Manan Lalit
Manan Lalit
I speak only as a reader of the publication, the authors would be able to give a more informed answer: 1. It should be possible to track on custom datasets....
Hello @kenta-takizawa, Thanks for looking into `EmbedSeg`! Could you also please share the `01-data` and `02-train` notebooks which you ran as well (for example, by exporting them to html. This...
Hello @Saharkakavand. Thank you for opening an issue and trying out _EmbedSeg_! Could you share the size of the original images and the `crop_size` which you used in `01-data.ipynb`? A...
Okay, so these look like confocal volume images since the size of the _z_ dimension appears almost the same as _x_ and _y_ dimensions, is that correct? [This](https://github.com/juglab/EmbedSeg/blob/main/examples/3d/Platynereis-ISH-Nuclei-CBG/01-data.ipynb) set of...
Hello @Saharkakavand Thanks for giving this a go. To me, the loss after 60 epochs looks reasonable- probably a better indicator of whether the training is stagnating is by looking...
The `iou` profile appears strange to me- my understanding is that the iou shouldn't really go down unless the validation and train images are quite different in their appearance. Would...
I am guessing this is similar to the related [issue](https://github.com/danielfrg/mkdocs-jupyter/issues/170#issue-1910109868) but not the same maybe, since the cell is not executed as opposed to the output being hidden?
Hello @codingS3b Thank you for looking into this and also for your pull request (I will get to it hopefully next week!). On this question front, I wanted to ask...