Graph-to-seq-comment-generation icon indicating copy to clipboard operation
Graph-to-seq-comment-generation copied to clipboard

run error

Open ECNUHP opened this issue 5 years ago • 4 comments

Traceback (most recent call last): File "train.py", line 299, in main() File "train.py", line 291, in main max_bleu = train(model, vocab, dataloader, scheduler, optim, updates) File "train.py", line 118, in train outputs = model(batch, use_cuda) File "/opt/lang.huo/miniconda3/envs/huopei/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in call result = self.forward(*input, **kwargs) File "/opt/lang.huo/mybot/question_generation/models/graph2seq.py", line 93, in forward contexts, state, attns = self.encode(src, src_mask, concept, concept_mask, title_index, adjs) File "/opt/lang.huo/mybot/question_generation/models/graph2seq.py", line 71, in encode return contexts, state, attn UnboundLocalError: local variable 'attn' referenced before assignment

出现上述错误是因为什么呢? 跪求解答

ECNUHP avatar Dec 31 '19 07:12 ECNUHP

同问,而且“segged_content.txt”是如何获得的

astrodrew avatar May 27 '20 17:05 astrodrew

可以通过从json文件中抽取

AbnerCode avatar May 31 '20 04:05 AbnerCode

Traceback (most recent call last): File "train.py", line 299, in main() File "train.py", line 291, in main max_bleu = train(model, vocab, dataloader, scheduler, optim, updates) File "train.py", line 118, in train outputs = model(batch, use_cuda) File "/opt/lang.huo/miniconda3/envs/huopei/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in call result = self.forward(*input, **kwargs) File "/opt/lang.huo/mybot/question_generation/models/graph2seq.py", line 93, in forward contexts, state, attns = self.encode(src, src_mask, concept, concept_mask, title_index, adjs) File "/opt/lang.huo/mybot/question_generation/models/graph2seq.py", line 71, in encode return contexts, state, attn UnboundLocalError: local variable 'attn' referenced before assignment

出现上述错误是因为什么呢? 跪求解答

需要预先定义一下,大概是代码中漏定义了。 def encode(self, contents, contents_mask, concepts, concept_mask, title_index, adjs): contexts = [] states = [] attn=[] ……

shenjian5 avatar Jul 20 '20 07:07 shenjian5

attn可以直接删去,这个是分析的时候看attention 权重的发自我的华为手机-------- 原始邮件 --------主题:Re: [lancopku/Graph-to-seq-comment-generation] run error (#7)发件人:shenjian5 收件人:lancopku/Graph-to-seq-comment-generation 抄送:Subscribed

Traceback (most recent call last):

File "train.py", line 299, in

main()

File "train.py", line 291, in main

max_bleu = train(model, vocab, dataloader, scheduler, optim, updates)

File "train.py", line 118, in train

outputs = model(batch, use_cuda)

File "/opt/lang.huo/miniconda3/envs/huopei/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in call

result = self.forward(*input, **kwargs)

File "/opt/lang.huo/mybot/question_generation/models/graph2seq.py", line 93, in forward

contexts, state, attns = self.encode(src, src_mask, concept, concept_mask, title_index, adjs)

File "/opt/lang.huo/mybot/question_generation/models/graph2seq.py", line 71, in encode

return contexts, state, attn

UnboundLocalError: local variable 'attn' referenced before assignment

出现上述错误是因为什么呢?

跪求解答

需要预先定义一下,大概是代码中漏定义了。

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

[

{

"@context": "http://schema.org",

"@type": "EmailMessage",

"potentialAction": {

"@type": "ViewAction",

"target": "https://github.com/lancopku/Graph-to-seq-comment-generation/issues/7#issuecomment-660855293",

"url": "https://github.com/lancopku/Graph-to-seq-comment-generation/issues/7#issuecomment-660855293",

"name": "View Issue"

},

"description": "View this Issue on GitHub",

"publisher": {

"@type": "Organization",

"name": "GitHub",

"url": "https://github.com"

}

}

]

liweitj47 avatar Jul 20 '20 07:07 liweitj47