Comments (3)
Hello, thank you for your great work, but I have some questions.
1、In engine.py, I see some state "on_start_epoch, on_sample, on_end_epoch, on_test_sample", but they only appear once, I can't figure out what's their function, can you explain it?
2、I see you set MAX_EPOCH to 100, but I find the performance on test set has not improved obviously since around 20 epochs, more epochs only improve the performance on training set. Do you have the same situation during your taining time?
- "on_start_epoch, on_sample, on_end_epoch, on_test_sample" are not called in our code. We leave it here for debug usage.
- For some dataset, the answer is yes. We use a large MAX_EPOCH to ensure our model can achieve the best performance under different datasets.
from 2d-tan.
Hello, thank you for your great work, but I have some questions.
1、In engine.py, I see some state "on_start_epoch, on_sample, on_end_epoch, on_test_sample", but they only appear once, I can't figure out what's their function, can you explain it?
2、I see you set MAX_EPOCH to 100, but I find the performance on test set has not improved obviously since around 20 epochs, more epochs only improve the performance on training set. Do you have the same situation during your taining time?
- "on_start_epoch, on_sample, on_end_epoch, on_test_sample" are not called in our code. We leave it here for debug usage.
- For some dataset, the answer is yes. We use a large MAX_EPOCH to ensure our model can achieve the best performance under different datasets.
Thank you for your reply and I have another question to bother you.
The results you show "[email protected] | [email protected] | [email protected] | [email protected] | [email protected] | [email protected]" are from the same checkpoint or you choose the highest score from different checkpoints respectively?
If the answer is the former, you know there may be no such as a checkpoint reach highest scores on all metrics, (e.g. some checkpoint may have higher [email protected] score but have lower [email protected] score), I didn't see you set a rule to stop training in your code, you just train for MAX_EPOCH to get all checkpoints, what's your criterion to choose an appropriate checkpoint to report?
from 2d-tan.
Hello, thank you for your great work, but I have some questions.
1、In engine.py, I see some state "on_start_epoch, on_sample, on_end_epoch, on_test_sample", but they only appear once, I can't figure out what's their function, can you explain it?
2、I see you set MAX_EPOCH to 100, but I find the performance on test set has not improved obviously since around 20 epochs, more epochs only improve the performance on training set. Do you have the same situation during your taining time?
- "on_start_epoch, on_sample, on_end_epoch, on_test_sample" are not called in our code. We leave it here for debug usage.
- For some dataset, the answer is yes. We use a large MAX_EPOCH to ensure our model can achieve the best performance under different datasets.
Thank you for your reply and I have another question to bother you.
The results you show "[email protected] | [email protected] | [email protected] | [email protected] | [email protected] | [email protected]" are from the same checkpoint or you choose the highest score from different checkpoints respectively?
If the answer is the former, you know there may be no such as a checkpoint reach highest scores on all metrics, (e.g. some checkpoint may have higher [email protected] score but have lower [email protected] score), I didn't see you set a rule to stop training in your code, you just train for MAX_EPOCH to get all checkpoints, what's your criterion to choose an appropriate checkpoint to report?
Results are from the same checkpoint. For activitynet, we choose the checkpoint with highest [email protected] on validation set. For tacos and charades, we choose the highest [email protected] on testing set, since validation sets are not provided.
from 2d-tan.
Related Issues (20)
- [SeqTrack] The performance on NFS are lag then paper report HOT 3
- [sqetrack]The target has disappeared, but the model still has predicted results. How to solve it? HOT 1
- [seqtrack]The number of template? HOT 2
- 请问一下这套框架下如何测试NFS?
- 我自己训练的时候,iou一直是nan,正常吗?
- 请问batchsize设置成40 训练多少个epoch比较合适呢?
- [X-CLIP] SampleFrames possible wrong arguments?
- [SeqTrack] vot-rank diagram
- [SeqTrack]seed HOT 1
- [X-CLIP] Some errors related about cuda during runtime
- Draw Figure
- 关于模型参数量问题
- [SeqTrack] How does the SeqTrack model determine when targets disappear?
- [SeqTrack] High memory usage
- VOT很差的性能 Poor performance of VOT
- 在线模板更新代码
- 【SeqTrack】如何测试自己的视频数据?
- Implementation method of heatmap visualization (as shown in Figure 6 of the ARTrack paper
- evaluation issues HOT 1
- Confusion about zero-shot
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 2d-tan.