jyang68sh

Hi. I used mmseg tools/benchmark.py to get the speed with mmseg. For mmdeploy, I used tools/test.py --speed-test option to get the speed. I think both scripts only counts the model...

> Could you post your test command? Sure. CUDA_VISIBLE_DEVICES=2 python tools/test.py xspace/1_apps/mmdeploy/configs/mmseg/segmentation_tensorrt_static-512x1024.py xspace/work_dirs/stdc2_cityscapes/stdc2_512x1024_80k_cityscapes.py --model xspace/work_dirs/stdc2_standards/end2end.engine --speed-test @lvhan028 Thanks!

@lvhan028 Sorry to bother. Is there any updates?

> @jyang68sh Sorry for late reply, the difference is mainly due to the different backend (pytorch vs tensorrt). > > I test this [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/stdc/stdc2_512x1024_80k_cityscapes.py) on 2070s. > > With benchmark.py,...

> Hi, @jyang68sh Is there any update? Hi, Sorry for the late reply. my machine was used for another series of experiments. I will have an update once the experiments...

@nikitadurasov Sorry I got confused. > To acquire predictions from different submodels one should transform input (with shape [1, H, W, C]) into batch (with shape [M, H, W, C])...

@nikitadurasov Thanks for the quick response. Now I see that you have already described the process in the paper. Sorry for the confusion. I just have a quick question. Masksembles...

@cclauss @c-liangyu Please have a look. Thanks!

@fangyixiao18 Thanks. I solved the issue. Great framework btw

Hi @MeowZheng Please have a look. I tried to debug but the error was ambiguous to me. Thanks!