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

关于zero-shot测试和few-shot测试的设置问题 #40

Open
yanghhx opened this issue May 30, 2023 · 3 comments
Open

关于zero-shot测试和few-shot测试的设置问题 #40

yanghhx opened this issue May 30, 2023 · 3 comments

Comments

@yanghhx
Copy link

yanghhx commented May 30, 2023

你好,请问zero-shot的实验是把有seen类别的数据结果当做预训练模型,然后直接把这个预训练的模型拿来直接预测unseen类别么?zero-shot的测试跟一般的测试只是测试集不一样吗?另外few-shot如何划分样本集呢?

@sallymmx
Copy link
Owner

sallymmx commented May 30, 2023 via email

@michaelwang66
Copy link

你好,请问zero-shot的实验是把有seen类别的数据结果当做预训练模型,然后直接把这个预训练的模型拿来直接预测unseen类别么?zero-shot的测试跟一般的测试只是测试集不一样吗?另外few-shot如何划分样本集呢?
我是这么划分数据集做零样本的,ucf101上成绩差很多,hmdb51上,是有42%-46%的top-1 acc,还是达不到论文的50%。我觉得论文里的结论是gzsl(广义零样本学习的结果),就是验证集同时有seen和unseen class。

@sallymmx
Copy link
Owner

sallymmx commented Oct 25, 2023 via email

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

3 participants