Where communities thrive


  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
People
Repo info
Activity
    Guillaume Klein
    @guillaumekln
    Not sure. Users have often very different requirements. I prefer making the code easily extensible than adding more options.
    Stergiadis Manos
    @steremma
    :+1:
    Anna Samiotou
    @annasamt
    image.png
    Hello, does the "train_alignments" work in opennmt-tf v2? when I add it in the config file (under data) I get this error :
    When I comment it out, training runs fine. Thanks in advance
    Guillaume Klein
    @guillaumekln
    Hi, most likely there is a mismatch between your alignment file and your training file. Can you check for any error?
    Anna Samiotou
    @annasamt
    I checked but I see no error. This is a test train with 100 source and 100 target segments (in separate files), transformer model, sentencepiece, mixed precision. As for the alignments, I have used the OpenNMTTokenizer in conservative mode to tokenize them, pasted source/target with " ||| " delimiter, and run fast_align to produce the pharaoh format. The alignment file also comprises 100 lines.
    Anna Samiotou
    @annasamt
    Possibly the error lies on the different tokenization methods i.e. that the alignment (by fast_align) was run on the (same) training files but tokenized by OpenNMTTokenizer (conservative) while the training files, for training the model, are sent as raw text to sentencepiece inside OpenNMT-tf. Any ideas on this?
    Guillaume Klein
    @guillaumekln
    The alignment model should be trained on the tokenized training files.
    Anna Samiotou
    @annasamt
    I understand. The thing is that tokenization of training files happens on-the-fly inside OpenNMT-tf which is more straightforward in my case, because when I do it offline, 1) I have to then de-tokenize myself 2) for protected tokens inside the ｟｠ I get funny encoding for these special parenthesis as we have previously discussed in http://forum.opennmt.net/t/issue-with-special-character-u-ff5f/2965/5
    Guillaume Klein
    @guillaumekln
    If you want to train with alignments you would need to tokenize offline. Did you look into using the OpenNMT Tokenizer directly? It is fast and have a convenient Python API. There should not be any encoding issues.
    Anna Samiotou
    @annasamt
    Thanks, I will look into it. So to clarify furher: 1) to train an NMT model with alignments, for the alignment I have to use the same type of tokenization that I do for the training, but I need to do it offline 2) For the training can I still keep the online tok method? or do I have to use the (offline) tokenized files? 3) Finally, does the same apply for word embeddings, if I want to train with embeddings as well?
    Guillaume Klein
    @guillaumekln
    1) Yes.
    2) You could still use the online method but since your already tokenized the files it's probably better to reuse them.
    3) Yes. You want your pretrained embedding vocabulary to cover your training vocabulary.
    Anna Samiotou
    @annasamt
    Many thanks for the support!
    Anna Samiotou
    @annasamt
    One more doubt: suppose I use the offline tokenized files for the training. For inference, could I use the online tokenization (with the same tok method, obviously) to avoid tokenizing source and detokenizing the prediction? If yes, how to specifiy this ( that is, applying tok only to infererence) in the config.yml file? Could I specify "source_tokenization:" under "infer:" ?
    Guillaume Klein
    @guillaumekln
    Mmh good question. Right now if you configure the tokenization in the YAML file it will apply it for all files: training, evaluation, and test.
    You could however define the tokenization configuration in a separate file and use it only for inference using the Multiple configuration files approach
    Anna Samiotou
    @annasamt
    @guillaumekln Mmm, I thought so; and the online tokenization is sooo handy. Anyway, we can't have it all, I suppose. If training with alignments and/or word embeddings improves the system performance I guess it is worth the extra effort.
    @guillaumekln Ah, OK, good point! I will try the multiple config option for inference. Thanks!
    Rahaf Alnajjar
    @MaryaAI
    Hi,
    I used to run OpenNMT-tf on GPU and
    Now I want to run it on CPU, Are there any restriction on that?? Does it work on CPU?
    Guillaume Klein
    @guillaumekln
    Hi, yes it works on CPU. It is just slower.
    Anna Samiotou
    @annasamt
    Hi, to run opennmt-tf inference on CPU only, do we use the model as such or is there a release option as in lua? Or is it enough to specify in the inference command --num_gpus 0?
