Chen Xin

What is your working directory looks like? Are there exist a folder named mmdeploy_runtime? If so, please change the working directory or the `import` will find modules in this folder...

can temporarily use this docker image for testing `docker pull irexyc/mmmdeploy:triton-22.12`

@Y-T-G > I created a dict for each bbox [here](https://github.com/open-mmlab/mmdeploy/blob/fcdf52f0a504f86e9d3528dd72856a71ef5e28d9/demo/triton/keypoint-detection/grpc_client.py#L84) and added to the value list, and used that, but the results are not accurate, although the number of keypoints...

``` test_pipeline = [ dict(type='LoadImageFromFile', backend_args=None), dict(type='Resize', scale=(1920, 1216), keep_ratio=True), dict( type='PackDetInputs', meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape', 'scale_factor')) ] ``` Please try to use detection_tensorrt-xxx_dynamic-xx.py and edit the min/opt/max shape according...

@himansh1314 There is a bug of static resize (mmdet treat the scale of resize as (w, h), while mmdeploy sdk treat it as (h, w)), this pr will fix it...

@himansh1314 We made nms as part of model inference instead of postprocess. However the settings for nms are fixed (won't read your model config) when you convert the model. You...

@himansh1314 It seems that you have already modified some content of `base_static.py`. However, you doesn't modify the `score_threshold` to 0.001. Not sure if it could help, you can have a...

Please keep pre_top_k = 5000, there are asserts in `allClassNMS.cu` ```cpp const static int BS = 512; ... const int t_size = (top_k + BS - 1) / BS; ASSERT(t_size

I think it will work for nms after comment the assert. I'm not quite sure why there has assert compared to https://github.com/NVIDIA/TensorRT/blob/master/plugin/common/kernels/allClassNMS.cu @grimoire may explain to you With score_threshold=0.001, the...

Can you try to clean the old build folder and build again?