PhilLint

mean std value for LAB/YCbCr normalization

1

With regards to the mean and std values required for normalization: How do the values arise for LAB and YCbCr respectively? My assumption was, that the training images were transformed...

The current version does not support (big) transformer models from the Tatoeba Challenge provided on hugging face (https://huggingface.co/Helsinki-NLP/opus-mt-tc-big-fi-en), right? If not, do you plan to add those? This seems important...