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

Update YOLOv5-4.0

Browse Source
This commit is contained in:
Marcos Luciano
2021-05-03 21:24:51 -03:00
committed by GitHub
parent ae849d2f8b
commit 18d33d78fd
1 changed files with 11 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
YOLOv5-4.0.md
View File

@@ -48,7 +48,7 @@ git clone -b yolov5-v4.0 https://github.com/wang-xinyu/tensorrtx.git
git clone -b v4.0 https://github.com/ultralytics/yolov5.git git clone -b v4.0 https://github.com/ultralytics/yolov5.git
``` ```
2. Download latest YoloV5 (YOLOv5s, YOLOv5m, YOLOv5l or YOLOv5x) weights to yolov5 folder (example for YOLOv5s) 2. Download latest YoloV5 (YOLOv5s, YOLOv5m, YOLOv5l or YOLOv5x) weights to yolov5/weights directory (example for YOLOv5s)
``` ```
wget https://github.com/ultralytics/yolov5/releases/download/v4.0/yolov5s.pt -P yolov5/weights wget https://github.com/ultralytics/yolov5/releases/download/v4.0/yolov5s.pt -P yolov5/weights
``` ```
@@ -66,6 +66,16 @@ python3 gen_wts.py
yolov5s.wts file will be generated in yolov5 folder yolov5s.wts file will be generated in yolov5 folder
<br />
Note: if you want to generate wts file to another YOLOv5 model (YOLOv5m, YOLOv5l or YOLOv5x), edit get_wts.py file changing yolov5s to your model name
```
model = torch.load('weights/yolov5s.pt', map_location=device)['model'].float() # load to FP32
model.to(device).eval()
f = open('yolov5s.wts', 'w')
```
## ##
### Convert wts file to TensorRT model ### Convert wts file to TensorRT model