Python cider_scorer.CiderScorer() Examples

The following are 17 code examples of cider_scorer.CiderScorer(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module cider_scorer , or try the search function .
Example #1
Source File: cider.py    From neural-question-generation with MIT License 5 votes vote down vote up 
def compute_score(self, gts, res):
        """
        Main function to compute CIDEr score
        :param  hypo_for_image (dict) : dictionary with key <image> and value <tokenized hypothesis / candidate sentence>
                ref_for_image (dict)  : dictionary with key <image> and value <tokenized reference sentence>
        :return: cider (float) : computed CIDEr score for the corpus 
        """

        assert(gts.keys() == res.keys())
        imgIds = gts.keys()

        cider_scorer = CiderScorer(n=self._n, sigma=self._sigma)

        for id in imgIds:
            hypo = res[id]
            ref = gts[id]

            # Sanity check.
            assert(type(hypo) is list)
            assert(len(hypo) == 1)
            assert(type(ref) is list)
            assert(len(ref) > 0)

            cider_scorer += (hypo[0], ref)

        (score, scores) = cider_scorer.compute_score()

        return score, scores
Example #2
Source File: cider.py    From image_captioning with MIT License 5 votes vote down vote up 
def compute_score(self, gts, res):
        """
        Main function to compute CIDEr score
        :param  hypo_for_image (dict) : dictionary with key <image> and value <tokenized hypothesis / candidate sentence>
                ref_for_image (dict)  : dictionary with key <image> and value <tokenized reference sentence>
        :return: cider (float) : computed CIDEr score for the corpus 
        """

        assert(gts.keys() == res.keys())
        imgIds = gts.keys()

        cider_scorer = CiderScorer(n=self._n, sigma=self._sigma)

        for id in imgIds:
            hypo = res[id]
            ref = gts[id]

            # Sanity check.
            assert(type(hypo) is list)
            assert(len(hypo) == 1)
            assert(type(ref) is list)
            assert(len(ref) > 0)

            cider_scorer += (hypo[0], ref)

        (score, scores) = cider_scorer.compute_score()

        return score, scores
Example #3
Source File: cider.py    From CommonSenseMultiHopQA with MIT License 5 votes vote down vote up 
def compute_score(self, gts, res):
        """
        Main function to compute CIDEr score
        :param  hypo_for_image (dict) : dictionary with key <image> and value <tokenized hypothesis / candidate sentence>
                ref_for_image (dict)  : dictionary with key <image> and value <tokenized reference sentence>
        :return: cider (float) : computed CIDEr score for the corpus 
        """

        assert(gts.keys() == res.keys())
        imgIds = gts.keys()

        cider_scorer = CiderScorer(n=self._n, sigma=self._sigma)

        for id in imgIds:
            hypo = res[id]
            ref = gts[id]

            # Sanity check.
            assert(type(hypo) is list)
            assert(len(hypo) == 1)
            assert(type(ref) is list)
            assert(len(ref) > 0)

            cider_scorer += (hypo[0], ref)

        (score, scores) = cider_scorer.compute_score()

        return score, scores
Example #4
Source File: cider.py    From QG-Net with MIT License 5 votes vote down vote up 
def compute_score(self, gts, res):
        """
        Main function to compute CIDEr score
        :param  hypo_for_image (dict) : dictionary with key <image> and value <tokenized hypothesis / candidate sentence>
                ref_for_image (dict)  : dictionary with key <image> and value <tokenized reference sentence>
        :return: cider (float) : computed CIDEr score for the corpus 
        """

        assert(gts.keys() == res.keys())
        imgIds = gts.keys()

        cider_scorer = CiderScorer(n=self._n, sigma=self._sigma)

        for id in imgIds:
            hypo = res[id]
            ref = gts[id]

            # Sanity check.
            assert(type(hypo) is list)
            assert(len(hypo) == 1)
            assert(type(ref) is list)
            assert(len(ref) > 0)

            cider_scorer += (hypo[0], ref)

        (score, scores) = cider_scorer.compute_score()

        return score, scores
Example #5
Source File: cider.py    From neural-image-captioning with MIT License 5 votes vote down vote up 
def compute_score(self, gts, res):
        """
        Main function to compute CIDEr score
        :param  hypo_for_image (dict) : dictionary with key <image> and value <tokenized hypothesis / candidate sentence>
                ref_for_image (dict)  : dictionary with key <image> and value <tokenized reference sentence>
        :return: cider (float) : computed CIDEr score for the corpus 
        """

        assert(sorted(gts.keys()) == sorted(res.keys()))
        imgIds = gts.keys()

        cider_scorer = CiderScorer(n=self._n, sigma=self._sigma)

        for id in imgIds:
            hypo = res[id]
            ref = gts[id]

            # Sanity check.
            assert(type(hypo) is list)
            assert(len(hypo) == 1)
            assert(type(ref) is list)
            assert(len(ref) > 0)

            cider_scorer += (hypo[0], ref)

