thebears/deepstream_yolo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

New features

Browse Source 
- Added support for INT8 calibration
- Added support for non square models
- Updated mAP comparison between models
- Minor fixes
This commit is contained in:
Marcos Luciano
2021-06-18 00:33:07 -03:00
committed by GitHub
parent cbd9675dc2
commit 80b1c61488
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
readme.md
View File

@@ -190,7 +190,7 @@ deepstream-app -c deepstream_app_config.txt
Note: NVIDIA recommends at least 500 images to get a good accuracy. In this example I used 1000 images to get better accuracy (more images = more accuracy). Higher INT8_CALIB_BATCH_SIZE values will increase the accuracy and calibration speed. Set it according to you GPU memory. This process can take a long time. The calibration isn't available for YOLOv5 models. Note: NVIDIA recommends at least 500 images to get a good accuracy. In this example I used 1000 images to get better accuracy (more images = more accuracy). Higher INT8_CALIB_BATCH_SIZE values will increase the accuracy and calibration speed. Set it according to you GPU memory. This process can take a long time. The calibration isn't available for YOLOv5 models.
### ##
### mAP/FPS comparison between models ### mAP/FPS comparison between models