文章目录
📙 Mac 电脑 配置 yolov8 环境
- YOLO 推理测试、小数据集训练，基础版 Mac 即可满足
- 博主这里代码运行的 Mac 版本为 M1 Pro
conda create -n yolopy39 python=3.9
conda activate yolopy39
pip3 install torch torchvision torchaudio
# ultralytics 对 opencv-python 的版本需求如下
pip3 install opencv-python>=4.6.0
# 因此我选择安装的版本如下
pip3 install opencv-python==4.6.0.66
cd Desktop
mkdir moli
cd moli
git clone https://github.com/ultralytics/ultralytics.git
pip install -e .
pwd
/Users/moli/Desktop/moli/ultralytics
📙 代码运行
- https://github.com/ultralytics/ultralytics
- https://docs.ultralytics.com/modes/track/#persisting-tracks-loop
推理测试
yolo predict model=yolov8n.pt source='https://ultralytics.com/images/bus.jpg'
# 输出如下
Matplotlib is building the font cache; this may take a moment.
Downloading https://github.com/ultralytics/assets/releases/download/v8.2.0/yolov8n.pt to 'yolov8n.pt'...
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 6.25M/6.25M [01:34<00:00, 69.6kB/s]
Ultralytics YOLOv8.2.77 🚀 Python-3.9.19 torch-2.2.2 CPU (Apple M1 Pro)
[W NNPACK.cpp:64] Could not initialize NNPACK! Reason: Unsupported hardware.
YOLOv8n summary (fused): 168 layers, 3,151,904 parameters, 0 gradients, 8.7 GFLOPs
Downloading https://ultralytics.com/images/bus.jpg to 'bus.jpg'...
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 134k/134k [00:00<00:00, 470kB/s]
image 1/1 /Users/moli/Desktop/moli/ultralytics/bus.jpg: 640x480 4 persons, 1 bus, 1 stop sign, 221.3ms
Speed: 5.8ms preprocess, 221.3ms inference, 4.0ms postprocess per image at shape (1, 3, 640, 480)
Results saved to /Users/moli/Desktop/moli/ultralytics/runs/detect/predict
模型训练 - 转 onnx
from ultralytics import YOLO
# Load a model
model = YOLO("yolov8n.yaml") # build a new model from scratch
model = YOLO("yolov8n.pt") # load a pretrained model (recommended for training)
# Use the model
model.train(data="coco8.yaml", epochs=3) # train the model
metrics = model.val() # evaluate model performance on the validation set
results = model("https://ultralytics.com/images/bus.jpg") # predict on an image
# 转换 onnx 也是封装好的模块，这里调用传参即可
path = model.export(format="onnx") # export the model to ONNX format
python train_test.py
[W NNPACK.cpp:64] Could not initialize NNPACK! Reason: Unsupported hardware.
Ultralytics YOLOv8.2.77 🚀 Python-3.9.19 torch-2.2.2 CPU (Apple M1 Pro)
engine/trainer: task=detect, mode=train, model=yolov8n.pt, data=coco8.yaml, epochs=3, time=None, patience=100, batch=16, imgsz=640, save=True, save_period=-1, cache=False, device=None, workers=8, project=None, name=train, exist_ok=False, pretrained=True, optimizer=auto, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=10, resume=False, amp=True, fraction=1.0, profile=False, freeze=None, multi_scale=False, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, split=val, save_json=False, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, vid_stride=1, stream_buffer=False, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, embed=None, show=False, save_frames=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, show_boxes=True, line_width=None, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=None, workspace=4, nms=False, lr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=7.5, cls=0.5, dfl=1.5, pose=12.0, kobj=1.0, label_smoothing=0.0, nbs=64, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, bgr=0.0, mosaic=1.0, mixup=0.0, copy_paste=0.0, auto_augment=randaugment, erasing=0.4, crop_fraction=1.0, cfg=None, tracker=botsort.yaml, save_dir=/Users/moli/Desktop/moli/ultralytics/runs/detect/train
Dataset 'coco8.yaml' images not found ⚠️, missing path '/Users/moli/Desktop/moli/datasets/coco8/images/val'
Downloading https://ultralytics.com/assets/coco8.zip to '/Users/moli/Desktop/moli/datasets/coco8.zip'...
