Jerome Lecoq
Jerome Lecoq
On `RoiResponseSeries`, that is the name of the object type. If you look at these files, I noticed there are "Deconvolved" and "Neuropil" objects so it is akward to have...
Appending seems reasonable. I think that is the desired process with immutable files. The question that follows is which software would be the first one to create the original NWB?...
Just a quick question, you can still edit some of these placeholder fields, right? Say for example you did a mistake in the data or gender of the mouse, do...
What are the metadata 2p imaging segmentation need to be filled in? I wonder if they are all relevant.
> > You can still edit some of these placeholder fields, right? Say for example you did a mistake in the data or gender of the mouse, do you have...
Very good example. In some cases, brain areas might be undefined at the time of the experiment and could be worked out much later on. Suite2p has no way to...
Also experienced by @danielsf
Hi Chris, I am happy to help with this. What is your batch size for 2p? This can increase the need for GPU memory quite quickly.
The key to this error is RESOURCE_EXHAUSTED: OOM when allocating tensor with shape[5,192,512,512] This size array is not requested at any point in the network architecture, which suggests that some...
For large datasets, the expected use of the .predict function in tensorflow is to feed in the entire dataset and the internal system would loop through it, creating internal batches....