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

我在训练多分辨率融合时遇到一个问题 #14

Open
yuanxin703heb opened this issue Sep 17, 2021 · 9 comments
Open

我在训练多分辨率融合时遇到一个问题 #14

yuanxin703heb opened this issue Sep 17, 2021 · 9 comments

Comments

@yuanxin703heb
Copy link

ir_batch[b, :, :] = scipy.ndimage.zoom(ir_or_batch[b, :, :], 0.25)

ValueError: could not broadcast input array from shape (0,21) into shape (21,21)

执行的过程中报了这个错误。请问应该如何处理

@superxmmdm
Copy link

我遇到了同样的问题,请问您解决了吗?

@Xyler6561
Copy link

您好, 我也遇到了一样的问题,不知道这个问题有没有相关解决方法呢?

@hanna-xu
Copy link
Owner

数据维度不一致造成的,建议交换数据维度

@superxmmdm
Copy link

superxmmdm commented Oct 11, 2022 via email

@lmydream
Copy link

我也遇到了这个问题,请问您是怎么解决的呢?非常感谢

@1214083397
Copy link

建议修改为:
VIS_batch = source_imgs[batch * BATCH_SIZE:(batch * BATCH_SIZE + BATCH_SIZE), 0, :, :]
ir_or_batch = source_imgs[batch * BATCH_SIZE:(batch * BATCH_SIZE + BATCH_SIZE), 1, :, :]

@1214083397
Copy link

ir_batch[b, :, :] = scipy.ndimage.zoom(ir_or_batch[b, :, :], 0.25)

ValueError: could not broadcast input array from shape (0,21) into shape (21,21)

执行的过程中报了这个错误。请问应该如何处理

建议修改为:
VIS_batch = source_imgs[batch * BATCH_SIZE:(batch * BATCH_SIZE + BATCH_SIZE), 0, :, :]
ir_or_batch = source_imgs[batch * BATCH_SIZE:(batch * BATCH_SIZE + BATCH_SIZE), 1, :, :]

@1214083397
Copy link

我也遇到了这个问题,请问您是怎么解决的呢?非常感谢

建议修改为:
VIS_batch = source_imgs[batch * BATCH_SIZE:(batch * BATCH_SIZE + BATCH_SIZE), 0, :, :]
ir_or_batch = source_imgs[batch * BATCH_SIZE:(batch * BATCH_SIZE + BATCH_SIZE), 1, :, :]

@lmydream
Copy link

lmydream commented Jun 9, 2023

数据维度不一致造成的,建议交换数据维度
想用自己的数据集跑same-resolution vis-ir image fusion的图像融合,然后把一张源图像分为若干个84X84patch组成数据集,但是训练结果非常非常差,请问一下这是我数据集制作的错误吗

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

6 participants