Comments (12)
OIC.. the random effect seems to be due to the Dropout.
from sequence_tagging.
You're right, there is no shuffling anywhere. Randomness surely comes from dropout + initialization. However, if you carefully control the random seeds, you should get non-random convergence!
from sequence_tagging.
Thanks so much. Although simply setting the random state does not work, I found a page here regarding the exactly the same question.
I will have a try!
from sequence_tagging.
maybe you should also set python's random seed fixed
from sequence_tagging.
It seems that even if I set dropout=1, the results are still changing.
from sequence_tagging.
@lovejasmine i have tried but not effective...: (
from sequence_tagging.
I tried use different tf random seed and I found that the results are very different than before.
Thus, it seems that setting random seed is effective to some extent but cannot keep the results 100% exactly the same. I guess it maybe due to the multi-thred thing.
It seems that the tensorflow is often complained by users about the random state stuff..
from sequence_tagging.
Have you tried running it on CPU on a subset of the dataset with a batch of size 1 with dropout = 1? I'm not too familiar with tf random seeds, and the stackoverflow post you refered above seems to mention some pretty weird behavior. Batch size = 1 could alleviate the problem they're mentioning.
from sequence_tagging.
@yuchenlin maybe this help: https://stackoverflow.com/questions/38469632/tensorflow-non-repeatable-results
from sequence_tagging.
@yuchenlin did you make progress on this issue? Should we keep it open or should we close it?
from sequence_tagging.
@guillaumegenthial sorry for the delayed reply! I was busy doing other stuff. Yes, I guess we can close it. It seems that the current methods are difficult to maintain the stable results under the GPU settings. Thanks!
from sequence_tagging.
@yuchenlin no problem! I'll close it, but I must confess that this is an interesting issue and I'd love to hear more about it if you find the answer one day.
from sequence_tagging.
Related Issues (20)
- recipe for target 'run' failed HOT 4
- Unicode Decode Error HOT 2
- Prediction shows I-LOC without B-LOC HOT 2
- how to shuffle batches with the iterator? HOT 1
- The loss depends on the max length of sequence in a batch, which should not be the case. HOT 1
- Extraction of specific expressions HOT 2
- Char Embedding Error HOT 2
- Huge error on prediction (NER) HOT 1
- how to get the input and output nodes of the model HOT 1
- How to get or create 'data/glove.6B/glove.6B.300d.txt'? HOT 6
- How to improve precision by this model?
- Not mentioned <start>、<end> token
- How to evaluate the precision, recall and F1-value of the code?
- KeyError: 'O' makefile:7: recipe for target 'run' failed HOT 1
- what is the difference between self.word_embeddings with tf.nn.dropout and without it
- Saving the model weights in TF 2
- F1 score of all custom named entity
- How can I get eng.testa.iob?
- Why use training, validation and test set to build vocabulary in build_data.py ? Isn't it information leak ?
- Code snippet for tensorflow 2.x
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 sequence_tagging.