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

utils/loss.py似乎不支持多分类问题 #57

Open
Faccococo opened this issue Apr 5, 2023 · 3 comments
Open

utils/loss.py似乎不支持多分类问题 #57

Faccococo opened this issue Apr 5, 2023 · 3 comments

Comments

@Faccococo
Copy link

您好!我注意到在utils/loss.py的170行附近有这样一处表达:pkpt_score = ps[:, 8::3]
您似乎没有考虑多分类的情况?当分类数量大于1时,关键点的置信度应该并不是从8,而是从7+num_class处开始。

@XhHello
Copy link

XhHello commented Apr 13, 2023

您好!我注意到在utils/loss.py的170行附近有这样一处表达:pkpt_score = ps[:, 8::3] 您似乎没有考虑多分类的情况?当分类数量大于1时,关键点的置信度应该并不是从8,而是从7+num_class处开始。

请问为啥要从8改为7+num_calss呢

@CabbageWust
Copy link

您好!我注意到在utils/loss.py的170行附近有这样一处表达:pkpt_score = ps[:, 8::3] 您似乎没有考虑多分类的情况?当分类数量大于1时,关键点的置信度应该并不是从8,而是从7+num_class处开始。

那“pkpt_x = ps[:, 6::3] * 2. - 0.5” 和 “pkpt_y = ps[:, 7::3] * 2. - 0.5” 这两句是不是都要改,请问下您训练了多分类了吗?

@Faccococo
Copy link
Author

您好!我注意到在utils/loss.py的170行附近有这样一处表达:pkpt_score = ps[:, 8::3] 您似乎没有考虑多分类的情况?当分类数量大于1时,关键点的置信度应该并不是从8,而是从7+num_class处开始。

那“pkpt_x = ps[:, 6::3] * 2. - 0.5” 和 “pkpt_y = ps[:, 7::3] * 2. - 0.5” 这两句是不是都要改,请问下您训练了多分类了吗?

看起来是的。我还没能走完整个训练流程,看起来像是在生成混淆矩阵是出错了

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

3 participants