        (score, scores) = cider_scorer.compute_score()

        return score, scores
Example #6
Source File: cider.py    From video-caption.pytorch with MIT License 5 votes vote down vote up 
def __init__(self, n=4, df="corpus"):
        """
        Initialize the CIDEr scoring function
        : param n (int): n-gram size
        : param df (string): specifies where to get the IDF values from
                    takes values 'corpus', 'coco-train'
        : return: None
        """
        # set cider to sum over 1 to 4-grams
        self._n = n
        self._df = df
        self.cider_scorer = CiderScorer(n=self._n, df_mode=self._df)
Example #7
Source File: cider.py    From captionGAN with MIT License 5 votes vote down vote up 
def compute_score(self, gts, res):
        """
        Main function to compute CIDEr score
        :param  hypo_for_image (dict) : dictionary with key <image> and value <tokenized hypothesis / candidate sentence>
                ref_for_image (dict)  : dictionary with key <image> and value <tokenized reference sentence>
        :return: cider (float) : computed CIDEr score for the corpus 
        """

        #assert(gts.keys() == res.keys())
        assert(set(gts.keys()) == set(res.keys()))
        imgIds = gts.keys()

        cider_scorer = CiderScorer(n=self._n, sigma=self._sigma)

        for id in imgIds:
            hypo = res[id]
            ref = gts[id]

            # Sanity check.
            assert(type(hypo) is list)
            assert(len(hypo) == 1)
            assert(type(ref) is list)
            assert(len(ref) > 0)

            cider_scorer += (hypo[0], ref)

        (score, scores) = cider_scorer.compute_score()

        return score, scores
Example #8
Source File: cider.py    From video-caption.pytorch with MIT License 5 votes vote down vote up 
def __init__(self, n=4, df="corpus"):
        """
        Initialize the CIDEr scoring function
        : param n (int): n-gram size
        : param df (string): specifies where to get the IDF values from
                    takes values 'corpus', 'coco-train'
        : return: None
        """
        # set cider to sum over 1 to 4-grams
        self._n = n
        self._df = df
        self.cider_scorer = CiderScorer(n=self._n, df_mode=self._df)
Example #9
Source File: cider.py    From deepQuest with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def compute_score(self, gts, res):
        """
        Main function to compute CIDEr score
        :param  hypo_for_image (dict) : dictionary with img_id <image> and value <tokenized hypothesis / candidate sentence>
                ref_for_image (dict)  : dictionary with img_id <image> and value <tokenized reference sentence>
        :return: cider (float) : computed CIDEr score for the corpus 
        """

        assert (gts.keys() == res.keys())
        imgIds = gts.keys()

        cider_scorer = CiderScorer(n=self._n, sigma=self._sigma)

        for id in imgIds:
            hypo = res[id]
            ref = gts[id]

            # Sanity check.
            assert (type(hypo) is list)
            assert (len(hypo) == 1)
            assert (type(ref) is list)
            assert (len(ref) > 0)

            cider_scorer += (hypo[0], ref)

        (score, scores) = cider_scorer.compute_score()

        return score, scores
Example #10
Source File: cider.py    From video-caption-openNMT.pytorch with MIT License 5 votes vote down vote up 
def __init__(self, n=4, df="corpus"):
        """
        Initialize the CIDEr scoring function
        : param n (int): n-gram size
        : param df (string): specifies where to get the IDF values from
                    takes values 'corpus', 'coco-train'
        : return: None
        """
        # set cider to sum over 1 to 4-grams
        self._n = n
        self._df = df
        self.cider_scorer = CiderScorer(n=self._n, df_mode=self._df)
Example #11
Source File: cider.py    From AREL with MIT License 5 votes vote down vote up 
def compute_score(self, gts, res):
        """
        Main function to compute CIDEr score
        :param  hypo_for_image (dict) : dictionary with key <image> and value <tokenized hypothesis / candidate sentence>
                ref_for_image (dict)  : dictionary with key <image> and value <tokenized reference sentence>
        :return: cider (float) : computed CIDEr score for the corpus 
        """

        # assert(gts.keys() == res.keys())
        assert(sorted(gts.keys()) == sorted(res.keys()))
        imgIds = gts.keys()

        cider_scorer = CiderScorer(df=self.df, n=self._n, sigma=self._sigma)

        for id in imgIds:
            hypo = res[id]
            ref = gts[id]

            # Sanity check.
            assert(type(hypo) is list)
            assert(len(hypo) == 1)
            assert(type(ref) is list)
            assert(len(ref) > 0)

            cider_scorer += (hypo[0], ref)

        (score, scores) = cider_scorer.compute_score()

        return score, scores
Example #12
Source File: cider.py    From NQG_ASs2s with MIT License 5 votes vote down vote up 
def compute_score(self, gts, res):
        """
        Main function to compute CIDEr score
        :param  hypo_for_image (dict) : dictionary with key <image> and value <tokenized hypothesis / candidate sentence>
                ref_for_image (dict)  : dictionary with key <image> and value <tokenized reference sentence>
        :return: cider (float) : computed CIDEr score for the corpus 
        """

        assert(gts.keys() == res.keys())
        imgIds = gts.keys()

        cider_scorer = CiderScorer(n=self._n, sigma=self._sigma)

        for id in imgIds:
            hypo = res[id]
            ref = gts[id]

