Joran Deschamps
Joran Deschamps
From @tibuch in https://github.com/juglab/DenoiSeg/pull/40: The first epoch usually takes super long. In general it feels not very performant.
From @tibuch in https://github.com/juglab/DenoiSeg/pull/40: The image segmentation tensorboard is currently not working and commented. The normal loss tensorboard is available.
From @tibuch in https://github.com/juglab/DenoiSeg/pull/40: Datasets are currently limited, which leads to problems if steps_per_epoch x batch_size is larger than the dataset length. As long as steps_per_epoch x batch_size is smaller...
From @tibuch, modifying the loss so that the masking is per pixel instead of per patch. I drop the idea here otherwise it might get forgotten.
**Describe the bug** In the [bbbc010-2012 predict notebook](https://github.com/juglab/EmbedSeg/blob/main/examples/2d/bbbc010-2012/03-predict.ipynb), the default cell loading the pre-trained model fails. It seems it cannot load the `state_dict` because the module path has changed (`encoder.initial_block.conv.weight`...
Pytorch lightning model format is just a `pytorch_state_dict` with more entries. It should be quite straightforward to make a model adaptor for it, or adapt the current adaptor. Potentially a...
It seems to me that the only way to change the "SaveMode" (single or multi) settings of a DefaultDatastore is through the MDA dialog. If one wants to run an...
Hi there, Finally found the time to look around and start playing with dacapo! I have a few questions and remarks regarding the COSEM models, some of which might just...