Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

FileWriter Warning #16

Open
plenari opened this issue Nov 18, 2019 · 6 comments
Open

FileWriter Warning #16

plenari opened this issue Nov 18, 2019 · 6 comments

Comments

@plenari
Copy link

plenari commented Nov 18, 2019

Finished trainig!Saving model to disk.保存模型的时候 attempting to use a closed FileWriter .The operation will be a noop unless the FileWriter is explicitly reopened.

@plenari
Copy link
Author

plenari commented Nov 18, 2019

python 3.7 tensorflow 1.13.1,ubuntu 18.04

@Danbinabo
Copy link

embeddings = end_points_1['embeddings']这里报错,KeyError: 'embeddings'这里是取的那一层的特征图啊?谢谢!

@plenari
Copy link
Author

plenari commented Nov 26, 2019

embeddings = end_points_1['embeddings']这里报错,KeyError: 'embeddings'这里是取的那一层的特征图啊?谢谢!
默认的就是inception_V3_bap啊,不要该模型名称。你进去看看就知道了。

@Danbinabo
Copy link

Danbinabo commented Nov 26, 2019 via email

@plenari
Copy link
Author

plenari commented Nov 26, 2019

不是这个吧,你说的这个是预训练模型,我说的计算calculate_pooling_center_loss这里输入的特征层是哪一个,帮我看一下,谢谢

---Original--- From: "plenari"<[email protected]> Date: Tue, Nov 26, 2019 16:45 PM To: "tau-yihouxiang/WS_DAN"<[email protected]>; Cc: "Comment"<[email protected]>;"zhouwenbo"<[email protected]>; Subject: Re: [tau-yihouxiang/WS_DAN] FileWriter Warning (#16) embeddings = end_points_1['embeddings']这里报错,KeyError: 'embeddings'这里是取的那一层的特征图啊?谢谢! 默认的就是inception_V3_bap啊,不要该模型名称。你进去看看就知道了。 — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.

你去看一下源码net/incepton_v3_bap

@Danbinabo
Copy link

大佬加个qq私聊以下,谢谢

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants