DuZzzs
DuZzzs
dimension `label = mx.symbol.Variable('focalloss_label',shape=(batch_size,))`
@hailanyi @Typolo Hi, do you know how to save as a gif file? Thanks.
Thanks
Hi，followed readme/GETTING_STARTED.md, I can't reproduce the readme results。What changes did you make？My result: https://github.com/Banconxuan/RTM3D/issues/36#issuecomment-848445215 Thank you. @FanghaiZhao
同样无法复现结果。 - 使用readme中第一个预训练模型res18，kitti-split1，进行测试。（由于部分图网络没有检测到目标，在eval时会报错（你们没遇到？？）修改代码不算入这些图，理论上下面计算出的指标应该更高些）。测试结果如下，低于readme中列出的指标： ``` Car [email protected], 0.70, 0.70: bbox AP:90.02, 79.79, 70.61 bev AP:23.77, 17.18, 16.02 3d AP:17.79, 13.85, 12.25 aos AP:89.06, 78.50, 69.24 Car [email protected], 0.70, 0.70: bbox AP:93.30,...
After filtering out the test data like the following code, I got the correct boxes. ``` if self.with_annotations: sensor_cache = sensor_cache[sensor_cache.split != 'test'] ``` There is another problem. I want...
@benjaminrwilson Thanks. I'll try later. Is there a reference code for this kind of picture in the readme? 
@hova88 @vietanhdev Have you solved the problem of random results? I also encountered this problem. Thank you.
We have tested the this repo code on demo point cloud dataset and my dataset(only one frame). When use demo data, detection results is alawys changing. In my dataset, box...
Thanks. Two more points need to be pointed out： 1. We observed cuda memory increased in loop inference, and we fixed it by `cudafree`， you can check it in pull...