Théo Trouillon

Same issue here.

I did a dirty fix by adding: `hparams.num_translations_per_input = flags.num_translations_per_input` `hparams.beam_width = flags.beam_width` in nmt.py, in `run_main(.)` just after `hparams` is loaded, it works just fine.

Go ahead :) Though it should probably be something cleaner and more general (to pass other unpassed parameters too) than what I proposed.

Same here, I would like to get each alignment map for each of the top-k translations when beam search is activated, is this planned any time soon? If not, what...

@oahziur Ok thanks for the precisions, is there an already existing branch working on beam_search and alignment_history compatibility that I can follow/contribute?

@oahziur Looks like beam_search and alignment_history compatibility issue will soon be [resolved and merged](https://github.com/tensorflow/tensorflow/pull/13312)

I do use a beam search decoder too, and also with num_translations_per_input > 1, I am quite interested in getting the alignments too. Can you point us to where to...

So I had a look at the way the TextVectorization object does the padding ( https://github.com/keras-team/keras/blob/v3.8.0/keras/src/layers/preprocessing/text_vectorization.py#L568 ). It transforms the input into a `RaggedTensor` (through the call to `tf.strings.split` in...

Hi @mehtamansi29, Thank you for digging into this. Indeed it works with enough iterations, but validation accuracy stalls at 0.5 for about 10 iterations, which is strange, and was not...

I just realized I couldn't edit your gist, [here](https://colab.research.google.com/gist/ttrouill/592b95720991fe258102e739e782f213/text_classification_from_scratch.ipynb) is a copy that only adds `go_backwards = True` to the first layer, and the corresponding output. Edit : I updated...