Comments (5)
Dear @aemrey,
thanks for your interest in our code. From what you mention, it seems that the RL training part has not even started so it is fairly normal that you are getting lower results. Please keep it running until the training stops by itself.
Lorenzo.
from meshed-memory-transformer.
Hi @aemrey, I'm following your steps and right now I'm extracting the features of my set of images. I'm using this model loaded with these weights.
Now, how do you pack those features into an Nx2048
tensor? I understood "features" by the output of the blob cls_prob
here, but it returns an Nx1601
tensor. I'm sure I'm missing something here, maybe not taking the correct blob or using the wrong model.
Thanks!
P.S.: Don't know if I should maybe open a new issue
EDIT: Well, I understand now that I should take the blob res5c
, maybe? Though the output is Nx2048x14x14
, so don't really know what to do with those 14x14. And still I guess I need the cls_prob
to sort the array.
I'll keep updating, but if you see something odd on what I'm doing and have a quick hint, please let me know.
EDIT2: Moved to #7
from meshed-memory-transformer.
I ran a couple of times your code.
The test cider is always below 1.30. Any clues?
from meshed-memory-transformer.
Hi @ruotianluo,
thanks for your interest in our work.
We noticed that the results and the training behavior can be slightly different by changing the underlying architecture. For this reason, we also provided the weights of our final model.
In our experiments, we used an NVIDIA 2080 Ti GPU. The other settings are the ones we reported in our repository.
from meshed-memory-transformer.
I ran a couple of times your code.
![]()
The test cider is always below 1.30. Any clues?
I think it caused by the difference between bottom-up features provided in [1] and provided in this project. The testing results shown in , the curve named m2_transformer_wan used the features provided in [1] and the curve named m2_transformer_wan n used the features provided in this project.
I compare the features of [1] and this project , and find numbers of box in some image_id are different.
from meshed-memory-transformer.
Related Issues (20)
- Problems during operation
- memory
- About Rl training
- RuntimeError: gather(): Expected dtype int64 for index, in beam_search/beam_search.py, line 26, in fn HOT 1
- FileNotFoundError: [Errno 2] No such file or directory: 'java' HOT 2
- About Online Evaluation
- no file found
- FileNotFoundError: [WinError 2] 系统找不到指定的文件。 HOT 6
- Ensemble problem
- Vocabulary of the test split
- Test on Custom Dataset HOT 1
- Beam search error HOT 3
- coco_detections.hdf5
- OSError: [Errno 24] Too many open files
- Hello, I would like to ask myself where is the description of the output generated by the model? HOT 1
- incomplete captions generated! HOT 1
- Features extracted from the flickr30k dataset
- "Error when running model: TypeError: 'generator' object is not callable" HOT 1
- OSError: [Errno 22] Invalid argument
- 关于cider得分的问题
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 meshed-memory-transformer.