Octav Florescu

Had the same issue, in my case, VSCode added automatically an import, while our codebase usually adds the path to sys paths, so full path is not required. This resulted...

I have encountered the same error, and the reason **in my case** was pretty straight forward: model was generated on server, i was copying it to local machine, and i...

Cool PR, thank you! i am using it with `albumentations==0.5.2`

same in parallel for torch_cpu/torch-cpu -> ModuleNotFoundError: No module named 'aimet_torch'

not solved, but workaround: ``` export AIMET_VARIANT=onnx-gpu export WORKSPACE=/data/local/data/octavf/edge/aimet/ export docker_image_name=artifacts.codelinaro.org/codelinaro-aimet/aimet-dev:1.28.0.${AIMET_VARIANT} export docker_container_name=aimet-dev-octavf docker ps -a | grep ${docker_container_name} && docker kill ${docker_container_name} docker run -p 9876:9876 --rm -it -u...

hi @AllentDan here it is the model: ``` fp16 = dict(loss_scale=512.0) norm_cfg = dict(type='GN', num_groups=32, requires_grad=True) model = dict( type='CascadeRCNN', pretrained='open-mmlab://resnext50_32x4d', backbone=dict( type='ResNeXt', depth=50, groups=32, base_width=4, num_stages=4, out_indices=(0, 1, 2,...

hi, i have come back to this... if i try and run the mdoel conversion, it ends here: ``` File "/usr/local/lib/python3.8/site-packages/mmdeploy/codebase/mmdet/models/detectors/two_stage.py", line 58, in two_stage_detector__simple_test proposals, _ = self.rpn_head.simple_test_rpn(x, img_metas)...