J L

> Hi, could you check if the pytorch matches cuda verison? This error often occurs when they are not matched. can you tell us pytorch and cuda version I use...

> @chenyilun95 Please provide a dockerfile. > > I am facing lots of issues with spconv and cumm intsallation. > > Thanks > Hi, could you check if the pytorch...

code: import torch from mmdet.apis import init_detector,inference_detector from mmdet2trt import mmdet2trt from mmdet2trt.apis import create_wrap_detector,inference_trt_model cfg_path = "/home/azuryl/data2/mmdetection/configs/mask_rcnn/mask_rcnn_r50_fpn_mstrain-poly_3x_coco.py" weight_path = "/home/azuryl/data2/mmdetection-to-tensorrt/models/mask_rcnn_r50_fpn_mstrain-poly_3x_coco_20210524_201154-21b550bb.pth" save_model_path = "/home/azuryl/data2/mmdetection-to-tensorrt/models/mask_rcnn_r50_fpn_mstrain-poly_3x_coco32.trt" save_engine_path = "/home/azuryl/data2/mmdetection-to-tensorrt/models/mask_rcnn_r50_fpn_mstrain-poly_3x_coco32.engine" device = 'cuda:0'...

I save trt_model and warp_model t respectively and tested opt_shape_param=[ [ [1,3,320,320], # min shape [1,3,1280,1280], # optimize shape [1,3,1344,1344], # max shape ] ] max_workspace_size=1

> This error can be ignored by setting the class name in > > https://github.com/grimoire/mmdetection-to-tensorrt/blob/5352f1568e71cb0b5f187211a0d92fe0dc570756/mmdet2trt/apis/inference.py#L62 > . @grimoire Dear yes I modified this section according to you suggestion def get_classes_from_config(model_cfg):...

> This error can be ignored by setting the class name in > > https://github.com/grimoire/mmdetection-to-tensorrt/blob/5352f1568e71cb0b5f187211a0d92fe0dc570756/mmdet2trt/apis/inference.py#L62 > . I convert MASK RCNN R-50-FPN |pytorch from https://github.com/open-mmlab/mmdetection/tree/master/configs/mask_rcnn but there are another issue...

> Hi, Which mmdet version are you using? Not that the master branch of this repo only support mmdet1.18+. > > You can check your environment with [collect_env.py](https://github.com/grimoire/mmdetection-to-tensorrt/blob/master/tools/collect_env.py). > >...

> Oh, err... sorry, master branch requires mmdet 2.18.0+ , I forgot to update the Readme.md. Would you mind updating mmdetection and trying again? ok I will try it

> Oh, err... sorry, master branch requires mmdet 2.18.0+ , I forgot to update the Readme.md. Would you mind updating mmdetection and trying again? @grimoire Dear grimire I have update...

> You need to enable the flag to convert a model with instance segmentation. please read [this](https://github.com/grimoire/mmdetection-to-tensorrt/blob/master/docs/getting_started.md#instance-segmentation-supportexperimentation) for more detail. And as your input is `x = torch.ones([1,3,320,320])`, I think...