search

ZikangZhou / QCNet

[CVPR 2023] Query-Centric Trajectory Prediction
https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_Query-Centric_Trajectory_Prediction_CVPR_2023_paper.pdf
Apache License 2.0
432 stars 70 forks source link

Brier score is oscillating #15

Open harshy105 opened 11 months ago

harshy105 commented 11 months ago

The Brier score in my training is not decreasing while all the losses and the socre seems to be converging to the reported values. The corresponding value after 68 hours of training on A100, with 100GB RAM.

The training hyperparameters are: --num_workers=32 --train_batch_size=16 --val_batch_size=16 --test_batch_size=16 --max_epoch=50 --pl2pl_radius=150 --time_span=10 --pl2a_radius=50 --a2a_radius=50 --num_t2m_steps=30 --pl2m_radius=150 --a2m_radius=150

Current training status; Epoch: 32 Training duration: 68 hours

Brier: 0.61 (osciallting near this value since the begining of the training) MR (k=6): 0.1824 minADE (k=6): 0.751 minFDE (k=6): 1.359

I am also attaching the Tensorboard checkpoint for further analysis. Please let me know if anything else is required. Checkpoint.zip

ZikangZhou commented 11 months ago

Hi @harshy105,

I also observed a similar phenomenon. No idea about how to get a lower Brier score while also achieving decent ADE/FDE.