S3DIS results

[hpc100]

Thanks for sharing your work ! It's possible to provide Swin3D-L (without pretrained) results and the log for Swin3D-S (without pretrained). I ran some this two exp with 4GPU & 100 epoch and I get :

• for swin3D-S (without pretrained) mIoU=68.0 (Area 5 validation) (4 points lower your result (72.5))
• for swin3D-L (without pretrained) mIoU = 69.4 (Area 5 valdiation) For both model (pretrained on Structured3D), I get your performance : 73 for Swin3d-S and 74.5 for Swin3d-L). So, in paper you announced 3000 epochs for S3DIS to train from scratch on S3DIS, is the number of epochs is 3000 or 100, for training without pretrained pth on Structured3D ? If the number if different from 100, which hyperparameter do you used (eval_freq = 2 or higher to save time, ...) Thank's

[Yukichiii]

The number of epochs is 100, but the loop is set to 30, which is equivalent to 3000 epochs. The eval_freqis 2, which is equivalent to evaluate every 60 epochs (due to loop=30).

[hpc100]

Thank's for your reply. I'm going to test this ;)

[hpc100]

@Yukichiii I applied epochs = 100 // loop = 30 and eval_freq = 2. I get on Area 5 :

• Swin3d-S : 69.76
• Swin3d-L : 69.79 It is possible to provide the log ? For the tests do you use num_vote = 12 ? For training did you change any parameters on relation to code https://github.com/Yukichiii/Swin3D_Task The result in your paper Swin3D-S | ✗ | 72.5 (without pretrained weight), is obtained with RGB or RGB + Normals. Thank's