RajUpadhyay

what if you try inspecting your onnx with netron to see how the onnx is changing w.r.t. the activation function? how does the results don't match, like in what way?...

I know this is an old issue but use c++ or deepstream for inference on a jetson. (more like you should only use those) I personally got upto 29 FPS...

@azhurkevich thank you for the sample, it helped alot. For inference it took some time but I was able to do it with c++ and later was able to use...

OK I will give it a try, I did make an onnx but it only gave heatmaps and not the actual points. Now that I know it is doable, I...

Ok wow thanks. If I do eventually manage to make an onnx for keypoints, I'll ping you. Thanks again.

Hi, If you are the same guy as in this post, follow what the method I suggested over there. If you are not, even then follow the method suggested on...

> Hi, sorry for the late reply, > > @RajUpadhyay I am effectively the same guy as in the other post. The method you shared is the same I used...

Does [this](https://github.com/NVIDIA/TensorRT/issues/2142#:~:text=I%20can%20tell%20you%20the%20answer%20but%20it%20will%20be%20a%20long%20one.) explaination help? Atleast the first para might help you with the explaination of why your resolution might not be working as expected.

Hi there! I am sorry but I am facing the exact same issue. **Command:** python create_onnx.py --exported_onnx /workspace/model.onnx --onnx /workspace/converted.onnx --det2_config /workspace/detectron2/configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml --det2_weights ~/.torch/iopath_cache/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl --sample_image /workspace/1344x1344.jpg **Error:** Traceback (most recent...

@azhurkevich Thank you for the reply. I saw the link you sent me and yes, that could have also worked. I found another way but in a sense, it does...