100%|███████████████████████████████████████████████████████████████████████████████████████████| 433k/433k [00:03<00:00, 135kB/s]
Unzipping /Users/moli/Desktop/moli/datasets/coco8.zip to /Users/moli/Desktop/moli/datasets/coco8...: 100%|██████████| 25/25 [00:00
Dataset download success ✅ (5.4s), saved to /Users/moli/Desktop/moli/datasets
...
...
Logging results to /Users/moli/Desktop/moli/ultralytics/runs/detect/train
Starting training for 3 epochs...
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
1/3 0G 1.412 2.815 1.755 22 640: 100%|██████████| 1/1 [00:01<00:00, 1.90s/it]
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 1.30
all 4 17 0.613 0.883 0.888 0.616
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
2/3 0G 1.249 2.621 1.441 23 640: 100%|██████████| 1/1 [00:01<00:00, 1.51s/it]
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 2.24
all 4 17 0.598 0.896 0.888 0.618
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
3/3 0G 1.142 4.221 1.495 16 640: 100%|██████████| 1/1 [00:01<00:00, 1.50s/it]
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 2.06
all 4 17 0.58 0.833 0.874 0.613
3 epochs completed in 0.002 hours.
Optimizer stripped from /Users/moli/Desktop/moli/ultralytics/runs/detect/train/weights/last.pt, 6.5MB
Optimizer stripped from /Users/moli/Desktop/moli/ultralytics/runs/detect/train/weights/best.pt, 6.5MB
Validating /Users/moli/Desktop/moli/ultralytics/runs/detect/train/weights/best.pt...
Ultralytics YOLOv8.2.77 🚀 Python-3.9.19 torch-2.2.2 CPU (Apple M1 Pro)
Model summary (fused): 168 layers, 3,151,904 parameters, 0 gradients, 8.7 GFLOPs
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 1.72
all 4 17 0.599 0.898 0.888 0.618
person 3 10 0.647 0.5 0.52 0.29
dog 1 1 0.315 1 0.995 0.597
horse 1 2 0.689 1 0.995 0.598
elephant 1 2 0.629 0.887 0.828 0.332
umbrella 1 1 0.539 1 0.995 0.995
potted plant 1 1 0.774 1 0.995 0.895
Speed: 4.2ms preprocess, 134.0ms inference, 0.0ms loss, 0.8ms postprocess per image
Results saved to /Users/moli/Desktop/moli/ultralytics/runs/detect/train
Ultralytics YOLOv8.2.77 🚀 Python-3.9.19 torch-2.2.2 CPU (Apple M1 Pro)
Model summary (fused): 168 layers, 3,151,904 parameters, 0 gradients, 8.7 GFLOPs
val: Scanning /Users/moli/Desktop/moli/datasets/coco8/labels/val.cache... 4 images, 0 backgrounds, 0 corrupt: 100%|██████████| 4/4
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 1/1 [00:00<00:00, 2.02
all 4 17 0.599 0.898 0.888 0.618
person 3 10 0.647 0.5 0.52 0.29
dog 1 1 0.315 1 0.995 0.597
horse 1 2 0.689 1 0.995 0.598
elephant 1 2 0.629 0.887 0.828 0.332
umbrella 1 1 0.539 1 0.995 0.995
potted plant 1 1 0.774 1 0.995 0.895
Speed: 4.1ms preprocess, 113.0ms inference, 0.0ms loss, 0.7ms postprocess per image
Results saved to /Users/moli/Desktop/moli/ultralytics/runs/detect/train2
image 1/1 /Users/moli/Desktop/moli/ultralytics/ultralytics/assets/bus.jpg: 640x480 4 persons, 1 bus, 188.4ms
Speed: 3.9ms preprocess, 188.4ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 480)
Ultralytics YOLOv8.2.77 🚀 Python-3.9.19 torch-2.2.2 CPU (Apple M1 Pro)
# 开始模型转换
PyTorch: starting from '/Users/moli/Desktop/moli/ultralytics/runs/detect/train/weights/best.pt' with input shape (1, 3, 640, 640) BCHW and output shape(s) (1, 84, 8400) (6.2 MB)
requirements: Ultralytics requirement ['onnx>=1.12.0'] not found, attempting AutoUpdate...
