SASA

SASA copied to clipboard

It does not seem to consider removing empty boxes (i.e., the box padding for collecting batch) https://github.com/blakechen97/SASA/blob/cd79f60e923242590b64cb0cc70203a524e7e9a7/pcdet/utils/loss_utils.py#L308-L335

OuyangJunyuan

sasa_nuscenes model

4

Dear author, can you provide the nuscenes pretrained model

liuhuaijjin

Custom dataset training ?

2

Please help me, is it possible to train the model with custom dataset , how can I train and inference the model with custom dataset , if possible please help...

devendraswamy

HuangZhe885

experimental results

7

Hi, Dear author! I would want to know, your public results of 3DSSD+SASA whose moderate's is 85.91, is trained by"80% train+20%val" or 70&30? Waiting for your answer~~~~

pummi823

Dear author: I try to implement your results in your paper, but just get mAP of 20 (the reason may be i just set the batch_size to 3 instead of...

pummi823

Hello, thank u for your brilliant work! I've tried 3dssd_SASA to train 'Car', but when I add more classes (eg car, pedestrian), the code raises some error, and I want...

Jane-QinJ

Hello author, which part of the source code is used in the "semantic-guided farthest point sampling" mentioned in your paper?

2311762665

verification and test results

3

Z-Lee-corder

about batch_size

2

Dear author: in your paper, for 3DSSD, you said that " The total batch size is set to 16, equally distributed on four NVIDIA V100 GPUs". But in your code...

pummi823