ZhuLifa

我也遇到了相同的问题. 后来发现是因为我用了两个显示器,打开微信后cpu占用100%,但找不到微信.后来换成一个显示器正常了.

> Hi, lifa, I am training it from scratch on S3DIS and got approximately the same results as yours. Specifically, 30 epochs now (still training), best mIoU 58.388, best eval...

@AmeetR I think It's hard to reproduce this repo. I ran it 1 month ago, debugged it, and failed. Then I code PSPNet myself, and achieved 0.74 mIoU. Maybe you...

@fatemechangizian No.

Hi @CrazyMage24, Try to update the `point_cloud_range` parameter in the following 3 code blocks, 1. https://github.com/zhulf0804/PointPillars/blob/9c98d51742ff21209e1a587cf6c6f680f1cc5224/model/pointpillars.py#L220-L226 2. https://github.com/zhulf0804/PointPillars/blob/9c98d51742ff21209e1a587cf6c6f680f1cc5224/test.py#L15 3. https://github.com/zhulf0804/PointPillars/blob/9c98d51742ff21209e1a587cf6c6f680f1cc5224/test.py#L38 Please let me know if there are any problems, thanks.

Hello @CrazyMage24, Could you please send the tested Lidar data to my mailbox ([email protected]) if possible? I'll debug it in the next few days. Thanks.

Hi @CrazyMage24, Maybe there are **4** code blocks to be updated for point cloud range. **In addition to** the above 3 code blocks, **the 4th** code block needed to be...

Good question. But I remember the inference was with a fast speed. I'll test the inference speed later and reply here. **Updates** 1. Using TITAN X (an older GPU) to...

I'm not sure now. I'll retest the speed on RTX3090 when the machine is free.

Nice and careful analysis. It seems strange about the time consumption of `nn.BatchNorm1d`. Do you have any ideas about the result ? BTW, what type of your GPU and Cuda...