Christopher Dupuis
Christopher Dupuis
Currently, there doesn't seem to be a nice way of interfacing a batch with a model with multiple inputs/outputs. This list comprehension works, but I think there could be a...
See issues #36 and #38 @jhamman @rabernat I'm not sure if this solves the problem in all cases, can you have a look?
Otherwise, the user has to do this on their own to match the Keras interfaces.
In trying to solve #36, I found that this warning `WARNING:tensorflow:Keras is training/fitting/evaluating on array-like data. Keras may not be optimized for this format, so if your input data format...
### Is your feature request related to a problem? When you create a batch generator, what happens when you have data with NaNs? For example, if we consider an ocean...
### What is your issue? I've been doing some ad-hoc performance profiling, and it looks like `_drop_input_dims` is always the culprit for why my batch generation runs slow. I blame...
### Is your feature request related to a problem? Title. Basically, in most cases you can control your batch size by setting the `batch_dims` option in BatchGenerator. However, if you...
### What is your issue? Title. The problem is that changing dimension names makes it difficult for the user to index into batched arrays in a batch loop. This is...
Re: #231
### Dataset Name PyQG Subgrid Forcing ### Dataset URL The base URL is `https://g-402b74.00888.8540.data.globus.org/`, but see below for examples. ### Description For full details, see the official publication here: https://agupubs.onlinelibrary.wiley.com/doi/abs/10.1029/2022MS003258...