MarouaneMja
MarouaneMja
Hello , any updates about this bug, please? I have the same error, I am trying to test my onnx model but I found this : `failed:Fatal error: SoftNonMaxSuppression is...
I will try this , but I am not sure to have the same results. Thanks
It does not work unfortunately using nms. I actually have found this in the documentation `mmcv::SoftNonMaxSuppression is only supported for single image by now.`, which mean it's supported. I have...
Indeed NMS is a common operator. But for CO-DETR, I dont know why It does not work If I modify sof_nms with nms. When I made this modification, the exportation...
Actually, when I debug my code, it stucks in this if condition in the image below , then it stopped with no error message. I don't know if you have...
@TempleX98 I have tried your suggestion but I encounter some problems but when verify the documentation in mmdeploy, I found that CO-DETR is not supported, here is the list of...
Hello, Any updates about the model exportation to onnx , please ?
Hi @TempleX98 , thank you I will look it up
Hi @TempleX98 , I managed to export the CO-DETR to onnx using mmdeploy as you suggested, however the SoftNonMaxSuppression is not supported by onnxruntime `failed:Fatal error: SoftNonMaxSuppression is not a...
Thank you for your help @TempleX98 , it worked. However when I launch infernce with triton inference server , the onnx model takes more space in gpu memory than using...