1. 启动
2.相关配置
2.1 data.yaml
path: D:/yolo-tool/yaunshen-yolov8/YOLOv8ys/YOLOv8-CUDA10.2/1/datasets/ceshi001
train: images
val: images
names: ['蔡徐坤','篮球']2.2 cfg.yaml
# Ultralytics YOLOv8, GPL-3.0 license
# Default training settings and hyperparameters for medium-augmentation COCO training
task: detect # inference task, i.e. detect, segment, classify
mode: train # YOLO mode, i.e. train, val, predict, export
# Train settings -------------------------------------------------------------------------------------------------------
model: C:\Users\AF5\Desktop\YOLOv8ql\YOLOv8-CPU\1\datasets\qh\pt\train2\weights\best.pt # path to model file, i.e. yolov8n.pt, yolov8n.yaml 模型文件路径
data: C:\Users\AF5\Desktop\YOLOv8ql\YOLOv8-CPU\1\datasets\qh\data.yaml # path to data file, i.e. i.e. coco128.yaml 数据集data文件路径
epochs: 100000 # number of epochs to train for 训练次数，达到这个次数后将终止训练，且无法该模型无法继续训练
patience: 0 # epochs to wait for no observable improvement for early stopping of training 超过这个次数没有提升将自动完成训练
batch: 1 # number of images per batch (-1 for AutoBatch) 批数量，设越大占用显存越多
imgsz: 640 # size of input images as integer or w,h 一般默认640，训练时的图片宽高
save: True # save train checkpoints and predict results
save_period: -1 # Save checkpoint every x epochs (disabled if < 1)
cache: False # True/ram, disk or False. Use cache for data loading
device: # device to run on, i.e. cuda device=0 or device=0,1,2,3 or device=cpu
workers: 0 # number of worker threads for data loading (per RANK if DDP) 勿改，必须为0
project: C:/Users/AF5/Desktop/YOLOv8ql/YOLOv8-CPU/1/datasets/qh/val # project name 勿改
name: train # experiment name 训练完成的文件夹名称
exist_ok: False # whether to overwrite existing experiment
pretrained: False # whether to use a pretrained model
optimizer: SGD # optimizer to use, choices=['SGD', 'Adam', 'AdamW', 'RMSProp']
verbose: True # whether to print verbose output
seed: 0 # random seed for reproducibility
deterministic: True # whether to enable deterministic mode
single_cls: False # train multi-class data as single-class
image_weights: False # use weighted image selection for training
rect: False # support rectangular training if mode='train', support rectangular evaluation if mode='val'
cos_lr: False # use cosine learning rate scheduler
close_mosaic: 10 # disable mosaic augmentation for final 10 epochs
resume: False # resume training from last checkpoint 为True时为继续模型的训练
min_memory: False # minimize memory footprint loss function, choices=[False, True, <roll_out_thr>]
# Segmentation
overlap_mask: True # masks should overlap during training (segment train only)
mask_ratio: 4 # mask downsample ratio (segment train only)
# Classification
dropout: 0.0 # use dropout regularization (classify train only)
# Val/Test settings ----------------------------------------------------------------------------------------------------
val: True # validate/test during training 为True，训练时计算mAP
split: val # dataset split to use for validation, i.e. 'val', 'test' or 'train'
save_json: False # save results to JSON file
save_hybrid: False # save hybrid version of labels (labels + additional predictions)
conf: # object confidence threshold for detection (default 0.25 predict, 0.001 val)
iou: 0.7 # intersection over union (IoU) threshold for NMS
max_det: 300 # maximum number of detections per image
half: False # use half precision (FP16)
dnn: False # use OpenCV DNN for ONNX inference
plots: True # save plots during train/val
# Prediction settings --------------------------------------------------------------------------------------------------
source: C:\Users\AF5\Desktop\YOLOv8ql\YOLOv8-CPU\1\datasets\qh\images\qh174.png # source directory for images or videos 需要进行预测视频或图片的路径
show: False # show results if possible
save_txt: True # save results as .txt file
save_conf: False # save results with confidence scores
save_crop: False # save cropped images with results
hide_labels: False # hide labels
hide_conf: False # hide confidence scores
vid_stride: 1 # video frame-rate stride
line_thickness: 3 # bounding box thickness (pixels)
visualize: False # visualize model features
augment: False # apply image augmentation to prediction sources
