Comments (4)
@JunqiaoLi Hi, I haven't met with this before. Perhaps you could run a sanity check to see where these two functions are different? According to my memory, they should perform the same on a short video clip (e.g. 3 frames) under the setup of multi-frame detection (multi-frame detection as in here).
from pf-track.
@JunqiaoLi Hi, I haven't met with this before. Perhaps you could run a sanity check to see where these two functions are different? According to my memory, they should perform the same on a short video clip (e.g. 3 frames) under the setup of multi-frame detection (multi-frame detection as in here).
Hi, let me describe my operation in detail:
- The model that I use is your f3_fullres_all model.
- I use test.py and forward_test to evaluate the model with 8 gpus. The MAP is 0.42181965127297494 (which is the same perfoemance as your log)
- I comment out the original forward_test, and change forward_track as forward_test, still use test.py to evaluate the model with only 1 gpu. The MAP is 0.055639788009346346.
From my understanding, the forward_test will regard the model as a detection model, which means it will generate_empty_instance at every time.
As for forward_track, it will only generate_empty_instance at the first frame, then keep some track instances and pass to next frame.
I'm not sure if there is any error in my steps described above? And could u plz tell me about how did you check that 'they should perform the same on a short video clip' ?
from pf-track.
@JunqiaoLi I see. If you use the tracking evaluation for the detection evaluation, the phenomenon described above makes more sense now. (Actually, I don't recommend this. Please check out the reasons in here.)
Ok, now, potential solutions. There are a handful of differences between forward_test
and forward_track
. I cannot remember everything after several months, but here are two examples. (1) link test_tracking
filters out the categories not for tracking evaluation; (2) link More complicated update of active tracks is used for tracking. Perhaps aligning the behaviors is the key to getting good detection results.
Furthermore, how about getting the bounding boxes via the tracking results tools/test_track.py
then evaluate the mAP. You might need to align the format with detection, though.
from pf-track.
@JunqiaoLi It seems this issue is no longer active. Thanks for the discussion! Would you mind close this issue?
from pf-track.
Related Issues (20)
- Question about Track Extension HOT 6
- About the motion prediction evaluation HOT 2
- Why two step training HOT 12
- question about visualization HOT 6
- question about distributed training HOT 6
- What is the result.json file in relation to visualization code? HOT 2
- about visualization HOT 2
- about result.json HOT 6
- Evaluaiton on the test set HOT 2
- for Validation HOT 6
- Docker file
- Didn't provide mmdet3d folder HOT 2
- Train and infer on KITTI data HOT 1
- Gradient checkpointing with ddp HOT 6
- About the tracking result HOT 5
- Get some Errors when test tracking method HOT 4
- Adjusting batch size HOT 4
- detection_head HOT 5
- nuscenes_dataset 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 pf-track.