model exporter

conversion_tools/model_exporter.py

@@ -0,0 +1,39 @@
+# c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))
+# cv2.rectangle(img, c1, c2, color, thickness=2, lineType=cv2.LINE_AA)
+# [batch size, channel number, height, width]
+# cv2.dnn.NMSBoxes
+# input shape (1,3,640,640) BCHW
+# output shape (1,5,8400)
+
+from ultralytics import YOLO
+
+# Load a model
+model = YOLO("yolov8n.pt")  # load an official model
+model = YOLO("path/to/best.pt")  # load a custom trained model
+
+# Export the model
+model.export(format="onnx")
+
+from ultralytics import YOLO
+
+# Load the YOLOv8 model
+model = YOLO("yolov8n.pt")
+
+# Export the model to TensorRT format
+model.export(format="engine")  # creates 'yolov8n.engine'
+
+# Load the exported TensorRT model
+tensorrt_model = YOLO("yolov8n.engine")
+
+# Run inference
+results = tensorrt_model("https://ultralytics.com/images/bus.jpg")
+
+# logging style:
+# PyTorch: starting from '/home/user/ROS/models/maize/Maize.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 5, 8400) (5.9 MB)
+# ONNX: starting export with onnx 1.16.2 opset 12...
+# ONNX: export success ✅ 1.7s, saved as '/home/user/ROS/models/maize/Maize.onnx' (11.7 MB)
+# Export complete (3.8s)
+# Results saved to /home/user/ROS/models/maize
+# Predict:         yolo predict task=detect model=/home/user/ROS/models/maize/Maize.onnx imgsz=640  
+# Validate:        yolo val task=detect model=/home/user/ROS/models/maize/Maize.onnx imgsz=640 data=config.yaml  
+

conversion_tools/model_inference.py

@@ -0,0 +1,108 @@
+# stream off:
+from ultralytics import YOLO
+
+# Load a model
+model = YOLO("yolov8n.pt")  # pretrained YOLOv8n model
+
+# Run batched inference on a list of images
+results = model(["image1.jpg", "image2.jpg"])  # return a list of Results objects
+
+# Process results list
+for result in results:
+    boxes = result.boxes  # Boxes object for bounding box outputs
+    masks = result.masks  # Masks object for segmentation masks outputs
+    keypoints = result.keypoints  # Keypoints object for pose outputs
+    probs = result.probs  # Probs object for classification outputs
+    obb = result.obb  # Oriented boxes object for OBB outputs
+    result.show()  # display to screen
+    result.save(filename="result.jpg")  # save to disk
+
+# stream on:
+from ultralytics import YOLO
+
+# Load a model
+model = YOLO("yolov8n.pt")  # pretrained YOLOv8n model
+
+# Run batched inference on a list of images
+results = model(["image1.jpg", "image2.jpg"], stream=True)  # return a generator of Results objects
+
+# Process results generator
+for result in results:
+    boxes = result.boxes  # Boxes object for bounding box outputs
+    masks = result.masks  # Masks object for segmentation masks outputs
+    keypoints = result.keypoints  # Keypoints object for pose outputs
+    probs = result.probs  # Probs object for classification outputs
+    obb = result.obb  # Oriented boxes object for OBB outputs
+    result.show()  # display to screen
+    result.save(filename="result.jpg")  # save to disk
+
+
+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)
+
+from ultralytics import YOLO
+
+# Load a pretrained YOLOv8n model
+model = YOLO("yolov8n.pt")
+
+# Run inference on an image
+results = model("bus.jpg")  # results list
+
+# View results
+for r in results:
+    print(r.boxes)  # print the Boxes object containing the detection bounding boxes
+
+from PIL import Image
+
+from ultralytics import YOLO
+
+# Load a pretrained YOLOv8n model
+model = YOLO("yolov8n.pt")
+
+# Run inference on 'bus.jpg'
+results = model(["bus.jpg", "zidane.jpg"])  # results list
+
+# Visualize the results
+for i, r in enumerate(results):
+    # Plot results image
+    im_bgr = r.plot()  # BGR-order numpy array
+    im_rgb = Image.fromarray(im_bgr[..., ::-1])  # RGB-order PIL image
+
+    # Show results to screen (in supported environments)
+    r.show()
+
+    # Save results to disk
+    r.save(filename=f"results{i}.jpg")
+
+import cv2
+from ultralytics import YOLO
+import time
+
+model = YOLO("/home/user/ROS/models/maize/Maize.engine")
+image = cv2.imread("/home/user/ROS/assets/maize/IMG_1822_14.JPG")
+
+sum = 0
+# stream = True?
+for _ in range(100):
+    tic = time.perf_counter_ns()
+    result = model.predict(
+        image,  # batch=8 of the same image
+        verbose=False,
+        device="cuda",
+    )
+    elapsed_time = (time.perf_counter_ns() - tic) / 1e6
+    print(f"Elapsed time: {(elapsed_time):.2f} ms")
+    sum += elapsed_time
+    annotated_frame = result[0].plot()
+    cv2.imshow("YOLOv8 Inference", annotated_frame)
+    if cv2.waitKey(1) & 0xFF == ord("q"):
+            break
+
+avearage_time = (sum - 2660) / 100
+print(f"Average time: {avearage_time:.2f} ms")
+cv2.destroyAllWindows()