batrlatom
batrlatom
Normally yes, but not yet for your model. I do not know about any instance segmentation network which could be reasonably exported to tensorrt ( maskrcnn could, but the speedup...
Hi, I have solved the problem by going around :] with fastapi, uvicorn and saving/loading the model directly. Probably not so fast, but good enough for me now. ``` #...
> @pliablepixels You could export and test Edge TPU model with https://github.com/zldrobit/yolov5/tree/tf-android-tfl-detect. > PS: I attached the COCO Edge TPU model with 320x320 input resolution in case you're interested. >...
do you think you could share the jupyter notebook for training?
This is the middle of the road, but it is necessary to be able to use tensorrt (through the torch_tensorrt library). Check out this implementation. Converting to torchscript and layer...
I have tried it, works great! I was trying to export the transformer version, I have succeeded. But the inference code is not compatible with such version. Do you think...
Ok, thank you for checking it out. If you will have time sometimes and will try to use adapt it for transformer, just update it here, so we also will...
@vladmandic btw. I was playing with the code a little more and I am unable to get results that are similar to the results before the conversion. I am using...
thanks, I will take a look!
There is not any problem with the conversion as your model gives me the same result. But the difference between js and vanilla implementation lies in the scores. Scores calculated...