)
                accs.append(acc)
            unique_answer_scores[unique_answer] = sum(accs) / len(accs)

        return unique_answer_scores

    def eval_pred_list(self, pred_list):
        pred_scores = []
        for entry in tqdm(pred_list):
            pred_answer = self.answer_processor(entry["pred_answer"])
            unique_answer_scores = self._compute_answer_scores(entry["gt_answers"])
            score = unique_answer_scores.get(pred_answer, 0.0)
            pred_scores.append(score)

        accuracy = sum(pred_scores) / len(pred_scores)
        return accuracy


class STVQAAccuracyEvaluator:
    def __init__(self):
        self.answer_processor = EvalAIAnswerProcessor()

    def eval_pred_list(self, pred_list):
        pred_scores = []
        for entry in pred_list:
            pred_answer = self.answer_processor(entry["pred_answer"])
            gts = [self.answer_processor(a) for a in entry["gt_answers"]]
            score = 1.0 if pred_answer in gts else 0.0
            pred_scores.append(score)

        accuracy = sum(pred_scores) / len(pred_scores)
        return accuracy


class STVQAANLSEvaluator:
    def __init__(self):
        import editdistance  # install with `pip install editdistance`

        self.get_edit_distance = editdistance.eval

    def get_anls(self, s1, s2):
        s1 = s1.lower().strip()
        s2 = s2.lower().strip()
        iou = 1 - self.get_edit_distance(s1, s2) / max(len(s1), len(s2))
        anls = iou if iou >= 0.5 else 0.0
        return anls

    def eval_pred_list(self, pred_list):
        pred_scores = []
        for entry in pred_list:
            anls = max(
                self.get_anls(entry["pred_answer"], gt) for gt in entry["gt_answers"]
            )
            pred_scores.append(anls)

        accuracy = sum(pred_scores) / len(pred_scores)
        return accuracy


class TextCapsBleu4Evaluator:
    def __init__(self):
        # The following script requires Java 1.8.0 and pycocotools installed.
        # The pycocoevalcap can be installed with pip as
        # pip install git+https://github.com/ronghanghu/coco-caption.git@python23
        # Original pycocoevalcap code is at https://github.com/tylin/coco-caption
        # but has no python3 support yet.
        try:
            from pycocoevalcap.bleu.bleu import Bleu
            from pycocoevalcap.tokenizer.ptbtokenizer import PTBTokenizer
        except ModuleNotFoundError:
            print(
                "Please install pycocoevalcap module using "
                "pip install git+https://github.com/ronghanghu/coco-caption.git@python23"  # noqa
            )
            raise

        self.tokenizer = PTBTokenizer()
        self.scorer = Bleu(4)

    def eval_pred_list(self, pred_list):
        # Create reference and hypotheses captions.
        gts = {}
        res = {}
        for idx, entry in enumerate(pred_list):
            gts[idx] = [{"caption": a} for a in entry["gt_answers"]]
            res[idx] = [{"caption": entry["pred_answer"]}]

        gts = self.tokenizer.tokenize(gts)
        res = self.tokenizer.tokenize(res)
        score, _ = self.scorer.compute_score(gts, res)

        bleu4 = score[3]  # score is (Bleu-1, Bleu-2, Bleu-3, Bleu-4)
        return bleu4