How to control the number of output images in the log directory when training on a custom model?

[Voyajer]

By default the images generated are based on their step count doubling each time for the first epoch, then for each subsequent epoch only the first step inputs and reconstructions are generated. Is there a way to change this behavior?

[chiexplorer]

You can adjust the frequency of output images using the 'batch_frequency' value, located at main.py->default_callbacks_cfg["image_logger"]["params"]["batch_frequency"]. Images will be logged when the batch index reaches an integer multiple of 'batch_frequency'. For more details, refer to the 'ImageLogger' class in main.py.