Comments (10)
Sorry, I have trouble increasing the accuracy recently.
Using different learning rate is just a trick I found useful sometimes.
My trouble now is the youtube-BB dataset. Due to the vpn's limit dosage, I can't download the dataset. And I'm trying to get the 0.3 EAO on VOT2015 without youtube-bb, but only 0.22 by now.
from siamese-rpn.
2, In the paper they say "Compared to ILSVRC [29] which consists of about 4,000 videos annotated frame-by-frame, Youtube-BB [25] consists of more than 100,000 videos annotated once in every 30 frames. " and the ILSVRC-VID dataset I used has about 4417 videos, so this may have no problem probably.
3, In my initial idea, I use the former 3 layers' weight in the model the paper's code provided. And leave the 4 and 5 layers inited by nn.init.kaiming_normal_. This will need some warm epochs training with small learning rate, and then with big learning rate.
4, This is to make the new boxes' center in the image.
from siamese-rpn.
Thanks a lot for your patent answer! I have gained more clear after your response.
However , can you show me more explanation about the third point or ,share some ref-links or paper birth to strengthen ? I'am very interesting in your idea ( a pretrained neural network ,joined with a initiate that replace its last layer, demand for multiple learning rates ). In my opinion , it's my first glance of
multiple learning rates in training period. maybe like TTUR
from siamese-rpn.
Your code's quality is so high that I can't wait to commit here again ,after reading your source code cautiously .
perfect work!
from siamese-rpn.
@HelloRicky123 How about using TrackinngNet which is released in ECCV2018 instead? It contains more videos than Youtube-BB.
from siamese-rpn.
hi, maybe you can use some ideas from object detection to improve your performance.
from siamese-rpn.
from siamese-rpn.
@HelloRicky123 How about using TrackinngNet which is released in ECCV2018 instead? It contains more videos than Youtube-BB.
But this will make it not fair when compared with the paper's code.
from siamese-rpn.
@HelloRicky123 How much time have you spend to train the model with ILSVRC(VID)?
from siamese-rpn.
About 150 image/s with two 1080Ti GPU.
from siamese-rpn.
Related Issues (20)
- Error: ModuleNotFoundError: No module named 'siamfc' HOT 2
- about youtube_BB dataset 111G
- Shouldn't bbox be 0-based before passing to crop method in imagenet data generation?
- I want to ask some question about the code in "net/dataset.py"? HOT 1
- evaluate on OTB100 , I get 0.6016 AUC
- The anchors seems to be wrong.. HOT 1
- I run your program and got only 0.1%AUC on OTB100 HOT 4
- About instance_size HOT 1
- AttributeError: 'NoneType' object has no attribute '__buffer__' HOT 1
- About run test_OTB.py !! HOT 6
- typeerror: expected str, bytes or os.pathlike object, not int HOT 1
- TypeError: a bytes-like object is required, not 'NoneType' HOT 2
- data HOT 2
- data lost
- The parameter amount of the model is larger than that of the original siameserpn? HOT 1
- The trained model has too low accuracy.
- A little confused in dataset HOT 1
- 从哪里找到算法跑完的结果,也就是txt文件
- Would you please upload the data to create lmdb to google drive and share it?
- 请问可以在Windows环境下训练吗? 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 siamese-rpn.