predict模式用于在新圖像或視頻上使用經(jīng)過訓(xùn)練的YOLOv8模型進(jìn)行預(yù)測，在此模式下，模型從checkpoint 文件加載，用戶可以提供圖像或視頻來執(zhí)行推理。模型預(yù)測輸入圖像或視頻中對象的類別和位置。

from ultralytics import YOLO
from PIL import Image
import cv2

model = YOLO("model.pt")
# 接受所有格式-image/dir/Path/URL/video/PIL/ndarray。0用于網(wǎng)絡(luò)攝像頭
results = model.predict(source="0")
results = model.predict(source="folder", show=True) # 展示預(yù)測結(jié)果

# from PIL
im1 = Image.open("bus.jpg")
results = model.predict(source=im1, save=True)  # 保存繪制的圖像

# from ndarray
im2 = cv2.imread("bus.jpg")
results = model.predict(source=im2, save=True, save_txt=True)  # 將預(yù)測保存為標(biāo)簽

# from list of PIL/ndarray
results = model.predict(source=[im1, im2])

YOLOv8預(yù)測模式可以為各種任務(wù)生成預(yù)測，在使用流模式時返回結(jié)果對象列表或結(jié)果對象的內(nèi)存高效生成器。通過在預(yù)測器的調(diào)用方法中傳遞stream=True來啟用流模式。stream=True的流媒體模式應(yīng)用于長視頻或大型預(yù)測源，否則結(jié)果將在內(nèi)存中累積并最終導(dǎo)致內(nèi)存不足錯誤。

inputs = [img, img]  # list of numpy arrays
results = model(inputs, stream=True)  # generator of Results objects

for result in results:
    boxes = result.boxes  # Boxes object for bbox outputs
    masks = result.masks  # Masks object for segmentation masks outputs
    probs = result.probs  # Class probabilities for classification outputs

相關(guān)參數(shù)如下：

YOLOv8可以接受各種輸入源，如下表所示。這包括圖像、URL、PIL圖像、OpenCV、numpy數(shù)組、torch張量、CSV文件、視頻、目錄、全局、YouTube視頻和流。該表指示每個源是否可以在流模式下使用stream=True?以及每個源的示例參數(shù)。

圖像類型

視頻類型

預(yù)測結(jié)果對象包含以下組件：

Results.boxes: — 具有用于操作邊界框的屬性和方法的boxes

Results.masks: — 用于索引掩碼或獲取段坐標(biāo)的掩碼對象

Results.probs: — 包含類概率或logits

Results.orig_img: — 載入內(nèi)存的原始圖像

Results.path： — 包含輸入圖像路徑的路徑

默認(rèn)情況下，每個結(jié)果都由一個torch. Tensor組成，它允許輕松操作：

results = results.cuda()
results = results.cpu()
results = results.to('cpu')
results = results.numpy()

from ultralytics import YOLO
import cv2
from ultralytics.yolo.utils.benchmarks import benchmark

model = YOLO("yolov8-seg.yaml").load('yolov8n-seg.pt')
results = model.predict(r'E:\CS\DL\yolo\yolov8study\bus.jpg')
boxes = results[0].boxes
masks = results[0].masks
probs = results[0].probs 
print(f"boxes:{boxes[0]}")
print(f"masks:{masks.xy }")
print(f"probs:{probs}")

output:

image 1/1 E:\CS\DL\yolo\yolov8study\bus.jpg: 640x480 4 0s, 1 5, 1 36, 25.9ms
Speed: 4.0ms preprocess, 25.9ms inference, 10.0ms postprocess per image at shape (1, 3, 640, 640)
WARNING  'Boxes.boxes' is deprecated. Use 'Boxes.data' instead.
boxes:ultralytics.yolo.engine.results.Boxes object with attributes:

boxes: tensor([[670.1221, 389.6674, 809.4929, 876.5032,   0.8875,   0.0000]], device='cuda:0')   
cls: tensor([0.], device='cuda:0')
conf: tensor([0.8875], device='cuda:0')
data: tensor([[670.1221, 389.6674, 809.4929, 876.5032,   0.8875,   0.0000]], device='cuda:0')    
id: None
is_track: False
orig_shape: tensor([1080,  810], device='cuda:0')
shape: torch.Size([1, 6])
xywh: tensor([[739.8075, 633.0853, 139.3708, 486.8358]], device='cuda:0')
xywhn: tensor([[0.9133, 0.5862, 0.1721, 0.4508]], device='cuda:0')
xyxy: tensor([[670.1221, 389.6674, 809.4929, 876.5032]], device='cuda:0')
xyxyn: tensor([[0.8273, 0.3608, 0.9994, 0.8116]], device='cuda:0')
masks:[array([[     804.94,       391.5],
       [     794.81,      401.62],
       [     794.81,      403.31],
       [     791.44,      406.69],
       ......
probs:None

我們可以使用Result對象的plot()函數(shù)在圖像對象中繪制結(jié)果。它繪制在結(jié)果對象中找到的所有組件（框、掩碼、分類日志等）

annotated_frame = results[0].plot()
# Display the annotated frame
cv2.imshow("YOLOv8 Inference", annotated_frame)
cv2.waitKey()
cv2.destroyAllWindows()

使用OpenCV（cv2）和YOLOv8對視頻幀運(yùn)行推理的Python腳本。

import cv2
from ultralytics import YOLO

# Load the YOLOv8 model
model = model = YOLO("yolov8-seg.yaml").load('yolov8n-seg.pt')

# Open the video file
video_path = "sample.mp4"
cap = cv2.VideoCapture(video_path)

# Loop through the video frames
while cap.isOpened():
    # Read a frame from the video
    success, frame = cap.read()

    if success:
        # Run YOLOv8 inference on the frame
        results = model(frame)

        # Visualize the results on the frame
        annotated_frame = results[0].plot()

        # Display the annotated frame
        cv2.imshow("YOLOv8 Inference", annotated_frame)

        # Break the loop if 'q' is pressed
        if cv2.waitKey(1) & 0xFF == ord("q"):
            break
    else:
        # Break the loop if the end of the video is reached
        break

# Release the video capture object and close the display window
cap.release()
cv2.destroyAllWindows()

文章來源地址http://www.zghlxwxcb.cn/news/detail-458439.html

到了這里，關(guān)于【目標(biāo)檢測】YOLOV8實(shí)戰(zhàn)入門（五）模型預(yù)測的文章就介紹完了。如果您還想了解更多內(nèi)容，請?jiān)谟疑辖撬阉鱐OY模板網(wǎng)以前的文章或繼續(xù)瀏覽下面的相關(guān)文章，希望大家以后多多支持TOY模板網(wǎng)！