    Guillaume Klein
    @guillaumekln
    If there is no GPU on the system, it will automatically use the CPU. There is no specific option.
    Anna Samiotou
    @annasamt
    So if the system does have at least one GPU there is no way to use CPU-only for the inference, right?
    Guillaume Klein
    @guillaumekln
    You can set the environment variable CUDA_VISIBLE_DEVICES, e.g. CUDA_VISIBLE_DEVICES= onmt-main ...
    Anna Samiotou
    @annasamt
    OK, I'll try using this env var without a value this time. Thx
    Also if the OpenNMT-tf model v2x is trained on GPU, can inference still be run on CPU-only?
    Guillaume Klein
    @guillaumekln
    Yes, checkpoints do not include any information regarding the training device.
    Anna Samiotou
    @annasamt
    OK great
    image.png
    I have a different question: While training, with omnt-tf v2x, I get this message in the log which does not hinder the training , however I wonder about its meaning/consequencies. Any idea?
    I read that this is probably due to the fact that the number of iterations performed on the dataset is greater than the number of batches in the dataset. Is this a problem? Or should I ignore the message?
    Guillaume Klein
    @guillaumekln
    You should ignore this message. It just means that we finished iterating on the dataset.
    Anna Samiotou
    @annasamt
    Thx
    newger
    @newger18
    Hi, @guillaumekln, I meet the same problem that @emesha92 mentioned. The GPU utils is very low，most of the time 0%. sample_buffer_size is 500000, gpu num is 8, Accumulate gradients of 2 iterations to reach effective batch size of 25000. I wonder if the preparation of data is too slow?
    Rahaf Alnajjar
    @MaryaAI
    @guillaumekln thanks
    Rahaf Alnajjar
    @MaryaAI
    I have another question, I want to save the output of translation to txt file but the documentation mentions that "The predictions will be printed on the standard output." and the output is printed as cell output on google colab any suggestion to that issue?
    Guillaume Klein
    @guillaumekln
    @MaryaAI See the command line option --predictions_file. Alternatively you can also redirect the standard output to a file with >.
    @newger18 This sounds odd. Are you training a Transformer model? What is the reported "words per second"?
    Rahaf Alnajjar
    @MaryaAI
    Thanks so much! @guillaumekln
    last question, If I want to change configuration. Can I put all configuration in data.yml ?? like this?
    "!onmt-main --model_type Transformer --config data.yml --auto_config train --with_eval"
    In this way it will take auto config or the configs in my data.yml file?
    Guillaume Klein
    @guillaumekln
    It will take both, but the values defined in the user YAML configuration takes priority over the automatic configuration.
    Rahaf Alnajjar
    @MaryaAI
    Thank you for your guidance
    sergei-from-vironit
    @sergei-from-vironit
    Hello i try to train TransformerBig model. WARNING:tensorflow:It seems that global step (tf.train.get_global_step) has not been increased. Current value (could be stable): 5008 vs previous value: 5008. And get warning You could increase the global step by passing tf.train.get_global_step() to Optimizer.apply_gradients or Optimizer.minimize.
    What can be it?
    Guillaume Klein
    @guillaumekln
    This is just warning as a consequence of gradient accumulation (TensorFlow thinks we forgot to increase the training step). I suggest upgrading to V2.
    Milad Nozari
    @mnvoh
    Hello guys. Has anyone successfully used a trained onmt model in GoLang?
    Milad Nozari
    @mnvoh
    OK, so I resolved most of my issues and even got the output, but here's the thing. Apparently TF's bindings for Go doesn't support/implement GatherTree which means I have to set beam_width to 1 when exporting my model. The thing is that the result of beam_width set to 1 is utter nonsense compared to when beam_width is set to say 5.
    Any suggestions/tips/resources would be appreciated. Thanks
    Guillaume Klein
    @guillaumekln
    Yeah that's a limitation. I think the TensorFlow team is working on enabling dynamic loading of custom ops (such as GatherTree). In the meantime, you should get usable output with greedy search by training longer/on more data.
    Milad Nozari
    @mnvoh
    @guillaumekln Thanks for the answer man. Actually I'm at 10k steps of training, but you saying that reaching the end of training makes it better was a relief, because I was thinking about implementing GatherTree myself, which not only is beyond my expertise, I was afraid that that wasn't the only operation missing from Go's bindings.