triple-mu

As the issue is shown in yolov7 https://github.com/WongKinYiu/yolov7/pull/273#issuecomment-1196561884 We will support dynamic batch for end2end detect! The example notebooks will be pushed after!

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand...

Add grid concat and fuse such operators

2

Now we can export concat all anchors outputs in flag `--grid` ! If we use `--grid` only, we will export an onnx with one concat output. If we use `--grid`...

New way for register nms in onnx for tensorrt onnxruntime openvino

8

The last [pr](https://github.com/ultralytics/yolov5/pull/7736) provides a basic solution for exporting onnx and modifying it. This pr improves the last pr so that registered nms is completely dependent on pytorch. Simple yet...

There are something wrong in WSL2 with tensorrt example

11

## Description I try to test tensorrt example sample_mnist in WSL2, and I get a wrong output. This is the error log: &&&& RUNNING TensorRT.sample_mnist [TensorRT v8203] # ./sample_mnist [01/30/2022-16:45:10]...

This pr will support python>=3.7 and pytorch >= 1.7. I have tested in pytorch1.7 1.8 1.10 1.12.

BUG?

4

(base) ubuntu@y9000p:~$ curl -sL https://gitee.com/mirrors/dochat/raw/main/dochat.sh | bash ____ ____ _ _ | _ \ ___ / ___| |__ __ _| |_ | | | |/ _ \| | | '_...

Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily receiving feedbacks. If you do not understand...

Add nms for tensorrt8.0+ / onnxruntime / openvino(the same way as onnxruntime)

26

Maybe it is the easiest way for registering EfficientNMS plugin in onnx and building tensorrt engine. I am inspired by this issue : https://github.com/ultralytics/yolov5/issues/6430