How to infer for images of small size

[GiannakopoulosIlias]

Hello,

I have a custom datasets of jpgs of a small size (38x47 to be precise).

Is it possible to adjust the network to infer the edges for these images?

If I run without any modifications in the network, I get this error:

File "./DiffusionEdge-main/denoising_diffusion_pytorch/mask_cond_unet.py", line 952, in forward
x = torch.cat((x, h.pop()), dim = 1)
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 4 but got size 5 for tensor number 1 in the list.

Thanks!

[GuHuangAI]

@GiannakopoulosIlias
Hello, I have two suggestions:
(1) Since the model is trained with the image size of 320x320, it can not deal with images that have smaller sizes. Without retraining the model, you can try to resize the smaller images to larger sizes. I guess the performance may be not good.
(2) The better way to obtain correct edges is to retrain the diffusionedge with a crop size of 32x32.
Besides, I'm a little curious what your images look like.

[GiannakopoulosIlias]

Hello, thanks a lot for the inputs on this.

For (1) I agree that an interpolation might lead it sub-optimal results.
For (2) we have 2D quantitative maps and we can export them to jpgs. Here is how the python plot looks like.
Do you think retraining the network with one of the available datasets would work well for these type of edges? Unfortunately we don't have any ground-truth edge mask.

[GuHuangAI]

I think diffusionedge can handle this type of image when training on the similar datasets (small images), however, I don't know if there is such a dataset. If you want to train diffusionedge on this type of dataset (32x32), you do not have to use latent diffusion model, but just train the model in the image space.

[GiannakopoulosIlias]

I think diffusionedge can handle this type of image when training on the similar datasets (small images), however, I don't know if there is such a dataset. If you want to training diffusion edge on this type of dataset (32x32), you do not have to use latent diffusion model, but just train the model in the image space.

Thanks again! I will experiment a bit further with resizing as it seems simpler for now.

[15634960802]

我认为 diffusionedge 在类似的数据集（小图像）上训练时可以处理这种类型的图像，但是，我不知道是否有这样的数据集。如果要在这种类型的数据集 （32x32） 上训练扩散边缘，则不必使用潜在扩散模型，而只需在图像空间中训练模型即可。

再次感谢！我将进一步尝试调整大小，因为它现在看起来更简单。

Hello, how did you solve it in the end? I also encountered a similar problem. But I don't have a similar small-sized training dataset