DeepStream-Yolo icon indicating copy to clipboard operation
DeepStream-Yolo copied to clipboard

NVIDIA DeepStream SDK 7.0 / 6.4 / 6.3 / 6.2 / 6.1.1 / 6.1 / 6.0.1 / 6.0 / 5.1 implementation for YOLO models

Results 232 DeepStream-Yolo issues
Sort by recently updated
recently updated
newest added

Hi! you did greate job! And there was a question which confused me. According to [New optimized NMS](https://github.com/marcoslucianops/DeepStream-Yolo/commit/c8a4a49f16ffe3c7e3e82315fee37678bde811ac), you changed cluster-mode from 4 to 2. Does it means that you...

`Jetpack 4.6 deepstream 6.0.1 yolov5 6.1 ` I tested yolov5s , yolov7 , yolor (untrained,all of them),the can work well. I trained yolov5(changed backbone,but layers(CBH , LC_block , Dense) can...

Hello, Is there a way to activate or implement the NMS clustering on overlapping detections belonging to different classes. I want to eliminate the problem of the same object being...

![Screenshot from 2022-09-22 14-05-45](https://user-images.githubusercontent.com/72983482/191656130-368fcb89-279b-42b3-b173-4b0b74e80cff.png) I trained the yolov5 model with size 640, and wants to set the inference size to be as big as possible. In one case the width...

Hardware: Jetson AGX Orin Developer Kit Software: JetPack 5.0.1 DP What works: Inference works well with FP32 Issue: Inference does not work with INT8. The following output log can be...

I used yolov5 to train a model for recognizing icons. I want to know how to get the specific coordinate position (X,Y coordinate) of the bounding box

Hello! This PR adds support for torch based YOLOv4-tiny from [PyTorch_YOLOv4](https://github.com/WongKinYiu/PyTorch_YOLOv4) to convert from `pt+cfg` to `wts+cfg`. - [x] Added `[route_lhalf]` layer to `nvdsinfer_custom_impl_Yolo` - [x] Added converter script from...

Hello! First, thank you for this super repository. I'd like to help add support for Yolov4-P6 from pytorch `.pt`. I noticed the yolo-large models at [ScaledYOLOv4](https://github.com/WongKinYiu/ScaledYOLOv4/) look really similar to...

When we will get support for yolov7 segmentation model? @marcoslucianops

hey, thanks for the nice work. I wonder if there is any way that we can access to the outputs of the Nvinfer directly ? I have trained a custom...