            # Sanity check.
            assert(type(hypo) is list)
            assert(len(hypo) == 1)
            assert(type(ref) is list)
            assert(len(ref) > 0)

            cider_scorer += (hypo[0], ref)

        (score, scores) = cider_scorer.compute_score()

        return score, scores
Example #13
Source File: cider.py    From DialoGPT with MIT License 5 votes vote down vote up 
def compute_score(self, gts, res):
        """
        Main function to compute CIDEr score
        :param  hypo_for_image (dict) : dictionary with key <image> and value <tokenized hypothesis / candidate sentence>
                ref_for_image (dict)  : dictionary with key <image> and value <tokenized reference sentence>
        :return: cider (float) : computed CIDEr score for the corpus 
        """

        assert(gts.keys() == res.keys())
        imgIds = gts.keys()

        cider_scorer = CiderScorer(n=self._n, sigma=self._sigma)

        for id in imgIds:
            hypo = res[id]
            ref = gts[id]

            # Sanity check.
            assert(type(hypo) is list)
            assert(len(hypo) == 1)
            assert(type(ref) is list)
            assert(len(ref) > 0)

            cider_scorer += (hypo[0], ref)

        (score, scores) = cider_scorer.compute_score()

        return score, scores
Example #14
Source File: cider.py    From keras-image-captioning with MIT License 5 votes vote down vote up 
def compute_score(self, gts, res):
        """
        Main function to compute CIDEr score
        :param  hypo_for_image (dict) : dictionary with key <image> and value <tokenized hypothesis / candidate sentence>
                ref_for_image (dict)  : dictionary with key <image> and value <tokenized reference sentence>
        :return: cider (float) : computed CIDEr score for the corpus
        """

        assert(set(gts.keys()) == set(res.keys()))
        imgIds = gts.keys()

        cider_scorer = CiderScorer(n=self._n, sigma=self._sigma)

        for id in imgIds:
            hypo = res[id]
            ref = gts[id]

            # Sanity check.
            assert(type(hypo) is list)
            assert(len(hypo) == 1)
            assert(type(ref) is list)
            assert(len(ref) > 0)

            cider_scorer += (hypo[0], ref)

        (score, scores) = cider_scorer.compute_score()

        return score, scores
Example #15
Source File: cider.py    From NeuralBabyTalk with MIT License 5 votes vote down vote up 
def __init__(self, n=4, df="corpus"):
        """
        Initialize the CIDEr scoring function
        : param n (int): n-gram size
        : param df (string): specifies where to get the IDF values from
                    takes values 'corpus', 'coco-train'
        : return: None
        """
        # set cider to sum over 1 to 4-grams
        self._n = n
        self._df = df
        self.cider_scorer = CiderScorer(n=self._n, df_mode=self._df)
Example #16
Source File: cider.py    From densecap-tensorflow with MIT License 5 votes vote down vote up 
def compute_score(self, gts, res):
        """
        Main function to compute CIDEr score
        :param  hypo_for_image (dict) : dictionary with key <image> and value <tokenized hypothesis / candidate sentence>
                ref_for_image (dict)  : dictionary with key <image> and value <tokenized reference sentence>
        :return: cider (float) : computed CIDEr score for the corpus 
        """

        assert(gts.keys() == res.keys())
        imgIds = gts.keys()

        cider_scorer = CiderScorer(n=self._n, sigma=self._sigma)

        for id in imgIds:
            hypo = res[id]
            ref = gts[id]

            # Sanity check.
            assert(type(hypo) is list)
            assert(len(hypo) == 1)
            assert(type(ref) is list)
            assert(len(ref) > 0)

            cider_scorer += (hypo[0], ref)

        (score, scores) = cider_scorer.compute_score()

        return score, scores
Example #17
Source File: cider.py    From Zeroshot-QuestionGeneration with MIT License 5 votes vote down vote up 
def compute_score(self, gts, res):
        """
        Main function to compute CIDEr score
        :param  hypo_for_image (dict) : dictionary with key <image> and value <tokenized hypothesis / candidate sentence>
                ref_for_image (dict)  : dictionary with key <image> and value <tokenized reference sentence>
        :return: cider (float) : computed CIDEr score for the corpus 
        """

        assert(gts.keys() == res.keys())
        imgIds = gts.keys()

        cider_scorer = CiderScorer(n=self._n, sigma=self._sigma)

        for id in imgIds:
            hypo = res[id]
            ref = gts[id]

            # Sanity check.
            assert(type(hypo) is list)
            assert(len(hypo) == 1)
            assert(type(ref) is list)
            assert(len(ref) > 0)

            cider_scorer += (hypo[0], ref)

        (score, scores) = cider_scorer.compute_score()

        return score, scores