Python utils.assert_eq方法代码示例

# 需要导入模块: import utils [as 别名]
# 或者: from utils import assert_eq [as 别名]
def _load_dataset(dataroot, name, img_id2val):
    """Load entries

    img_id2val: dict {img_id -> val} val can be used to retrieve image or features
    dataroot: root path of dataset
    name: 'train', 'val'
    """
    question_path = os.path.join(
        dataroot, 'v2_OpenEnded_mscoco_%s2014_questions.json' % name)
    questions = sorted(json.load(open(question_path))['questions'],
                       key=lambda x: x['question_id'])
    answer_path = os.path.join(dataroot, 'cache', '%s_target.pkl' % name)
    answers = cPickle.load(open(answer_path, 'rb'))
    answers = sorted(answers, key=lambda x: x['question_id'])

    utils.assert_eq(len(questions), len(answers))
    entries = []
    for question, answer in zip(questions, answers):
        utils.assert_eq(question['question_id'], answer['question_id'])
        utils.assert_eq(question['image_id'], answer['image_id'])
        img_id = question['image_id']
        entries.append(_create_entry(img_id2val[img_id], question, answer))

    return entries 

# 需要导入模块: import utils [as 别名]
# 或者: from utils import assert_eq [as 别名]
def tokenize(self, max_length=14):
        """Tokenizes the questions.

        This will add q_token in each entry of the dataset.
        -1 represent nil, and should be treated as padding_idx in embedding
        """
        for entry in self.entries:
            tokens = self.dictionary.tokenize(entry['question'], False)
            tokens = tokens[:max_length]
            if len(tokens) < max_length:
                # Note here we pad to the back of the sentence
                padding = [self.dictionary.padding_idx] * \
                          (max_length - len(tokens))
                tokens = tokens + padding
            utils.assert_eq(len(tokens), max_length)
            entry['q_token'] = tokens 

# 需要导入模块: import utils [as 别名]
# 或者: from utils import assert_eq [as 别名]
def _load_dataset(dataroot, name, img_id2val):
    """Load entries
    img_id2val: dict {img_id -> val} val can be used to retrieve image or features
    dataroot: root path of dataset
    name: 'train', 'val'
    """
    question_path = os.path.join(
        dataroot, 'v2_OpenEnded_mscoco_%s2014_questions.json' % name)
    questions = sorted(json.load(open(question_path))['questions'],
                       key=lambda x: x['question_id'])
    answer_path = os.path.join(dataroot, 'cache', '%s_target.pkl' % name)
    answers = pickle.load(open(answer_path, 'rb'))
    answers = sorted(answers, key=lambda x: x['question_id'])

    utils.assert_eq(len(questions), len(answers))
    entries = []
    for question, answer in zip(questions, answers):
        utils.assert_eq(question['question_id'], answer['question_id'])
        utils.assert_eq(question['image_id'], answer['image_id'])
        img_id = question['image_id']
        entries.append(_create_entry(img_id2val[img_id], question, answer))

    return entries 

# 需要导入模块: import utils [as 别名]
# 或者: from utils import assert_eq [as 别名]
def tokenize(self, max_length=14):
        """Tokenizes the questions.

        This will add q_token in each entry of the dataset.
        -1 represent nil, and should be treated as padding_idx in embedding
        """
        for entry in self.entries:
            tokens = self.dictionary.tokenize(entry['question'], False)
            tokens = tokens[:max_length]
            if len(tokens) < max_length:
                # Note here we pad in front of the sentence
                padding = [self.dictionary.padding_idx] * (max_length - len(tokens))
                tokens = padding + tokens
            utils.assert_eq(len(tokens), max_length)
            entry['q_token'] = tokens 

# 需要导入模块: import utils [as 别名]
# 或者: from utils import assert_eq [as 别名]
def make_json(logits, qIds, dataloader):
    utils.assert_eq(logits.size(0), len(qIds))
    results = []
    for i in range(logits.size(0)):
        result = {}
        result['question_id'] = qIds[i].item()
        result['answer'] = get_answer(logits[i], dataloader)
        results.append(result)
    return results 

# 需要导入模块: import utils [as 别名]
# 或者: from utils import assert_eq [as 别名]
def _load_dataset(dataroot, name, coco_train_img_id2val, coco_val_img_id2val,
                  label2ans):
    """Load entries

    coco_train_img_id2val/coco_val_img_id2val:
        dict {img_id -> val} val can be used to retrieve image or features
    dataroot: root path of dataset
    name: 'train', 'val'
    """
    question_path = os.path.join(
        dataroot, 'cp_v2_questions/vqacp_v2_%s_questions.json' % name)
    questions = sorted(json.load(open(question_path)),
                       key=lambda x: x['question_id'])
    answer_path = os.path.join(dataroot, 'cache', 'cp_v2_%s_target.pkl' % name)
    answers = pickle.load(open(answer_path, 'rb'))
    answers = sorted(answers, key=lambda x: x['question_id'])

    utils.assert_eq(len(questions), len(answers))
    entries = []
    for question, answer in zip(questions, answers):
        utils.assert_eq(question['question_id'], answer['question_id'])
        utils.assert_eq(question['image_id'], answer['image_id'])
        img_id = question['image_id']
        coco_split = question["coco_split"]
        index = coco_train_img_id2val[img_id]\
            if coco_split == "train2014" else coco_val_img_id2val[img_id]
        if not COUNTING_ONLY \
           or is_howmany(question['question'], answer, label2ans):
            entries.append(_create_entry(index, question, answer))
    return entries 

# 需要导入模块: import utils [as 别名]
# 或者: from utils import assert_eq [as 别名]
def _load_dataset(dataroot, name, img_id2val, label2ans):
    """Load entries

    img_id2val: dict {img_id -> val} val can be used to
                retrieve image or features
    dataroot: root path of dataset
    name: 'train', 'val', 'test-dev2015', test2015'
    """
    question_path = os.path.join(
        dataroot, 'Questions/v2_OpenEnded_mscoco_%s_questions.json' %
        (name + '2014' if 'test' != name[:4] else name))
    questions = sorted(json.load(open(question_path))['questions'],
                       key=lambda x: x['question_id'])
    # train, val
    if 'test' != name[:4]:
        answer_path = os.path.join(dataroot, 'cache', '%s_target.pkl' % name)
        answers = pickle.load(open(answer_path, 'rb'))
        answers = sorted(answers, key=lambda x: x['question_id'])

        utils.assert_eq(len(questions), len(answers))
        entries = []
        for question, answer in zip(questions, answers):
            utils.assert_eq(question['question_id'], answer['question_id'])
            utils.assert_eq(question['image_id'], answer['image_id'])
            img_id = question['image_id']
            if not COUNTING_ONLY \
               or is_howmany(question['question'], answer, label2ans):
                entries.append(_create_entry(img_id2val[img_id],
                                             question, answer))
    # test2015
    else:
        entries = []
        for question in questions:
            img_id = question['image_id']
            if not COUNTING_ONLY \
               or is_howmany(question['question'], None, None):
                entries.append(_create_entry(img_id2val[img_id],
                                             question, None))

    return entries 

# 需要导入模块: import utils [as 别名]
# 或者: from utils import assert_eq [as 别名]
def tokenize(self, max_length=14):
        """Tokenizes the questions.
        This will add q_token in each entry of the dataset.
        -1 represent nil, and should be treated as padding_idx in embedding
        """
        for entry in self.entries:
            tokens = self.dictionary.tokenize(entry['question'], False)
            tokens = tokens[:max_length]
            if len(tokens) < max_length:
                # Note here we pad in front of the sentence
                padding = [self.dictionary.padding_idx] * (max_length - len(tokens))
                tokens = padding + tokens
            utils.assert_eq(len(tokens), max_length)
            entry['q_token'] = tokens 

# 需要导入模块: import utils [as 别名]
# 或者: from utils import assert_eq [as 别名]
def _load_dataset(dataroot, name, img_id2val, label2ans):
    """Load entries

    img_id2val: dict {img_id -> val} val can be used to retrieve image or features
    dataroot: root path of dataset
    name: 'train', 'val', 'test-dev2015', test2015'
    """
    question_path = os.path.join(
        dataroot, 'v2_OpenEnded_mscoco_%s_questions.json' % \
        (name + '2014' if 'test'!=name[:4] else name))
    questions = sorted(json.load(open(question_path))['questions'],
                       key=lambda x: x['question_id'])
    if 'test'!=name[:4]: # train, val
        answer_path = os.path.join(dataroot, 'cache', '%s_target.pkl' % name)
        answers = cPickle.load(open(answer_path, 'rb'))
        answers = sorted(answers, key=lambda x: x['question_id'])

        utils.assert_eq(len(questions), len(answers))
        entries = []
        for question, answer in zip(questions, answers):
            utils.assert_eq(question['question_id'], answer['question_id'])
            utils.assert_eq(question['image_id'], answer['image_id'])
            img_id = question['image_id']
            if not COUNTING_ONLY or is_howmany(question['question'], answer, label2ans):
                entries.append(_create_entry(img_id2val[img_id], question, answer))
    else: # test2015
        entries = []
        for question in questions:
            img_id = question['image_id']
            if not COUNTING_ONLY or is_howmany(question['question'], None, None):
                entries.append(_create_entry(img_id2val[img_id], question, None))

    return entries 

# 需要导入模块: import utils [as 别名]
# 或者: from utils import assert_eq [as 别名]
def tokenize(self, max_length=14):
        """Tokenizes the questions.

        This will add q_token in each entry of the dataset.
        -1 represent nil, and should be treated as padding_idx in embedding
        """
        for entry in self.entries:
            tokens = self.dictionary.tokenize(entry['question'], False)
            tokens = tokens[:max_length]
            if len(tokens) < max_length:
                # Note here we pad in front of the sentence
                padding = [self.dictionary.padding_idx] * (max_length - len(tokens))
                tokens = tokens + padding
            utils.assert_eq(len(tokens), max_length)
            entry['q_token'] = tokens