Christian Bartz
Christian Bartz
Hi, this is indeed very odd. Could you provide me with the exact error?
I see you are using anaconda. This could be the problem because according to the [Kornia release notes](https://github.com/kornia/kornia/releases/tag/v0.3.1) it should support Python 3.8. If it really does not work, you...
Hi, using our code, you can also do style mixing. However, you unfortunately used the wrong script for this. `file_based_simple_style_transfer.py` can be used to perform real neural style transfer as...
Your changes look good so far. Right now, you are running into a fundamental problem with our approach. If you train an autoencoder without any special care, the latent code...
Hi, the exact training data for the assessor are the images created using backgrounds and templates and the calculated iou of the image crop and the pasted object. Your assessor...
Hi, it looks like you used the script in the correct way. How large are your background images? > How and where can I select Box ? Can you please...
Do you mean a video showing how to create a dataset for training?
Good idea, I might do it when I find some time =)
Hi, if you download an image from the internet, it should actually work with the code... You can download one of the models and use the script `image_sheeping.py` with a...
> But , what if localizer crops only a portion of target object ? This case is handled by preparing the dataset in such a way that if the localizer...