Issues with VSNeuromast Inference

[edyoshikun]

When I was testing this with Maddy I found two errors in the inference example.

1. The code only works if the dataset is preprocessed
2. The code executes a TensorboardLogger when it is not needed. We can just set Trainer(logger=False)
3. There are redundancies when running inference. We don't need to data_module.prepare_data() or set the prediction_dataloader(). Lightning will handle this.

[ziw-liu]

Which file are yo referring to?

[edyoshikun]

Here, I am referring to the examples VSNeuromast.

We should clarify that you need to run the preprocessing explicitly. You can't run the code with any other normalization other than NormalizedSampled. At least from the example Mady had setup. I'll try to replicate this when we update the script