Peter Rupprecht

We can give it a try. 1 Hz is rather slow, so we have to see what we get. I will train a network with all data and another network...

I just uploaded a few models pretrained on the ground truth that was resampled to 1 Hz. In step (7) of the Colab Notebook, you can now select one of...

P.S. If the trained network does not work, let me know. Due to the different timescale, I had to adapt the network structure on the fly, and if it turns...

Hi Max, You might also want to check out issue #39. This is also an application of Cascade to fish (zebrafish) data recorded at relatively low framerate (4.3 Hz). Here,...

Hi Yannick, You are right, Cascade uses the absolute dF/F values to infer spike rates. Yes, there a couple of factors that influence absolute dF/F values, which is not great...

Hi Tony, Thanks a lot for your very clear report and your feedback! Your example recording looks really good to me, given that it comes probably from 2P GRIN lens...

That's a good suggestion. I have added such an entry. I some point in the future I will go through the entire FAQ again and check whether it is still...

Hi @Mariofe25, Thanks for reporting these bugs. I think you're not doing something wrong, there were indeed some bugs in the script. For my own purposes, I was using a...

Coming back to the second issue: 2. After a bit of testing, I found that some specific properties of a subset of ground truth datasets was the cause for the...

I tested the script with a noise level = 4 setting, and it went through smoothly. I hope this solves the issue for you as well, and I will close...