liutianling
liutianling
这么少的数据你也赶上深度学习，厉害了
这个问题在句子长度有所增加以后，结果好像好了一些。 vec1 = bc.encode([['我', '喜欢', '吃', '苹果']], is_tokenized=True) vec2 = bc.encode([['我', '用', '苹果', '手机', "妹妹", "在吃", "橘子"]], is_tokenized=True) for i in range(7): print(cos_sim(vec1[0][4], vec2[0][i+1])) 这是结果： 0.8890991046993251 0.901118192389121 0.93790840387366 0.9325583833568518 0.9351127618819679...
@ScottishFold007 有没有通过指定部分关键词生成短文本或长文本的计划？
@zhezhaoa 非常感谢您的工作。请问下，现在中文的ngram词向量训练是否已经支持了呢？另外，说明文档关于再训练的部分好像比较少。谢谢！
@Gladysgong 我看的感觉比较迷糊，你整理的怎样了啊？
@dingjibang 这个问题你解决了吗？我也遇到了这样的问题. @yanwii 但是我关掉GPU后epoch跑到４０００，报错确实段错误
@ma-ji The speed you test is on GPU or CPU? Thanks.
@ma-ji Thanks, have you test the speed on CPU, I test it. And found it really slow. I test three tasks with tokenize,pos and ner, and the average time cost...
Ｉ want to get the output of the layer 'Identity with EfficientNet.Identity. I algo get the same error AttributeError: 'EfficientNet' object has no attribute 'Identity'
By installing tensorflow-gpu 1.0.0, it seems solved the problem of @Zumbalamambo . But i met another problem of memory. Did it need so large memory of 10.9GB just test an...