shenweichen / GraphEmbedding

Implementation and experiments of graph embedding algorithms.
MIT License
3.68k stars 995 forks source link

执行deepwalk_wiki.py文件时的报错__init__() got an unexpected keyword argument 'size' #50

Closed Dzhilin closed 2 years ago

Dzhilin commented 3 years ago

请问是怎么解决的呢?

leekm189 commented 3 years ago

tf版本问题吧,试试tf1.4

Dzhilin commented 3 years ago

好的,我试试,谢谢!发自我的华为手机-------- 原始邮件 --------发件人: leekm189 @.>日期: 2021年4月29日周四 下午3:56收件人: shenweichen/GraphEmbedding @.>抄送: Dzhilin @.>, Author @.>主 题: Re: [shenweichen/GraphEmbedding] 执行deepwalk_wiki.py文件时的报错init() got an unexpected keyword argument 'size' (#50)

tf版本问题吧,试试tf1.4

—You are receiving this because you authored the thread.Reply to this email directly, view it on GitHub, or unsubscribe.

kexin997 commented 3 years ago

me too

lostdirt commented 3 years ago

hello,请问这个问题您解决了吗?

bruceEeZhao commented 2 years ago

这个问题是因为word2vec的版本问题,word2vec将size变成了vector_size,因此需要修改/models/deepwalk.py文件,

@@ -38,12 +38,12 @@ class DeepWalk:

         kwargs["sentences"] = self.sentences
         kwargs["min_count"] = kwargs.get("min_count", 0)
-        kwargs["size"] = embed_size
+        kwargs["vector_size"] = embed_size
         kwargs["sg"] = 1  # skip gram
         kwargs["hs"] = 1  # deepwalk use Hierarchical Softmax
         kwargs["workers"] = workers
         kwargs["window"] = window_size
-        kwargs["iter"] = iter
+        kwargs["epochs"] = iter

node2vec, struct2vec因为使用了word2vec也需要做同样的修改,

修改完之后需要对这个模块进行重新安装

pip uninstall ge
python.exe setup.py install