Stack Overflow
Stack Overflow

Questions tagged [opennmt]

38 questions
13
votes
2 answers

UserWarning: Implicit dimension choice for log_softmax has been deprecated

I´m using Mac OS el capitán and I am trying to follow the quick start tutorial for OpenNMT pytorch version. In the training step I get the following warning message: OpenNMT-py/onmt/modules/GlobalAttention.py:177: UserWarning: Implicit dimension…
secuaz
  • 459
  • 3
  • 6
  • 15
7
votes
6 answers

Error in training opennmt - caffe2_detectron_ops.dll not found

I have torch 1.6 and python 3.8. When training OpenNMT, it throws the following error - OSError: [WinError 126] The specified module could not be found. Error loading…
girishnjha
  • 81
  • 1
  • 3
4
votes
2 answers

Tensorflow "Transformer model for language understanding" with another Dataset?

I have been reading the official guide here (https://www.tensorflow.org/text/tutorials/transformer) to try and recreate the Vanilla Transformer in Tensorflow. I notice the dataset used is quite specific, and at the end of the guide, it says to try…
Dametime
  • 581
  • 1
  • 6
  • 23
3
votes
1 answer

how convert string to path in opemnmt-py

I use opennmt-py for MT and in the code any time I want to set a path I have to write all directory and it's not good looking when I have long directory. is there any way to set a string as the main directory and just add the file name to the end. I…
zana saedpanah
  • 324
  • 3
  • 12
3
votes
2 answers

How to install torch audio on Windows 10 conda?

In Anaconda Python 3.6.7 with PyTorch installed, on Windows 10, I do this sequence: conda install -c conda-forge librosa conda install -c groakat sox then in a fresh download from https://github.com/pytorch/audio I do python setup.py install and…
Lars Ericson
  • 1,952
  • 4
  • 32
  • 45
3
votes
1 answer

Lua and Torch issues with GPu

I am trying to run the Lua based program from the OpenNMT. I have followed the procedure from here : http://forum.opennmt.net/t/text-summarization-on-gigaword-and-rouge-scoring/85 I have used the command: th train.lua -data textsum-train.t7…
Jaffer Wilson
  • 7,029
  • 10
  • 62
  • 139
2
votes
1 answer

(OpenNMT) Spanish to English Model Improvement

I’m currently trying to train a Spanish to English model using yaml scripts. My data set is pretty big but just for starters, I’m trying to get a 10,000 training set and 1000-2000 validation set working well first. However, after trying for days, I…
Jose Chavez
  • 115
  • 9
2
votes
1 answer

Trouble with OpenNMT Toy Example (Python3.9)

I recently installed OpenNMT but getting the following error when going through the toy example. I have macOS Big Sur 11.2.1 I have python2.7 and python3.9 installed. pip install --upgrade OpenNMT-py==2.0.0rc1 wget…
Jose Chavez
  • 115
  • 9
2
votes
0 answers

Issue: Using TPU with OpenNMT-tf

I am trying to use free Google Colab TPU with OpenNMT-tf, it is an open source ecosystem for neural machine translation and neural sequence learning built on top of Tensorflow. TPU is not implemented yet, so I am trying to do that. I have created a…
Daniel abzakh
  • 430
  • 5
  • 10
2
votes
1 answer

Change source input from file to string in th translate.lua

I am new to lua and I am wondering if I can send on the translate.lua -src a string and not a file where the string exists. I have searched a lot before posting but I could not manage to find something similar. My main problem is that Machine…
tsiro
  • 2,323
  • 3
  • 24
  • 46
2
votes
1 answer

Explicit tensorflow session gives fetch error in Tensorflow/nmt

This kind of tf.session works fine: with tf.Session(graph=self.infer_model.graph, config=utils.get_config_proto()) as sess: loaded_infer_model = model_helper.load_model(self.infer_model.model, self.ckpt, sess, "infer") But I have to keep…
jolly
  • 3,353
  • 1
  • 15
  • 21
2
votes
1 answer

OpenNMT-py low BLEU scores for translators to German

I've trained OpenNLP-py models from English to German and from Italian to German on Europarl and I got very low BLEU scores: 8.13 for English -> German and 4.79 for Italian -> German. As I'm no expert in NNs (yet), I adopted the default…
Alberto
  • 597
  • 3
  • 17
1
vote
0 answers

RuntimeError: Found no NVIDIA driver on your system during docker build

I am trying to build a docker image that can use GPU for DeepLearning models. The problem is that I am getting this issue when trying to build the image RuntimeError: Found no NVIDIA driver on your system. Please check that you have an NVIDIA GPU…
nikita grygoryev
  • 11
  • 1
1
vote
1 answer

How to calculate the number of epochs based on the size of training dataset, batch_size and the number of training steps?

I am new to ONMT, and am a bit confused about the number of epochs and training steps. I know the number of epochs is the number of times that we iterate through the training dataset, but how can I calculate the number of epochs that I trained my…
azLe
  • 19
  • 3
1
vote
1 answer

What are the differences between BLEU score and METEOR?

I am trying to understand the concept of evaluating the machine translation evaluation scores. I understand how what BLEU score is trying to achieve. It looks into different n-grams like BLEU-1,BLEU-2, BLEU-3, BLEU-4 and try to match with the human…
Exploring
  • 2,493
  • 11
  • 56
  • 97
1
2 3