摘要：z = torch.full((3,4),-5) print(z) a = ~z print(a) print('') import numpy b = numpy.full((3,4),-5) print(z) a = ~z print(a) tensor([[-5, -5, -5, -5], [ 阅读全文

摘要：一个简单的主入口是这样滴： import sys sys.path.append('..') import torch from pytorch_pretrained_bert import BertTokenizer, BertModel, BertForMaskedLM # Load pre-t 阅读全文