Looking in indexes: http://pypi.douban.com/simple, http://mirrors.aliyun.com/pypi/simple/, https://pypi.tuna.tsinghua.edu.cn/simple/, http://pypi.mirrors.ustc.edu.cn/simple/
Collecting onnx>=1.12.0
Downloading http://mirrors.ustc.edu.cn/pypi/packages/4e/35/abbf2fa3dbb96b430f6e810e3fb7bc042ed150f371cb1aedb47052c40f8e/onnx-1.16.2-cp39-cp39-macosx_11_0_universal2.whl (16.5 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 16.5/16.5 MB 11.4 MB/s eta 0:00:00
Requirement already satisfied: numpy>=1.20 in /Users/moli/opt/anaconda3/envs/yolopy39/lib/python3.9/site-packages (from onnx>=1.12.0) (1.26.4)
Collecting protobuf>=3.20.2 (from onnx>=1.12.0)
Downloading http://mirrors.ustc.edu.cn/pypi/packages/ca/bc/bceb11aa96dd0b2ae7002d2f46870fbdef7649a0c28420f0abb831ee3294/protobuf-5.27.3-cp38-abi3-macosx_10_9_universal2.whl (412 kB)
Installing collected packages: protobuf, onnx
Successfully installed onnx-1.16.2 protobuf-5.27.3
requirements: AutoUpdate success ✅ 22.0s, installed 1 package: ['onnx>=1.12.0']
requirements: ⚠️ Restart runtime or rerun command for updates to take effect
ONNX: starting export with onnx 1.16.2 opset 17...
ONNX: export success ✅ 24.4s, saved as '/Users/moli/Desktop/moli/ultralytics/runs/detect/train/weights/best.onnx' (12.2 MB)
Export complete (26.1s)
Results saved to /Users/moli/Desktop/moli/ultralytics/runs/detect/train/weights
Predict: yolo predict task=detect model=/Users/moli/Desktop/moli/ultralytics/runs/detect/train/weights/best.onnx imgsz=640
Validate: yolo val task=detect model=/Users/moli/Desktop/moli/ultralytics/runs/detect/train/weights/best.onnx imgsz=640 data=/Users/moli/Desktop/moli/ultralytics/ultralytics/cfg/datasets/coco8.yaml
Visualize: https://netron.app
ls runs/detect/train/
F1_curve.png R_curve.png confusion_matrix_normalized.png results.csv train_batch1.jpg val_batch0_pred.jpg
PR_curve.png args.yaml labels.jpg results.png train_batch2.jpg weights
P_curve.png confusion_matrix.png labels_correlogram.jpg train_batch0.jpg val_batch0_labels.jpg
(yolopy39) moli@molideMacBook-Pro ultralytics % ls runs/detect/train/weights
best.onnx best.pt last.pt
视频-目标检测
cat yolov8_1.py
from ultralytics import YOLO
# Load an official or custom model
model = YOLO("yolov8n.pt") # Load an official Detect model
#model = YOLO("yolov8n-seg.pt") # Load an official Segment model
#model = YOLO("yolov8n-pose.pt") # Load an official Pose model
#model = YOLO("path/to/best.pt") # Load a custom trained model
# Perform tracking with the model
source = 'video/people.mp4'
results = model.track(source, show=True) # Tracking with default tracker
调用 Mac 电脑摄像头
from ultralytics import YOLO
# Load an official or custom model
model = YOLO("yolov8n.pt") # Load an official Detect model
#source = 'video/people.mp4'
source = 0
results = model.track(source, show=True) # Tracking with default tracker
# results = model.track(source, show=True, tracker="bytetrack.yaml") # with ByteTrack
PersistingTracksLoop 持续目标跟踪
import cv2
from ultralytics import YOLO
# Load the YOLOv8 model
model = YOLO("yolov8n.pt")
# Open the video file
video_path = "./video/test_people.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 tracking on the frame, persisting tracks between frames
results = model.track(frame, persist=True)
# Visualize the results on the frame
annotated_frame = results[0].plot()
# Display the annotated frame
cv2.imshow("YOLOv8 Tracking", 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()
Plotting Tracks 画轨迹
