Comments (5)
Hello sir,
I re-ran with the configurations provided by you on Python 2 and got the following output.
Training
Start training in minibatch mode...
Epoch 1.0000: train_ppl=370.9497 (words=5057, time=0-00:00:01)
Epoch 1.0000: test_ppl=249.1718 (words=5057, time=0-00:00:01)
Epoch 1.0000: best dev loss, writing model to /tmp/dev.mod
Evaluating
bleu: 0.0883409765451
wer: 0.903624733475
Epoch 2.0000: train_ppl=213.6305 (words=5057, time=0-00:00:05)
Epoch 2.0000: test_ppl=208.2777 (words=5057, time=0-00:00:05)
Epoch 2.0000: best dev loss, writing model to /tmp/dev.mod"
from xnmt.
The current idea is the following:
search_strategy returns the entire list of words (translated sentence) for a source sentence, which is sent to output for processing as a batch (array of array). The token iterator accesses the token ids in the batch. As you pointed out, the above error indicates the case of another dimension being added. But I am unable to reproduce it. Which version of Python is it? I haven't tested the pipeline on Python 3 yet. This was run on the current master branch.
from xnmt.
Hi,
This might be due to the change in a recent version of Numpy.
It apparently treats a single-element array as a scalar for the purposes of indexing. That would work against the above idea.
stack overflow
Can you please provide the version of Numpy you are using?
from xnmt.
Thanks for looking at this so quickly! Here is my info, it's the standard one I got from Anaconda, although the version of anaconda may be old...
(python2) gneubig@lor:~$ python
Python 2.7.13 |Continuum Analytics, Inc.| (default, Dec 19 2016, 13:46:45)
[GCC 4.4.7 20120313 (Red Hat 4.4.7-1)] on linux2
Type "help", "copyright", "credits" or "license" for more information.
Anaconda is brought to you by Continuum Analytics.
Please check out: http://continuum.io/thanks and https://anaconda.org
>>> import numpy as np
>>> print np.__version__
1.12.1
from xnmt.
@neubig, The error was being caused due to a change in output dimensions returned by concatenate function of the latest dynet. The latest version adds another dimension to the output. We reshape the output now.
from xnmt.
Related Issues (20)
- Search Strategies assume decoder supports calc_log_probs HOT 2
- Overabundance of forced decoding
- Stative Attenders HOT 3
- Post Processes on Dev/Test References HOT 1
- Recipe las-pyramidal.yaml does not work HOT 13
- @register_xnmt_event problems
- Problem while using SAAMSeqTransducer HOT 6
- Confusing error message when YAML file doesn't exist
- Output silently fails when path contains ~
- How to load an existing trained model and make predictions on the unseen data? HOT 1
- dy.sigmoid doesn't exist HOT 1
- Pyyaml Error when running example 19, subword sample
- how can I use for character-level sequences?
- Running 16_transformer.yaml: AssertionError: cannot pass dy.ParameterCollection to a Serializable class. HOT 1
- Segment fatal (core dump) using 3.8.0 HOT 1
- Problem running GPU version on RTX 2070 with 8GB Memory HOT 1
- How to train XNMT with datasets that do not fit in RAM? HOT 1
- How to use already tokenized BPE text and BPE vocab with xnmt ?
- Error when running experiments
- Can't run test/config/transformer.yaml
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from xnmt.