Liezl Maree

Hi @anas-masood, I just ran a quick test: training the network with images/videos of different size still results in offset predictions in the videos where SLEAP tries to automatically rescale...

Hi @anas-masood, @leonardolv, The fix has been merged into develop and will be available in the next release. Alternatively, you can [install SLEAP from source](https://sleap.ai/installation.html#conda-from-source) to get the fix now....

This issue has been resolved in the new release - install [here](https://sleap.ai/installation.html#conda-package).

Hi @aarahvar2, This is a known bug. Thanks for reporting! Closing for now and following up in #669. Thanks, Liezl

Re-opening this issue. I misinterpreted the original problem - seems related to #669, but not exactly the same. The same fix would be helpful in both cases, as @aarahvar2 suggests:...

## Relevant Code 1. Mouse press event for left click on node can have a few different modifiers applied (interested in `Alt` and no modifier events) https://github.com/talmolab/sleap/blob/219a60fad332afb047c2d000e8bf15abcd2b7674/sleap/gui/widgets/video.py#L1423-L1459 2. Update node...

This issue has been resolved in the new release - install SLEAP v1.2.7 [here](https://sleap.ai/installation.html#conda-package).

## Problem Analysis It seems we updated the `Predictor` base class with abstract methods while leaving `VisualPredictor` behind, namely `is_grayscale` and `_inititalize_inference_model` are the abstract methods that are not present...

Hi @Monnesee, Agreed, this is a very unpredictable feature especially when using SLEAP through the CLI. We originally introduced this bug in #768 when adding support to automatically generate analysis...

This issue has been resolved in the new release - install SLEAP v1.2.7 [here](https://sleap.ai/installation.html#conda-package).