Where communities thrive


  • Join over 1.5M+ people
  • Join over 100K+ communities
  • Free without limits
  • Create your own community
People
Activity
  • May 05 2021 16:41
    guillaumekln transferred #580
  • May 05 2021 16:22
    hangcao1004 opened #580
  • Apr 16 2021 02:57
    raymondhs closed #400
  • May 29 2020 07:14
    guillaumekln closed #579
  • May 29 2020 07:14
    guillaumekln commented #579
  • May 28 2020 20:37
    Roweida-Mohammed edited #579
  • May 28 2020 20:36
    Roweida-Mohammed opened #579
  • Feb 19 2020 16:08
    codecov-io commented #578
  • Feb 19 2020 16:08

    guillaumekln on master

    Updating the intel-mkl URL. (#5… (compare)

  • Feb 19 2020 16:08
    guillaumekln closed #578
  • Feb 19 2020 16:08
    guillaumekln commented #578
  • Feb 19 2020 15:59
    arturgontijo opened #578
  • Feb 12 2020 17:58
    melindaloubser1 closed #553
  • Feb 12 2020 17:58
    melindaloubser1 commented #553
  • Dec 13 2019 08:43
    guillaumekln transferred #574
  • Dec 13 2019 08:43
    guillaumekln transferred #577
  • Dec 13 2019 08:14
    tkngoutham edited #577
  • Dec 13 2019 08:13
    tkngoutham opened #577
  • Dec 13 2019 06:37
    tkngoutham commented #574
  • Oct 09 2019 11:36

    guillaumekln on master

    Add CTranslate2 Change project cards title (compare)

Konstantin Glushak
@gsoul

I’m thinking that maybe “-size 32000” for learn_bpe.lua is too much?

Because in comments it say that -size option is not a vocabulary size, but rather:

[[The number of merge operations to learn.]]

