Yuxiang Chen

As a newcomer, I don't understand why log sample should be used instead of uniform. Can someone give me some references or intuitive explanations? thanks!!

BUG Issue ( segmentation fault during backward)

3

## 环境 1.系统环境：ubantu 2.MegEngine版本： 1.9.0 3.python版本： 3.7 ## 复现步骤 简化case: ``` import megengine import megengine.functional as F from megengine.autodiff import GradManager import megengine.module as M import megengine.optimizer as optim import...

motion updating?

2

can you tell me where you do the motion updating in your code? I only find the ego-motion update in your val_nusc_tracking.py

can you share the log.json for the training on nuscenes dataset? By comparison, I know if there is a problem with my code， thanks!

I notice that in "simtrack/det3d/models/detectors/single_stage.py" line 32, init_weights is Annotated, why? how you init the parameters?

as title

about mask?

1

I have found two mask folds in your readme, i think they are for test? but for FVI dataset, i only find one kind mask? can you provide the other...

## ❓Question ``` my envs: ubuntu 20.04 coremltools 7.0b1 pytorch 1.13 ``` I followed the official documentation for **qat** training, and when I called the report() method of Quantizer, it...

can this project do image processing tasks?(like denoising or enhancement, input : rgb, output: rgb)

🐛 [Bug] dynamic shape support in h and w dims (e.g. [b,c,h,w] layerout)

1

## Bug Description I used the latest nvidia 23.12 docker image, tried to compile a model with a structure similar to UNET and with pixelshuffle and interpolate operators, set the...