CaMi1le
CaMi1le
> Thanks. You can refer to https://mmrazor.readthedocs.io/en/main/user_guides/quantization_user_guide.html for basic usage and examples. For openmmlab's models, it is theoretically possible to apply qat to your model by changing the config file....
It needs mmcv
I faced similar problem too. I solved by adding a judgement in detectors/base.py function forward_test, judging the type of img_meta. If it is Datacontainer, replace `img_meta[img_id]['batch_input_shape']` with `img_meta.data[img_id][0]['batch_input_shape']`
If mmdet models' QAT is supported, please let me know. Someone help for the config about the combination of backbone,neck and head?
#602 Says using mmcls==1.0.0rc6, which works fine for me
> I'm also trying the same thing; I tried using mmdeploy with the weights from mmrazor checkpoint. It works but I'm yet to test the onnx file. Sorry to bother....
> > I'm also trying the same thing; I tried using mmdeploy with the weights from mmrazor checkpoint. It works but I'm yet to test the onnx file. > >...
Working on this too, most carla-based datasets are kittis
Same issue. Has try ways above, not working `ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of...
hi I am using Ubuntu22.04 with RTX3090 running carla 0.9.12, I try your methods above but seems to have some same issue, the terminal still get crashed in about 50...