agnostic_nms: False # class-agnostic NMS
classes: # filter results by class, i.e. class=0, or class=[0,2,3]
retina_masks: False # use high-resolution segmentation masks
boxes: True # Show boxes in segmentation predictions
# Export settings ------------------------------------------------------------------------------------------------------
format: torchscript # format to export to
keras: False # use Keras
optimize: False # TorchScript: optimize for mobile
int8: False # CoreML/TF INT8 quantization
dynamic: False # ONNX/TF/TensorRT: dynamic axes
simplify: False # ONNX: simplify model
opset: 12 # ONNX: opset version (optional)
workspace: 4 # TensorRT: workspace size (GB)
nms: False # CoreML: add NMS
# Hyperparameters ------------------------------------------------------------------------------------------------------
lr0: 0.01 # initial learning rate (i.e. SGD=1E-2, Adam=1E-3)
lrf: 0.01 # final learning rate (lr0 * lrf)
momentum: 0.937 # SGD momentum/Adam beta1
weight_decay: 0.0005 # optimizer weight decay 5e-4
warmup_epochs: 3.0 # warmup epochs (fractions ok)
warmup_momentum: 0.8 # warmup initial momentum
warmup_bias_lr: 0.1 # warmup initial bias lr
box: 7.5 # box loss gain
cls: 0.5 # cls loss gain (scale with pixels)
dfl: 1.5 # dfl loss gain
fl_gamma: 0.0 # focal loss gamma (efficientDet default gamma=1.5)
label_smoothing: 0.0 # label smoothing (fraction)
nbs: 64 # nominal batch size
hsv_h: 0.015 # image HSV-Hue augmentation (fraction)
hsv_s: 0.7 # image HSV-Saturation augmentation (fraction)
hsv_v: 0.4 # image HSV-Value augmentation (fraction)
degrees: 0.0 # image rotation (+/- deg)
translate: 0.1 # image translation (+/- fraction)
scale: 0.5 # image scale (+/- gain)
shear: 0.0 # image shear (+/- deg)
perspective: 0.0 # image perspective (+/- fraction), range 0-0.001
flipud: 0.0 # image flip up-down (probability)
fliplr: 0.5 # image flip left-right (probability)
mosaic: 1.0 # image mosaic (probability)
mixup: 0.0 # image mixup (probability)
copy_paste: 0.0 # segment copy-paste (probability)
# Custom config.yaml ---------------------------------------------------------------------------------------------------
cfg: # for overriding defaults.yaml
# Debug, do not modify -------------------------------------------------------------------------------------------------
v5loader: False # use legacy YOLOv5 dataloader
# Tracker settings ------------------------------------------------------------------------------------------------------
tracker: botsort.yaml # tracker type, ['botsort.yaml', 'bytetrack.yaml']
2.3 主要代码
import cv2
import time
from ultralytics import YOLO
import json
import numpy as np
def Yolov10Detector(frame, model, image_size, conf_threshold, cap):
results = model.predict(source=frame, imgsz=image_size, conf=conf_threshold)
frame = results[0].plot()
# 获取当前帧的时间
current_time = cap.get(cv2.CAP_PROP_POS_MSEC) / 1000 # 以秒为单位
# 打印所有标签结果及对应的时间
for result in results:
for box in result.boxes:
c = int(box.cls)
name = result.names[c]
print(f"识别到的标签: {name}，对应的时间: {current_time} 秒")
return frame
def main():
image_size = 640 # Adjust as needed
conf_threshold = 0.3 # Adjust as needed
model = YOLO("D:/yolo-workspace/yoloy8-project/model/oneself/best.pt")
source = "C:/Users/wangwei/Desktop/2024-09-18/20240925_115452.mp4" # 0 for webcam
cap = cv2.VideoCapture(source)
while True:
success, frame = cap.read()
start_time = time.time()
if success:
print("读取帧成功！")
if not success:
print("读取帧失败！")
break
modelName = model.names
json.dumps(modelName, ensure_ascii=False)
#print("预检测 识别转json 信息为：" + json.dumps(modelName, ensure_ascii=False))
frame = Yolov10Detector(frame, model, image_size, conf_threshold, cap)
end_time = time.time()
fps = 1 / (end_time - start_time)
framefps = "FPS:{:.2f}".format(fps)
try:
cv2.rectangle(frame, (10, 1), (120, 20), (0, 0, 0), -1)
cv2.putText(frame, framefps, (15, 17), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 255, 255), 2)
except Exception as e:
print("")
cv2.imshow("yolov10-本地摄像头识别", frame) # Display the annotated frame
if cv2.waitKey(1) & 0xFF == ord('q'): # Exit on 'q' key pres:
break
cap.release()
cv2.destroyAllWindows()
main()
3. 模型训练
4.训练结果：
20240926_104219
