NVIDIA-AI-IOT/yolo_deepstream

Issues

• apply_custom_rules_to_quantizer 这个函数的作用和意义是什么？

  #59 opened 21 days ago by scuizhibin
  0

• Can this QAT model fit the original YOLOv7's detect.py/test.py ?

  #58 opened a month ago by RonaldYuren
  0

• Cloud Message (Kafka) Configurations for YOLO models

  #57 opened a month ago by tunahanertekin
  0

• YOLOv5s PQT/QAT - Getting 0% mAP in TensorRT int8 .engine models

  #56 opened 3 months ago by olibartfast
  1

• yolov8 + yolo-nas support

  #55 opened 4 months ago by IamShubhamGupto
  0

• About yolov7_qat, report a bug for cmd_sensitive_analysis in qat.py

  #45 opened a year ago by darrenzhang1007
  2

• Trtexec multi-source (streams) and multi-batch performance test failed

  #47 opened a year ago by YunghuiHsu
  1

• batch inference fps calculation

  #40 opened 4 months ago by victorzhu-epirus
  2

• shared memory using Jetson devices

  #39 opened 4 months ago by jjzhu
  2

• how to detect mutil rtsp streams？ how to change the config？ when i use 2 rtsp steams,its fps got very low. the method i used is one rtsp - one [source] - one[sinlk]

  #29 opened 4 months ago by lzh1998-jansen
  5

• Yolov7 instance segmentation with deepstream?

  #34 opened 4 months ago by aurelm95
  3

• Video Artifacts During Streaming with DeepStream

  #54 opened 4 months ago by GDbbq
  0

• [YOLOV7-QAT] Cannot convert onnx to trt engine

  #53 opened 6 months ago by HoangTienDuc
  4

• yolov5 qat Add graph still use useless data conversion node.

  #52 opened 8 months ago by maro-jeon
  1

• QAT with multiple GPUs?

  #49 opened 10 months ago by aidevmin
  1

• How do I use qat-yolov5.py?

  #51 opened 10 months ago by hujhcv
  0

• YOLOv7 EfficientNMS - Num Classes

  #50 opened 10 months ago by levipereira
  0

• Yolo v7 Object ID

  #48 opened a year ago by pipidx
  0

• About converting YOLOv7 QAT model to TensorRT engine(failed for dynamic-batch setting)

  #46 opened a year ago by YunghuiHsu
  1

• yolov7_qat

  #41 opened a year ago by junghyun-avikus
  1

• Yolov7-QAT: Different Graph exported in PTQ int8 compare with the guide

  #42 opened a year ago by Jackforward
  1

• Hang issue in Tesla T4 GPU

  #44 opened a year ago by nawinks
  1

• How to auto insert qdq in shortcut branch of network with residual structure ?

  #38 opened a year ago by lix19937
  2

• Lower Performance with Yolov7-Tiny Quantization

  #43 opened a year ago by farukoruc
  2

• during inference i get below error on custom yolov4 model . Could someone help

  #25 opened a year ago by h9945394143
  2

• What are topk and keeptopk parameters?

  #26 opened a year ago by DJT777
  1

• How to dynamically modify the model at runtime? For example, when you use yolov5 for one time, you will automatically switch to another model yolov7 after a period of time?

  #28 opened a year ago by flyingfish0918
  1

• Can you make a version of yolox QAT ？

  #32 opened a year ago by DWendou
  1

• export onnx error

  #31 opened a year ago by yuanl15
  2

• Efficient NMS option exporting to ONNX

  #33 opened a year ago by labar90
  1

• yolov7 Error Code 3: API Usage Error (pamameter check failed at: runtime/rt/runtime.cpp)

  #37 opened a year ago by jjzhu
  2

• No module named 'trex'

  #35 opened a year ago by Levi-zhan
  2

• Compile nvdsparsebbox_Yolo.cpp Error

  #16 opened 3 years ago by akashzade
  0

• error when build code.

  #12 opened 3 years ago by SokPhanith
  1

• The Python-deepStream API implements YOLOV4，Multichannel RTSP video stream inference cannot run

  #24 opened 2 years ago by zhidk
  1

• [Feature Request] Add support for Deepstream-6.0 (maybe?)

  #20 opened 3 years ago by DusKing1
  7

• Different throughput running deepstream vs trtexec mode

  #10 opened 3 years ago by vilmara
  0

• How to convert YOLOv4 Pytorch-ONNX --> TensorRT engine INT8 mode with INT8 calibration and Dynamic Shape

  #11 opened 3 years ago by vilmara
  0

• Why in the config files it is recommended batch size-size=1?

  #9 opened 3 years ago by vilmara
  0

• Plugin is not working on TX2 NX for Yolo V4

  #23 opened 2 years ago by caruofc
  0

• Performance report for tensorrt_yolov4

  #8 opened 3 years ago by jstumpin
  3

• when running deepstream_yolov4 readme 3.3 ,its let me copy the tensorRT engine ,but i don't know where is this engine ,could somebody tell me please?

  #19 opened 3 years ago by fratou
  0

• Where is the anchor of yolov4 handled?

  #13 opened 3 years ago by imerse
  0

• Using NHWC format instead of NCHW for deepstream

  #18 opened 3 years ago by romil611
  0

• [E] [TRT] ../rtSafe/cuda/cudaConvolutionRunner.cpp (457) - Cudnn Error in execute: 3 (CUDNN_STATUS_BAD_PARAM)

  #15 opened 3 years ago by daliel
  0

• [Solution] TensorRT 8.0.1 engine for YOLOv4 in standalone mode

  #21 opened 3 years ago by frenky-strasak
  0

• Deepstream Windows Version

  #27 opened 2 years ago by spacewalk01
  1

• _pickle.UnpicklingError: invalid load key, '<'.

  #22 opened 2 years ago by mfoglio
  1

• Run sample error using DeepStream 5.1 and YOLOv4

  #17 opened 3 years ago by rusubbiz-muzkaq
  1

• Deepstream-app with YOLOv4 ONNX model + BatchedNMSPlugin

  #14 opened 3 years ago by frenky-strasak
  1