Mohammed Innat

@qubvel any update?

Check [this answer](https://stackoverflow.com/a/67708260/9215780) regarding your issue. Hope it helps.

You can add a convolutional layer with feature maps 3 with pad size 3 (same) to match with the imagenet weights.

@shuaibaslam2019 I've played with fmix, cutmix, mixup with keras sequence generator, [notebook here](https://www.kaggle.com/ipythonx/tf-keras-cassava-advanced-training-mechanism), you may find it as a guide starter in keras.

No, it's not. Here is the official implementation. https://gist.github.com/aravindsrinivas/56359b79f0ce4449bcb04ab4b56a57a2

@muellerdo

@muellerdo Thanks for the reply. > patchwise-grid -> apply subfunctions on the whole image but split the preprocessed image in patches in a grid-like fashion. then pass all patches to...

> patching interface, automatically pads volumes to the minimum patch_shape. I think it's programmed [HERE](https://github.com/frankkramer-lab/MIScnn/blob/d715af62839b7577e61a6a2ce7fc5ff4a21bcc58/miscnn/processing/subfunctions/padding.py#L74). To match with the target volume, does it repeat the same slices that times?

> PS: I think this would be helpful also for other MIScnn users. Would it be ok for you, if we move this issue to the MIScnn repo? Yeah, sure....

I was reading paperwork, which used the 20 cases of covid ct images. While reading the paper, I came across the **name** of this repo (MIScnn). [HERE ](https://www.nature.com/articles/s41598-021-01502-0.pdf)is the paper....