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

请问如何进行测试 #32

Open
asasdsadagweh opened this issue Apr 3, 2023 · 3 comments
Open

请问如何进行测试 #32

asasdsadagweh opened this issue Apr 3, 2023 · 3 comments

Comments

@asasdsadagweh
Copy link

请问怎样只用来直接测试图像,不输入文本。代码里是如下:

        for x in self.annotation:
            if 'COCO_val2014_' + str(x['image_id']).zfill(12) + '.jpg' == _filename:
                caption = x['caption']
                break

如果没有caption将如何工作,谢谢

@buxiangzhiren
Copy link
Owner

train.py 649行的generate2_adpt_if这个函数

@buxiangzhiren
Copy link
Owner

请问怎样只用来直接测试图像,不输入文本。代码里是如下:

        for x in self.annotation:
            if 'COCO_val2014_' + str(x['image_id']).zfill(12) + '.jpg' == _filename:
                caption = x['caption']
                break

如果没有caption将如何工作,谢谢

这里是用来看validation dataset的loss哈。因为cider跟loss没有直接对应关系,loss小不一定cider高。

@asasdsadagweh
Copy link
Author

感谢,我再看一下,我想用图片来测试一下模型,不知道从哪里搞了。

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