vqa_data_provider_layer.py 文件源码

def __init__(self, vdict_path, adict_path, \
        batchsize=128, max_length=15, n_ans_vocabulary=1000, mode='train', data_shape=(2048)):

        self.batchsize = batchsize
        self.d_vocabulary = None
        self.batch_index = None
        self.batch_len = None
        self.rev_adict = None
        self.max_length = max_length
        self.n_ans_vocabulary = n_ans_vocabulary
        self.mode = mode
        self.data_shape = data_shape

        assert self.mode == 'test'

        # load vocabulary
        with open(vdict_path,'r') as f:
            vdict = json.load(f)
        with open(adict_path,'r') as f:
            adict = json.load(f)
        self.n_vocabulary, self.vdict = len(vdict), vdict
        self.n_ans_vocabulary, self.adict = len(adict), adict

        self.nlp = spacy.load('en', vectors='en_glove_cc_300_1m_vectors')
        self.glove_dict = {} # word -> glove vector