Marcos Luciano comments

Results 468 comments of


                                            Marcos Luciano

custom yolov7 model works in tensorrt, but not in deepstream. > deserializeEngineAndBackend()

Added support for YOLOv7.

Use 2 weights with different num classes

If you are using YOLO as secondary-gie, you need to change the sgie `yoloPlugins.h` file ``` const char* YOLOLAYER_PLUGIN_VERSION {"1"}; ``` to ``` const char* YOLOLAYER_PLUGIN_VERSION {"2"}; ``` Compile and...

Use 2 weights with different num classes

https://github.com/marcoslucianops/DeepStream-Yolo/blob/master/docs/multipleGIEs.md

Use 2 weights with different num classes

Can you send me your edited config_infer_primary and the deepstream_app_config.txt files?

Use 2 weights with different num classes

What's the topK value in the config_nms.txt?

Use 2 weights with different num classes

Can you test with the new commit files?

Use 2 weights with different num classes

Please change the `yolov2_ocr-net.cfg` to `yolov2-tiny_ocr-net.cfg`.

Use 2 weights with different num classes

Yes, the second model runs on the detected area of the first model. Can you send a video sample to run the model and test?

Use 2 weights with different num classes

![image](https://user-images.githubusercontent.com/47423225/186222213-a9516464-b6f4-4fcc-88ce-3468fbd321ab.png) I'm geting the outputs with your model as secondary detection.

Use 2 weights with different num classes

Can you test with the new `nvdsinfer_custom_impl_Yolo` from the current repo branch? Does the secondary detection work on NX?