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MSCOCO测试集 #3

Open
L4EX opened this issue Nov 25, 2020 · 2 comments
Open

关于MSCOCO测试集 #3

L4EX opened this issue Nov 25, 2020 · 2 comments

Comments

@L4EX
Copy link

L4EX commented Nov 25, 2020

因为一个图片对应的是五个caption,所以测试的是1K TEST 5折交叉验证用的是多少size的数据集, 5K TEST又用的是多少size的数据集?
在evalrank()函数中,有
for i in range(5):
print(i)
img_emb_new = img_embs[i * 5000 : int(i * 5000 + img_embs.size(0)/5):5]
cap_emb_new = cap_embs[i * 5000 : int(i * 5000 + cap_embs.size(0)/5)]
这里明显,如果用1K张图扩展五倍构成的数据集,是一定会下标越界的.

@kywen1119
Copy link
Owner

使用的同样的测试集,即5k张图片和25k条句子。分为5折交叉测试以及全部一起测试。
您提到的函数中。测试时图片为了和文本对齐,扩充成了25000张(每5张是一样的),每次测试1k张,比如说第一个1k就是下标0-4999的5k张每隔5张取一张,即:
img_emb_new = img_embs[i * 5000 : int(i * 5000 + img_embs.size(0)/5):5]

@L4EX
Copy link
Author

L4EX commented Nov 29, 2020 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

2 participants