Levi Pereira

New Feature - Pin Bounding Box to next Images.

1

Hi, Will be great if allow pin bounding box to nexts images. For example labeling Cars from a sequence of images from video. If some car shows in all images...

Hi, first of all thank you for excellent work. I have [VERI-Wild Dataset](https://github.com/PKU-IMRE/VERI-Wild), can you help me build a python script like [train_veri.py](https://github.com/nwojke/cosine_metric_learning/blob/feature/veri_dataset/train_veri.py) to train this Dataset Structure.

Enhancement Request: Additional GPU Information in Prometheus Metrics

5

**Is your feature request related to a problem? Please describe.** no Currently, the triton-server provides GPU utilization metrics in Prometheus format, like so: ``` # HELP nv_gpu_utilization GPU utilization rate...

Performance YOLOv7 vs YOLOv9-C vs YOLOv9-E over TensorRT engine

3

Perfomance Test using GPU RTX 4090 on AMD Ryzen 7 3700X 8-Core/ 16GB RAM. #### Model Performance Evaluation using TensorRT engine using Triton-Server All models were deployed using FP16 and...

YOLOv9-QAT TensorRT Q/DQ: Improved Speed and Zero Loss Accuracy

6

@WongKinYiu I have developed the initial version of YOLOv9-QAT using the Q/DQ method, tailored specifically for YOLOv9 models intended for execution solely on TensorRT. This implementation currently supports only the...

End2End ONNX Export Implementation for YOLOv9

1

#130 **YOLOv9 ONNX End2End with [TensorRT Efficient NMS](https://github.com/NVIDIA/TensorRT/tree/32c64a324e58f252eae4e5681f5c39dbe22ef2d5/plugin/efficientNMSPlugin) plugin** - **Support for End-to-End ONNX Export**: Added support for end-to-end ONNX export in `export.py` and `models/experimental.py`. - **Model Compatibility**: This functionality...

Hi @WongKinYiu, I successfully validated the YOLOv9 models using the [Yolov9 End2End implementation](https://github.com/levipereira/yolov9/), and the results were quite satisfactory. I'm considering opening a pull request to implement the End2End functionality,...

Fatal error: TRT:EfficientNMS_TRT(-1) is not a registered function/op

2

I need to run the Triton Server using an ONNX model that generates a TensorRT engine on-the-fly. I'm aware that I could use the trtexec utility to generate the TensorRT...

SerialLink - Allow Char instead Int

2

Hi, First of all, many thanks for your sharing...it's wonderful. I'm using your Lib Seriallink.h to others projects with esp8266 and arduino uno. I need send/receive char over serial comunication....

We're currently working on improving our YOLOv9 model by implementing quantization in the [class SPPELAN(nn.Module):](https://github.com/WongKinYiu/yolov9/blob/1bbce4d09a0a21ad974102bfaf139a4e13f6c5c1/models/common.py#L563) . We've observed that the current implementation is generating reformat operations. Any contributions, suggestions, or...