Comments (9)
from rmn.
one of the training tensorboard logs is as follows:
as illustrated in the picture, the light blue line represents one of the training records on msr-vtt dataset.
the output results :
BEST CIDEr(beam size = 2):
Bleu_1: 78.28
Bleu_2: 64.51
Bleu_3: 51.30
Bleu_4: 39.55
METEOR: 27.52
ROUGE_L: 59.84
CIDEr: 46.22
and the deep blue line is the training record that i executed the project again on msr-vtt without random seed settings yesterday
the later might be better than the former.
from rmn.
Hi! Does the latter one finishes training?
from rmn.
hi Ganchao!
thanks for ur attention to the training process.
the training is not over yet.
it will take 2 more days to finish all epochs.
so far, its logs is as follows:
it seems like better than before.
could i stop training and evaluate it now? is it appropriate to do so?
from rmn.
hi, Ganchao!
the result of the latter experiment is as follows:
BEST CIDEr(beam size = 2):
Bleu_1: 79.03
Bleu_2: 65.13
Bleu_3: 51.72
Bleu_4: 40.05
METEOR: 27.88
ROUGE_L: 60.12
CIDEr: 46.59
BEST METEOR(beam size = 2):
Bleu_1: 79.63
Bleu_2: 65.68
Bleu_3: 52.00
Bleu_4: 40.06
METEOR: 28.07
ROUGE_L: 60.50
CIDEr: 47.36
and the logs screenshot is as follows:
while the cider value is further improved in best-meteor epoch, there is still a gap to achieve the 49.6.
looking forward to your insights on the experiment, thanks!
from rmn.
What is the training batch size in your experiments? For msr-vtt, the best result I got is in the setting:--learning_rate=1e-4 --learning_rate_decay --learning_rate_decay_every=5 --learning_rate_decay_rate=3 --hidden_size=1300 --train_batch_size=48.
The results are as follows:(save 8 times for one epoch here)
BEST CIDEr(beam size = 2):
Bleu_1: 80.51
Bleu_2: 67.49
Bleu_3: 54.40
Bleu_4: 42.54
METEOR: 28.43
ROUGE_L: 61.62
CIDEr: 49.60
from rmn.
hi, Ganchao!
the training batch size set in all of my experiments is 8 due to gpu memory limitation.
so the key is the model performce will be affected by distinct batch size settings.
and would it be convenient for u to share the batch size settings for msvd dataset?
thanks for ur sincere sharing and generous help!
from rmn.
We set batch size to 32 for MSVD
from rmn.
hi, Ganchao~
i got it.
thanks again!
from rmn.
Related Issues (20)
- hi! would like to know how to resolve the following issue
- hi! would like to know how to get these
- the mismatch error happened when using the pretarined model you provide. HOT 5
- a bug report HOT 4
- TypeError: h5py objects cannot be pickled
- Spatial Feats HOT 3
- What's the range of cider score?
- POS
- The link of visual and text features cannot be opened HOT 1
- a problem about region_feature file HOT 3
- A refinement report
- text feature processing HOT 1
- Would I ask one question?
- When I tried to run evaluatie.py it reported the function incorrectly HOT 2
- a problem about msr-vtt_model.pth HOT 1
- a problem about sample.py
- a problem about features HOT 2
- problems about feature extraction models
- Problem about Feature Extraction 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 rmn.