from collections import defaultdict
import cv2
import numpy as np
from ultralytics import YOLO
# Load the YOLOv8 model
model = YOLO("yolov8n.pt")
# Open the video file
video_path = "./video/test_people.mp4"
cap = cv2.VideoCapture(video_path)
# Store the track history
track_history = defaultdict(lambda: [])
# Loop through the video frames
while cap.isOpened():
# Read a frame from the video
success, frame = cap.read()
if success:
# Run YOLOv8 tracking on the frame, persisting tracks between frames
results = model.track(frame, persist=True)
# Get the boxes and track IDs
boxes = results[0].boxes.xywh.cpu()
track_ids = results[0].boxes.id.int().cpu().tolist()
# Visualize the results on the frame
annotated_frame = results[0].plot()
# Plot the tracks
for box, track_id in zip(boxes, track_ids):
x, y, w, h = box
track = track_history[track_id]
track.append((float(x), float(y))) # x, y center point
if len(track) > 30: # retain 90 tracks for 90 frames
track.pop(0)
# Draw the tracking lines
points = np.hstack(track).astype(np.int32).reshape((-1, 1, 2))
cv2.polylines(annotated_frame, [points], isClosed=False, color=(230, 230, 230), thickness=10)
# Display the annotated frame
cv2.imshow("YOLOv8 Tracking", 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()
Multithreaded Tracking - 多线程运行示例
- 这里加载两个模型，运行两个线程，出现线程拥挤、导致无法弹窗，代码需要进一步修改
import threading
import cv2
from ultralytics import YOLO
def run_tracker_in_thread(filename, model, file_index):
"""
Runs a video file or webcam stream concurrently with the YOLOv8 model using threading.
This function captures video frames from a given file or camera source and utilizes the YOLOv8 model for object
tracking. The function runs in its own thread for concurrent processing.
Args:
filename (str): The path to the video file or the identifier for the webcam/external camera source.
model (obj): The YOLOv8 model object.
file_index (int): An index to uniquely identify the file being processed, used for display purposes.
Note:
Press 'q' to quit the video display window.
"""
video = cv2.VideoCapture(filename) # Read the video file
while True:
ret, frame = video.read() # Read the video frames
# Exit the loop if no more frames in either video
if not ret:
break
# Track objects in frames if available
results = model.track(frame, persist=True)
res_plotted = results[0].plot()
cv2.imshow(f"Tracking_Stream_{file_index}", res_plotted)
key = cv2.waitKey(1)
if key == ord("q"):
break
# Release video sources
video.release()
# Load the models
model1 = YOLO("yolov8n.pt")
model2 = YOLO("yolov8n-seg.pt")
# Define the video files for the trackers
video_file1 = "video/test_people.mp4" # Path to video file, 0 for webcam
#video_file2 = 'video/test_traffic.mp4' # Path to video file, 0 for webcam, 1 for external camera
video_file2 = 0
# Create the tracker threads
tracker_thread1 = threading.Thread(target=run_tracker_in_thread, args=(video_file1, model1, 1), daemon=True)
tracker_thread2 = threading.Thread(target=run_tracker_in_thread, args=(video_file2, model2, 2), daemon=True)
# Start the tracker threads
tracker_thread1.start()
tracker_thread2.start()
# Wait for the tracker threads to finish
tracker_thread1.join()
tracker_thread2.join()
# Clean up and close windows
cv2.destroyAllWindows()
📙 YOLO 系列实战博文汇总如下
🟦 YOLO 理论讲解学习篇
🟧 Yolov5 系列
🟨 YOLOX 系列
🟦 Yolov3 系列
- 💙 yolov3（darknet ）训练 - 测试 - 模型转换❤️darknet 转 ncnn 之C++运行推理❤️【yolov3 实战一览】
- 💙 YOLOv3 ncnn 模型 yolov3-spp.cpp ❤️【YOLOv3之Ncnn推理实现———附代码】