search

qizekun / ReCon

[ICML 2023] Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
https://arxiv.org/abs/2302.02318
MIT License
120 stars 13 forks source link

The pretrain ckpts choice for classification and segmentation task #16

Closed Amazingren closed 3 months ago

Amazingren commented 3 months ago

Dear @qizekun ,

Thanks for your very nice work, recently I noticed that reproducing the results for point cloud pretraining, usually, requires a decent pre-trained checkpoint.

My question is if the same pre-trained checkpoints are used for both the classification and the segmentation task.

For example, if I found ckpt-ep250 works well for classification, am i right to use it also for part segmentation? Or to produce also a decent result of part segmentation, I need to choose another ckpts (e.g., ckpt-ep300) ?

Thanks in advance for your answer.

Best regards and have a nice day,

qizekun commented 3 months ago

Thanks for your attention.

Yes, we use the same pre-trained checkpoint for both the classification and the segmentation task (the best for classification).

Amazingren commented 3 months ago

Thanks for your attention.

Yes, we use the same pre-trained checkpoint for both the classification and the segmentation task (the best for classification).

Thanks for the quick feedback. It helped a lot. :)

With warm regards,