Liezl Maree

### Problem Analysis SLEAP uses a class method on the `Labels` object to return a callable for the missing video search. We should return something from this callable to let...

Hi @isabelperezf, @auesro, Do you mind sharing the exported data with me? The problem seems to occur when we call tensorflow's `iter()` function during the creation of the training dataset....

Hi @isabelperezf, @auesro, It seems that the training error is due to a mix of color and grayscale videos in the project. The network architecture used in training requires the...

## Problem Analysis When attempting to train a SLEAP project which has a mix of color and grayscale videos, we get an error from tensorflow: `Shape of tensor EagerPyFunc [180,164,3]...

Hi @auesro, Taking a look at the Video dialog box in the GUI, you can verify how many channels your videos have.  **Fig: The Video Dialog in the SLEAP...

@talmo It seems the issue with the rgb/grayscale persists in inference as well (namely if we use a `LabelsReader` provider to create the dataset - which occurs when we "Predict...

# Problem Analysis When running training/inference from the GUI, SLEAP creates custom `sleap-train` and `sleap-track` CLI arguments to call respectively. For `sleap-track`, the construction of the CLI arguments depends on...

Hi @Estella23, Yes, there is a workaround: In the Training/Inference Pipeline (Predict > Run Training/Inference), you can elect to "Predict On:" either `nothing`, `user labeled frames`, or `suggested frames`. ...

Hi @Estella23, I have a hunch that the errors you are experiencing are due to poorly tuned hyperparameters (the parameters you set when in the Training Pipeline); thus, leading to...

Hi @Estella23, Ok, great. A few parameters you might want to look at: **Receptive Field Size:** The receptive field (RF) size is denoted by the blue square on the sample...