Konstantin Glushak
@gsoul
@guillaumekln when I increased “-size” parameter of learn_bpe to 64000, I finally could collect my vocabulary of 32k tokens. While there were ~48k unique tokens in the corpora.
lpzreq
@lpzreq
Anybody tested nvidia Volt with OpenNMT? Hou much it faster than GTX 1080 Ti?
Guillaume Klein
@guillaumekln
@gsoul Can you try without -nparallel? I already trained models on OpenNMT-tf with joiners and there were no issues. On a side note, you should pass -tok_mode aggressive -tok_segment_numbers to learn_bpe.lua for consistency.
Konstantin Glushak
@gsoul
@guillaumekln I will try, thank you. And if there are any recommendations, could you please advise on proper “-size” parameter for learn_bpe.lua?
Guillaume Klein
@guillaumekln
30000 is frequently used.
Konstantin Glushak
@gsoul
The issue is that when I use it for the giga-gren corpora, I can’t get a 32k vocabulary. Only about 14k. Though maybe that’s because I didn’t apply -tok_mode to learn_bpe, but did it for all the other steps. I’ll try it once more, thanks again!
Ben Peters
@bpopeters
Is there an easy way to extract feature embeddings? extract_embeddings.lua is only giving me the word embeddings.
Ratish Puduppully
@ratishsp
Hi, I am trying to understand the decoding process in decoder.lua. I want to know why we iterate in the reverse direction in backward method for t = batch.targetLength, 1, -1 do
Guillaume Klein
@guillaumekln
@bpopeters, in extract_embeddings.lua instead of catching torch.type(m) == "onmt.WordEmbedding" you could catch all torch.type(m) == "nn.LookupTable", dump m.weight and recognize the feature based on the vocabulary size.
@ratishsp, this is the idea of the backward pass: to walk the graph in the reverse order.
Vincent Nguyen
@vince62s
Did you guys read this https://arxiv.org/pdf/1712.05690.pdf
Jean Senellart
@jsenellart
Yes - met with them too. Same algorithms, different scores. The benchmarks are not good presented like that... and we need to do something about this
Data Scientist
@JayKimBravekjh
Hi everyone. I joined this room first time today, nice to meet you all
Jean Senellart
@jsenellart
Hi @bravekjh - welcome
Vincent Nguyen
@vince62s
@jsenellart @guillaumekln don't know which commit messed the server, but read this: http://forum.opennmt.net/t/error-in-rest-translation-server-lua-105-attempt-to-index-field-preds-a-nil-value-500/1114
Jean Senellart
@jsenellart
looks like the last message says it is fixed
Vincent Nguyen
@vince62s
oh, never mind, confused she said she was on master ....
Data Scientist
@JayKimBravekjh
thanks @jsenellart
Vincent Nguyen
@vince62s
do we need Lua instead of Luajit for lua-sentencepiece ? (see OpenNMT/lua-sentencepiece#3)
Vincent Nguyen
@vince62s
what is the command line to detokenize with lua-sentenpiece ?
Guillaume Klein
@guillaumekln
You are using the sentencepiece hook, right? I think you just need to call tools/detokenize.lua with it.
Vincent Nguyen
@vince62s
but with hooks/sentencepiece in the line ?
Guillaume Klein
@guillaumekln
Yes.
Vincent Nguyen
@vince62s
ok
Guillaume Klein
@guillaumekln
If you are preparing your data offline, you could also directly use the sentencepiece project and not the Lua wrapper.
lpzreq
@lpzreq
Hi. Will be added the google encoder in CTranslate? If not, where i can read information about google encoder?
Guillaume Klein
@guillaumekln
Hello, there is no plan to add it. You should at least change the forward logic and maybe the model loading based on the GoogleEncoder class.
lpzreq
@lpzreq
oh. thanks (
lpzreq
@lpzreq
why you not plan add it? GNMT not good? :)
Vincent Nguyen
@vince62s
Has someone tried to use CUDA 9 with Torch / Lua OpenNMT ?
Guillaume Klein
@guillaumekln
@lpzreq It's not a priority to support custom encoders in CTranslate. But a PR is always welcome.
lpzreq
@lpzreq
Ok. Thanks.
Ratish Puduppully
@ratishsp
Hi, On OpenNMT I tried 'general' attention of Luong et al and 'concat' attention of Bahdanau et al. I get considerably worse results with concat. The task I am working on is a summarization one. What has been your experience on NMT using OpenNMT with the two attention options?
Guillaume Klein
@guillaumekln
Hello, how does the perplexity compare?
Ratish Puduppully
@ratishsp
The perplexity of concat is only slightly higher than that of general
Jean Senellart
@jsenellart
Hi @ratishsp, I found the same although the difference reduces for larger model.
Jean Senellart
@jsenellart
@vince62s - first unsuccessful try tonight CUDA 9 / torch. There some complaints on torch gitter about the same. Did you try?
Vincent Nguyen
@vince62s
no I read similar stuff, but on the other hand TF 1.5 is now distributed with binary compiled on cuda 9. So would be good to find a solution.
how do people do with new V100 then ?
Jean Senellart
@jsenellart
I am trying to narrow down - it seems to be coming from incompatibility with some other library.
Vincent Nguyen
@vince62s
I guess you tried this export TORCH_NVCC_FLAGS="-D__CUDA_NO_HALF_OPERATORS__"right ?
Jean Senellart
@jsenellart
yes - it was not the point
Ratish Puduppully
@ratishsp
Hi, how do we disable dropout during testing?
Guillaume Klein
@guillaumekln
Hello, it is disabled automatically.
Ratish Puduppully
@ratishsp
Thanks @guillaumekln.
chiting765
@chiting765
Hi~ I have a question about joiner annotate. There is a -tok_joiner_annotate option at learn_bpe.lua and a -joiner_annotate option at tokenize.lua. Do I need to turn on both to have the joiner in the tokenized files?
Jean Senellart
@jsenellart
@chiting765 - I think the one in learn_bpe is not important. It is just coming with all tokenization options
it does not change the bpe model