Comments (3)
sujoyp
commented on June 7, 2024
Not sure if this is resolved. Could you please try backtracking through the code to see what is causing the problem? I do not recall getting NaNs in mAP.
from wtalc-pytorch.
yhZhai
commented on June 7, 2024
Hi, have you solved this issue? I encountered the same problem, particularly, the detection IoU and training loss became nan after about 1000 iterations. And I used the following parameter to run:
--dataset-name ActivityNet1.2 --num-class 100 --max-seqlen 3000 --model-name anet1.2 --batch-size 16
from wtalc-pytorch.
yhZhai
commented on June 7, 2024
hi, when I train on ActivityNet v1.2. the I got mIOU is nan.
how to solve the problem?
Hi, I solved this problem. This is because thumos14 used validation set to train, while activitynet used training set to train. So you have to change the subset name in detectionMAP.py (maybe some other files).
from wtalc-pytorch.
Related Issues (20)
- The model results vary greatly HOT 1
- I believe labels_all.npy is wrong HOT 1
- About Qualitative Results
- difference between labels.npy and labels_all.npy HOT 1
- Both Classification and Localization Performance is higher in my experiment than your eccv18 paper in Thumos14 HOT 4
- Specific parameter setting when training on activityNet v1.2 HOT 5
- How can i extract the feature by myself？ HOT 1
- RuntimeError: The size of tensor a (101) must match the size of tensor b (20) at non-singleton dimension 1
- Visualization
- FPS of ActivityNet?
- Could you provide the pre-trained encoder?
- Regarding feature extraction HOT 2
- Can you share the UntrimmedNet feature for ActivityNet1.2
- regarding result
- Specific composition of features HOT 1
- calculate features HOT 13
- features download HOT 4
- overfitting HOT 1
- extracted_fps of Thumos14reduced-I3D-JOINTFeatures HOT 3
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 wtalc-pytorch.