90、迁移yolov11-seg模型到全系列昇腾，并在310P3进行深度优化性能

基本思想：迁移yolov11-seg模型到昇腾800 9000上版本信息/usr/bin/python3 /home/ubuntu/PycharmProjects/PythonProject1/AAAimage.py Ultralytics 8.3.202 🚀 Python-3.8.10 torch-2.4.1+cu118 CPU (Intel Core(TM) i5-10400F 2.90GHz) YOLO11n-seg summary (fused): 113 layers, 2,868,664 parameters, 0 gradients, 10.4 GFLOPs PyTorch: starting from 'yolo11n-seg.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) ((1, 116, 8400), (1, 32, 160, 160)) (5.9 MB) ONNX: starting export with onnx 1.17.0 opset 11... ONNX: slimming with onnxslim 0.1.68... ONNX: export success ✅ 1.3s, saved as 'yolo11n-seg.onnx' (11.2 MB) Export complete (1.9s) Results saved to /home/ubuntu/PycharmProjects/PythonProject1 Predict: yolo predict task=segment model=yolo11n-seg.onnx imgsz=640 Validate: