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

请问为什么image_shape只能是[3, 512, 512]? #206

Closed
sidongfeng opened this issue Jun 15, 2020 · 7 comments
Closed

请问为什么image_shape只能是[3, 512, 512]? #206

sidongfeng opened this issue Jun 15, 2020 · 7 comments

Comments

@sidongfeng
Copy link

报错原因:Error: ShapeError: broadcast dimension mismatch
image

@dyning
Copy link
Collaborator

dyning commented Jun 15, 2020

这个是模型训练,还是预测?

@sidongfeng
Copy link
Author

训练模型

@LDOUBLEV
Copy link
Collaborator

可否提供完整的报错信息和运行指令

@sidongfeng
Copy link
Author

运行指令:
1148630c613ae60303af2b333fbc2d7
bb088595e6252c1c0b9487bd7dfddb0

报错信息:
image

@LDOUBLEV
Copy link
Collaborator

已修复,可以更新下代码

@sidongfeng
Copy link
Author

谢谢更新。

@BruceHan98
Copy link

你好,我在det_db预训练模型上训练自己的数据集(图片尺寸不是默认的(3,640,640))时,修改相应的配置文件的image_shape为自己数据集的图片尺寸,出现了同样的情况:Broadcast dimension mismatch.
请问需要修改哪些文件来解决?

Error Message Summary:

InvalidArgumentError: Broadcast dimension mismatch. Operands could not be broadcast together with the shape of X = [16, 96, 64, 10] and the shape of Y = [16, 96, 63, 10]. Received [64] in X is not equal to [63] in Y at i:2.

an1018 pushed a commit to an1018/PaddleOCR that referenced this issue Aug 17, 2022
* update YOLOv3_ENHANCEMENT.md
* update IoUloss and DropBlock configs for YOLOv3 related configs
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

4 participants