Noah F. Greenwald

Thanks for letting us know. Yes, we recently updated the model, which is what is causing the changes. While we sort it out, you can revert back to a previous...

Hey @E5ten, I looked into this a bit more. The data you are running through the model, based on a visual inspection, has a quite different signal to noise ratio...

Yeah, the workaround was don't do any subsampling and train on the whole dataset.

Hey @AlexInJar, this dataset contains microscopy images from a range of different microscopes. Each microscope has a different output range, depending on how the manufacturer configured it and the user...

The annotators get the raw version, with the ability to rescale each channel to whatever brightness they find useful. The histogram normalization is an automated way to accomplish the same...

The true positive is determined using a matching algorithm. You can take a look at the [code](https://github.com/vanvalenlab/deepcell-toolbox/blob/master/deepcell_toolbox/metrics.py) to see how its implemented. There's also a section in the methods section...

The model expects two channels of image data, one for the nucleus and one for the membrane. If your RGB data has three colors, you can select only the relevant...

Hi @tbudiman7, good question. It is indeed using the same seeds for the expansion. It's possible that there are very small objects which do not meet the minimum size threshold...

Hmmm, interesting issue. What _should_ happen is that images smaller than 256x256 are padded prior to prediction. It seems that logic may not be working correctly. I'm wondering if this...

I would suggest running the model on a very small crop (1024x1024) of your input image to make sure the memory/large image problems can be separated from the 0s and...