Comments (11)
Pair loss is worse and vseattmodel gives worse result too.
from disccaptioning.
thats very common in the first several epochs. Try training it a little bit longer. Or just restart the training.
from disccaptioning.
ok, thanks a lot, for another VSE model(VSEAttModel) and "pair loss" , whose result isn't shown in your paper "Discriminability objective for training descriptive captions" in CVPR 2018?
from disccaptioning.
thanks!if the retrieval model perform better(like the paper“Stacked Cross Attention for Image-Text Matching”),can we get a better result for captioning model?
from disccaptioning.
I think it's very likely.
from disccaptioning.
hello,luo
It's my result of pre-training retrieval model after i run “run_fc_con.sh”, there is still a difference with your result presented in your paper for the retrieval model.
Result:
Average i2t Recall: 53.9
Image to text: 29.9 59.2 72.6 4.0 19.6
Average t2i Recall: 42.3
Text to image: 20.6 46.5 59.8 7.0 40.8
from disccaptioning.
Did you download my pretrained model? Does it perform better and the same as what's reported in the paper?
https://drive.google.com/open?id=1oQ_O-O2KoSQv1xdBPKaIOGt-VW0gS-42
These are my training curves, to give you a hint.
from disccaptioning.
i might get the problem,i have used the size of 7x7 for coco fc features, i think u have used 14x14 for coco fc features?
from disccaptioning.
fc feature doest have spatial dimensions, it's a vector
from disccaptioning.
I found other paper use Karpathy'split for COCO, your paper use rama's split, whose test data are the same? why you can compare your result with the result in self-critical?
from disccaptioning.
the splits are different. The self critical one is my implementation on Rama's split. Using Rama split I'd because we need to compare ours to Rama's result.
from disccaptioning.
Related Issues (20)
- ValueError: sampler should be an instance of torch.utils.data.Sampler HOT 1
- att_masks HOT 2
- Similar work
- 关于每张图片使用几个句子 HOT 1
- Which are the negatives for the retrieval model. HOT 1
- What's the difference between Rama's split and Karpathy's split? HOT 1
- How to train on TopDown model?
- Training curve of reinforcement learning
- python: can't open file 'scripts/prepro_ngrams.py': [Errno 2] No such file or directory HOT 4
- when bash run_att_d.sh ,it broke HOT 13
- f30k-caption? HOT 4
- FileNotFoundError: [Errno 2] No such file or directory: 'cider/data/cocotalk_fc\\391895.npy Terminating BlobFetcher HOT 2
- Traceback (most recent call last): File "train.py", line 250, in <module> train(opt) File "train.py", line 163, in train if opt.evaluation_retrieval: AttributeError: 'Namespace' object has no attribute 'evaluation_retrieval' Terminating BlobFetcher HOT 4
- Make sure the vse opt are the same !!!!! HOT 2
- IOError: Failed to interpret file 'data/cocotalk_fc/100000.npy' as a pickle. HOT 7
- how come evaluation result is very bad, Bleu_4 is 0.000, Meteor is 0.009 . BTW, how to generate caption on customized dataset HOT 4
- infos_att_d1.pkl HOT 1
- Issues in FCModel HOT 2
- Unable to download pretrained models HOT 4
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 disccaptioning.