yolov8 默认支持BGR三通道图像输入,但是在很多工业场景下,存在很多灰度图像的场景,因此对yolov8代码做一些修改以支持单通道图像输入,满足项目实际需求。
修改后的代码如下:
https://github.com/shanglianlm0525/ultralytics
训练/推理时,只需要在输入参数中 添加 ch=1 即可。
训练
from ultralytics import YOLO
# Load a model
model = YOLO('yolov8n.yaml') # build a new model from YAML
model = YOLO('yolov8n.pt') # load a pretrained model (recommended for training)
model = YOLO('yolov8n.yaml').load('yolov8n.pt') # build from YAML and transfer weights
# Train the model
model.train(data='coco128.yaml', epochs=100, imgsz=640, ch=1)
推理
from ultralytics import YOLO
# Load a pretrained YOLOv8n model
model = YOLO('yolov8n.pt')
# Run inference on 'bus.jpg' with arguments
model.predict('bus.jpg', save=True, imgsz=320, conf=0.5, ch=1)