Comments (2)
When using a dictionary generated by BPE-processed data, the following error occurred, but there is no problem when using a dictionary generated from data that has not been processed by BPE, how should I modify it?
Traceback (most recent call last):
File "train.py", line 83, in
train(config)
File "train.py", line 18, in train
du.load_vocab()
File "/home/sxq/NMT_GAN-master/utils.py", line 56, in load_vocab
self.src2idx, self.idx2src = load_vocab_(self.config.src_vocab, self.config.src_vocab_size)
File "/home/sxq/NMT_GAN-master/utils.py", line 43, in load_vocab_
vocab = [line.split()[0] for line in codecs.open(path, 'r', 'utf-8')]
IndexError: list index out of rangeLooking forward to your reply.
Sorry to bother you,I want to know how you got those BPE-processed datas,by Sennrich‘s subword-nmt?If so,how do you map the generated files to the file paths in these yamls? For example,I have no idea how this file named “target.bpe.txt.vocab.34432” came from.
I would appreciate to receive your reply.
from nmt_gan.
同问。。。。
from nmt_gan.
Related Issues (20)
- Preprocessing of en2de data HOT 4
- InvalidArgumentError: Assign requires shapes of both tensors to match.
- Clarification on files in config_gan_train.yaml HOT 5
- How to get the vocab files? HOT 7
- Dropout HOT 1
- NoneType HOT 2
- file not found HOT 1
- the g_loss in function gan_output (in model.py) HOT 1
- Hi,Where is the training data? Thanks.
- Mistake in vocab.py?
- How to get the dis_negative_data in the config_discriminator_pretrain.yaml? HOT 2
- dis_saveto HOT 10
- Can't find data
- GAN training is too slow.
- dis_negative_data HOT 2
- the Adversal training is very very very slow!!!!
- About discriminator
- Nmt GANs
- Training data size for the generator and discriminator HOT 1
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 nmt_gan.