長榮中學 AICourse Build Your Own AI

tags: 長榮中學

HackMD：https://hackmd.io/@Titi/HktLJC840

YOLO

You Only Look Once

下載 Miniconda

Miniconda: https://www.anaconda.com/download/success

虛擬環境

Create

$ conda create --name ultralytics-env python=3.8 -y

Enter

$ conda activate ultralytics-env

安裝套件

$ conda install jupyterlab
$ conda install -c conda-forge ultralytics
$ conda install pytorch torchvision torchaudio cpuonly -c pytorch

執行 jupyter lab

$ jupyter lab

Project

• 創資料夾 (workspace)
• 創notebook

物件偵測

測試 YOLO 物件偵測

from ultralytics import YOLO

# Load a model
model = YOLO('yolov8n.pt')  # pretrained YOLOv8n model

# Predict with the model
results = model("https://ultralytics.com/images/bus.jpg")  # predict on an image
results[0].show()

測試 Webcam

import cv2

cap = cv2.VideoCapture(0)
cap.set(3, 640)
cap.set(4, 480)

while True:
    ret, img= cap.read()
    cv2.imshow('Webcam', img)
    if cv2.waitKey(1) == ord('q'):
        break

cap.release()
cv2.destroyAllWindows()

Webcam 進行物件偵測

from ultralytics import YOLO
import cv2
import math 
# start webcam
cap = cv2.VideoCapture(0)
cap.set(3, 640)
cap.set(4, 480)

# model
model = YOLO("yolov8n.pt")

# object classes
names = model.model.names


while True:
    success, img = cap.read()
    results = model(img, stream=True)

    # coordinates
    for r in results:
        boxes = r.boxes

        for box in boxes:
            # bounding box
            x1, y1, x2, y2 = box.xyxy[0]
            x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2) # convert to int values

            # put box in cam
            cv2.rectangle(img, (x1, y1), (x2, y2), (255, 0, 255), 3)

            # confidence
            confidence = math.ceil((box.conf[0]*100))/100
            print("Confidence --->",confidence)

            # class name
            cls = int(box.cls[0])
            print("Class name -->", names[cls])

            # object details
            org = [x1, y1]
            font = cv2.FONT_HERSHEY_SIMPLEX
            fontScale = 1
            color = (255, 0, 0)
            thickness = 2

            cv2.putText(img, names[cls], org, font, fontScale, color, thickness)

    cv2.imshow('Webcam', img)
    if cv2.waitKey(1) == ord('q'):
        break

cap.release()
cv2.destroyAllWindows()

實例分割

測試 YOLO 實例分割

from ultralytics import YOLO

# Load a model
model = YOLO("yolov8n-seg.pt")  # load an official model

# Predict with the model
results = model("https://ultralytics.com/images/bus.jpg")  # predict on an image
results[0].show()

Webcam 進行實例分割

from ultralytics import YOLO
from ultralytics.utils.plotting import Annotator, colors
import cv2
import math 
# start webcam
cap = cv2.VideoCapture(0)
cap.set(3, 640)
cap.set(4, 480)

# Load a model
print("Loading model")
model = YOLO("yolov8n-seg.pt")  # load an official model
names = model.model.names

while True:
    ret, im0 = cap.read()
    if not ret:
        print("Video frame is empty or video processing has been successfully completed.")
        break

    results = model.predict(im0)
    annotator = Annotator(im0, line_width=2)

    if results[0].masks is not None:
        clss = results[0].boxes.cls.cpu().tolist()
        masks = results[0].masks.xy
        for mask, cls in zip(masks, clss):
            annotator.seg_bbox(mask=mask, mask_color=colors(int(cls), True), det_label=names[int(cls)])

    cv2.imshow("instance-segmentation", im0)

    if cv2.waitKey(1) & 0xFF == ord("q"):
        break

cap.release()
cv2.destroyAllWindows()

骨架辨識

測試 YOLO 骨架辨識

from ultralytics import YOLO

# Load a model
model = YOLO("yolov8n-pose.pt")  # load an official model

# Predict with the model
results = model("https://ultralytics.com/images/bus.jpg")  # predict on an image
results[0].show()

Webcam 進行骨架辨識

from ultralytics import YOLO
from ultralytics.utils.plotting import Annotator, colors
import cv2
import math 
# start webcam
cap = cv2.VideoCapture(0)
cap.set(3, 640)
cap.set(4, 480)

# Load a model
print("Loading model")
model = YOLO("yolov8n-pose.pt")  # load an official model
names = model.model.names

while True:
    ret, im0 = cap.read()
    if not ret:
        print("Video frame is empty or video processing has been successfully completed.")
        break

    results = model.predict(im0)
    annotator = Annotator(im0)

    if results[0].keypoints is not None:
        for data in results[0].keypoints.data:
            annotator.kpts(kpts=data)

    cv2.imshow("pose", im0)

    if cv2.waitKey(1) & 0xFF == ord("q"):
        break

cap.release()
cv2.destroyAllWindows()