New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Code & Result on nuScenes #17
Comments
We didn't submit our results to nuScenes leaderboard, although we did conduct some experiments on the validation set. The mAP is about 0.3, and the code will be released. |
When is the code expected to be released? Thanks for your sharing. |
I need some time to re-organize these codes. Unfortunately, due to the coming of CVPR/ECCV, I have no time to do this during this period. So the release of the code may take three or four months. |
Got it. |
Hi @xinzhuma , I tried to modify your code and trained the model on the nuScenes dataset. Without so much hyperparameter tuning, I got mAP=0.26 based on your model structure & training parameters for KITTI. I am tuning the parameters to see if I could get better accuracy. |
@Treemann No TTA or model ensemble tricks. the performance of the single model can achieve about 0.3. The hyper-params are different, including the learning rate, batch size, score thresholds, etc. Besides, some instances are invisible for a specific view, and you need to remove them. |
@xinzhuma so the model structure is the same as that trained on KITTI ?
I'll continue to tune the hyperparameters, thanks for your reply~ |
@Treemann yes, only modify the number of the channels for the heatmap branch to detect all the ten classes. we didn't predict the velocity and attributes. |
Hi @xinzhuma , Thanks for your patience. |
800 * 448 is okay, we also adopt this setting. You can set the confidence threshold to 0.1, which is a better setting for nuScenes. we train the models with batchsize=192 and lr=0.0005 for 140 epochs. |
OK, I'll try with your setting. |
Hi, I have reproduced your result on KITTI.
I can't find your submission on the nuScenes leaderboard, so I wonder if you have done experiments on the nuScenes dataset. If yes, could you share your accuracy? Will you release the code for nuScenes?
Thanks for your excellent work~
The text was updated successfully, but these errors were encountered: