MCPcopy Create free account
hub / github.com/ICTMCG/FakeSV / Title_W2V_Dataset

Class Title_W2V_Dataset

code/utils/dataloader.py:537–576  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

535
536
537class Title_W2V_Dataset(Dataset):
538 def __init__(self, path_vid, wv_from_text):
539 self.data_complete = pd.read_json('./data/data.json',orient='records',dtype=False,lines=True)
540
541 self.vid = []
542 with open('./data/vids/'+path_vid, "r") as fr:
543 for line in fr.readlines():
544 self.vid.append(line.strip())
545 self.data = self.data_complete[self.data_complete.video_id.isin(self.vid)]
546 self.data['video_id'] = self.data['video_id'].astype('category')
547 self.data['video_id'].cat.set_categories(self.vid, inplace=True)
548 self.data.sort_values('video_id', ascending=True, inplace=True)
549 self.data.reset_index(inplace=True)
550
551 self.wv_from_text = wv_from_text
552
553 def __len__(self):
554 return self.data.shape[0]
555
556 def __getitem__(self, idx):
557 item = self.data.iloc[idx]
558
559 label = 1 if item['annotation']=='假' else 0
560 label = torch.tensor(label)
561
562 text = item['description']+' '+item['ocr']
563 title_w2v = []
564 for word in jieba.cut(text, cut_all=False):
565 if self.wv_from_text.__contains__(word):
566 try:
567 title_w2v.append(self.wv_from_text[word])
568 except:
569 continue
570
571 title_w2v = torch.FloatTensor(title_w2v)
572
573 return {
574 'label': label,
575 'title_w2v': title_w2v,
576 }
577
578
579class CommentsDataset(Dataset):

Callers 1

get_dataloaderMethod · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected