Comments (29)
@Vegeta2020 @shxzhao I also got a lower AP results when using the model from this repository:
Evaluation official_AP_11: car AP(Average Precision)@0.70, 0.70, 0.70:
bbox AP:90.61, 89.47, 89.02
bev AP:89.94, 88.11, 87.44
3d AP:88.44, 79.07, 78.27
aos AP:90.51, 89.10, 88.46
car AP(Average Precision)@0.70, 0.50, 0.50:
bbox AP:90.61, 89.47, 89.02
bev AP:90.67, 89.73, 89.38
3d AP:90.66, 89.67, 89.28
aos AP:90.51, 89.10, 88.46
Evaluation official_AP_40: car AP(Average Precision)@0.70, 0.70, 0.70:
bbox AP:96.27, 93.00, 90.56
bev AP:93.25, 89.64, 87.23
3d AP:89.73, 83.08, 80.57
aos AP:96.12, 92.55, 89.97
car AP(Average Precision)@0.70, 0.50, 0.50:
bbox AP:96.27, 93.00, 90.56
bev AP:96.45, 95.39, 93.02
3d AP:96.37, 95.22, 92.89
aos AP:96.12, 92.55, 89.97
from se-ssd.
Did you use your own training model or the pre training model the repository provided?
from se-ssd.
Same as you, and I found that as the training progresses, the accuracy will get lower and lower from epoch 1 to epoch 60.
from se-ssd.
I forget to set the eval result per epoch, but my result of eval dataset is so low, can you provide your set of train.py or provide the train model to me. My email is [email protected]
from se-ssd.
I didn't change the code of train.py, and my final result is same as yours. The only thing I modified is #14. Maybe the bad result is caused by this modification, or the author of the paper missed something. Could you give us some suggestions? @Vegeta2020
from se-ssd.
@shxzhao I used the pre-trained student model the repository provided.
from se-ssd.
@WWW2323 I find the results from epoch1 to epoch60 get lower and lower too, sometimes it also will crash during epoch 50 - 60 because of "out of cuda memory ", I am wondering if the model tend to predict more proposals and get lower mAP.
Can you give me some advice?
@Vegeta2020
from se-ssd.
This is my evaluation result using the provided model, it seems the same as in README.
If it's lower than that, I guess it's caused by data or dependencies preparation.
from se-ssd.
Maybe you need set batch size = 1 @pigtigger , i set the batch size = 1.
@FangGet Good job! did you change any code of the repository?such as #14, and what's your GPU type? Thanks!
from se-ssd.
nop, I keep everything the same as the original, the model copy issue in #14 may be caused by python version, try using python 3.6.
Btw, my GPU type is RTX 2080TI
from se-ssd.
I got the same results as yours when evaluate the provided model, but when I use it the as initial weights for student and teacher model and start training, the performance drops a lot @FangGet
from se-ssd.
I also obtained the same results as stated in the README!
from se-ssd.
@WWW2323 Thanks .
do you get a good results after training ? could you tell me the model you use for initialize student and teacher? I also modified #14 , but not sure if it is the reason for bad performance
from se-ssd.
I have no idea, i can't even get good results before training @pigtigger
from se-ssd.
@pigtigger I guess you should use the pre-trained model from CIA-SSD as the initial model, if SE-SSD pre-trained model is used, try to decrease the learning rate. But it's normal for performance drop as soft-target supervisor may disappear if the difference between teacher and student is ignorable, just my opinion.
from se-ssd.
I also get the same val set results as shown in README.md, but i run into another problem. When i use the model to inference test set and submit to kitti server, the results is as follows:
I don't know if I need to modify any configuration during testing, because the result of SE-SSD on test set is this:
If you get results similar to SE-SSD on test set, please @ me, thanks!! Or @Vegeta2020 can give some advice?
from se-ssd.
Do you use the pre-train model or the model you trained?@WWW2323
from se-ssd.
I use the pre-trained model provided in README to inference val set and test set. The result on the val set is more like the result in the SE-SSD paper, but the result on the test set is more like the result of the CIA-SSD. Now I don't know if the provided-model is the final model of SE-SSD or it is just used for SE-SSD initialization.
from se-ssd.
It should be the final model of SE-SSD.
from se-ssd.
I get the same results as yours @WWW2323
the final model's performance is similar to CIA-SSD, so I think it is not the final model and use it to initialize SE-SSD, but the training results is even lower.
from se-ssd.
Do you mean your result on the test set is the same as mine? @pigtigger
from se-ssd.
from se-ssd.
Hi, guys. The provided model is the SE-SSD model trained on the train split and not on the trainval split, and the results given in README are based on the evaluation on the val split. (I'm afraid I cannot provide the trained model on the trainval and help you produce prediction files for submission to KITTI evaluation server, as it will violate the submission policy and lead to account banning.)
To get decent results, you must use a pre-trained model to initialize both student & teacher model. In our previous experiments, we often get decent results with a pre-trained model training from scratch, but there are only a few cases that we cannot, we guess it' related to the initialization.
from se-ssd.
Hi, everybody, do you reproduce the results? I trained a CIA-SSD model and use it for the initialization of SE-SSD. Although there is no drop as using provided model in README for initialization, there is no increase. So sad
from se-ssd.
@WWW2323 do you mean that you use your own model trained from CIA-SSD for initialization to train SE-SSD and get almost the same results as your initialization model ? I use CIA-SSD pretrained model in CIA-SSD README and get a huge drop. could you send your trained CIA-SSD to me ? I want to have a try .Thanks, my email is [email protected]
from se-ssd.
Hi, everybody, do you reproduce the results? I trained a CIA-SSD model and use it for the initialization of SE-SSD. Although there is no drop as using provided model in README for initialization, there is no increase. So sad
@WWW2323 , did you use the pretrained model provided by author in CIA-SSD rep, and train using SE-SSD.
from se-ssd.
No, you need train a CIA-SSD model yourself with CIA-SSD rep. The head of CIA-SSD in CIA-SSD rep is different from the head of CIA-SSD in SE-SSD.
from se-ssd.
Can you share the log of training with me? Thank you very much.
from se-ssd.
Evaluation official: car AP(Average Precision)@0.70, 0.70, 0.70:
bbox AP:88.58, 77.79, 75.09
bev AP:84.71, 75.34, 67.57
3d AP:47.61, 41.61, 40.11
aos AP:87.11, 75.19, 72.10
car AP(Average Precision)@0.70, 0.50, 0.50:
bbox AP:88.58, 77.79, 75.09
bev AP:90.81, 89.37, 87.25
3d AP:90.62, 88.13, 79.81
aos AP:87.11, 75.19, 72.10
Evaluation coco: car coco [email protected]:0.05:0.95:
bbox AP:60.11, 56.47, 54.31
bev AP:53.67, 50.72, 47.66
3d AP:41.55, 37.92, 35.54
aos AP:59.18, 54.57, 52.16
from se-ssd.
Related Issues (20)
- det3d.visualization.kitti_data_vis.kitti.kitti_object import show_lidar_with_boxes_rect
- How SE SSD Evaluate 3 D Bounding Box IOU ?
- 明明是匹配的都是10.1版本,还显示NO supported GPU capabilities found。
- Why use intensity transform in sa_da
- Error in training HOT 3
- About student loss HOT 1
- Density or reflectivity? HOT 1
- About where is "kitti_infos_train.pkl" HOT 1
- Training a teacher network (custom dataset) HOT 1
- The problem about run train.py HOT 1
- how to update ema variables in different models, such as a big model and a small model ; HOT 2
- About the division of KITTI training dataset HOT 3
- question about ssl training HOT 2
- SE-SSD ALL IN TensorRT HOT 2
- RuntimeError: Expected object of backend CUDA but got backend CPU for argument #2 'mat2'
- Install error "relocation R_X86_64_PC32" when "python setup.py build develop"
- SA-DA HOT 3
- Problems in installing spconv! HOT 2
- Could you update the requirements file with version of packages HOT 2
- Sa_ Da_ V2.py file call
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 se-ssd.