Closed StanLei52 closed 6 months ago
Thank you so much for your reply. Based on your reply for 1 and 3, is the config for PointBERT in Tab 1 w/o hard negative mining?
yes
OK. May I confirm that python3 src/main.py --trial_name pointbert_all model.name=PointBERT model.scaling=4 model.use_dense=True training.lr=0.0005 training.lr_decay_rate=0.967
can reproduce the PointBERT perf as shown in Tab 1? I did this with 8-V100 and got worse results on Objaverse(~42%) and ScanObjectNN(~52%).
Thank you for reporting the issue. We just noticed that a patch was missing from the released code. The point cloud is not randomly permuted during training, which leads to bias in PointBERT tokenization -- the FPS grouper takes points with largest indices for each centroid. I just did a quick blind fix in commit 4748adb8ad202bc2446fddd0eee5cc1b32f13f3f.
Another difference may be that we trained the model with 4 A100s, each consuming a batch size of 48 resulting in a total batch size of 196. The effective batch size may be different if you have 8 V100s.
Thank you for your update, I will retry with this version.
Hi @eliphatfs, before I get started, I still have some questions on the new commit.
Compared to the previous version, the random sample is updated for get_others
for Four
Dataset, getitem
for ModelNet40Test
and getitem
for ObjaverseLVIS
. Is this correction enough for pretraining on Four
dataset, since get_objaverse
for Four
is NOT updated in your last commit? Could you please double-check for this?
Thanks!
Thank you for pointing out it and sorry, I missed that.
Hi author,
Thank you for working on the great OpenShape. I have some questions on the performance of the models.
python3 src/main.py --trial_name pointbert_all model.name=PointBERT model.scaling=4 model.use_dense=True training.lr=0.0005 training.lr_decay_rate=0.967
. I assumed this is the case without hard negative mining for PointBERT and found that the performance is less promising than using hard negative mining, e.g., -4% on Objaverse LVIS. May I know the performance of PointBERT_all w/o hard negative mining so that I can get a sense if I reproduced the correct results?Thanks!