1.创建文件夹：
YOLOv8开源地址 -- ultralytics-main文件下载链接：GitHub - ultralytics/ultralytics: NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite
其余文件由代码生成。
数据集下载地址：Fruit Detection | Kaggle
2.运行split_train_val.py 代码内容 ：
# 划分train、test、val文件
import os
import random
import argparse
parser = argparse.ArgumentParser()
# xml文件的地址，根据自己的数据进行修改 xml一般存放在Annotations下
parser.add_argument('--xml_path', default='D:/ultralytics-main/ultralytics-main/paper_data/Annotations', type=str, help='input txt label path')
# 数据集的划分，地址选择自己数据下的ImageSets/Main
parser.add_argument('--txt_path', default='D:/ultralytics-main/ultralytics-main/paper_data/ImageSets/Main', type=str, help='output txt label path')
opt = parser.parse_args()
trainval_percent = 1.0
train_percent = 8/9
xmlfilepath = opt.xml_path
txtsavepath = opt.txt_path
total_xml = os.listdir(xmlfilepath)
if not os.path.exists(txtsavepath):
os.makedirs(txtsavepath)
num = len(total_xml)
list_index = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list_index, tv)
train = random.sample(trainval, tr)
file_trainval = open(txtsavepath + '/trainval.txt', 'w')
file_test = open(txtsavepath + '/test.txt', 'w')
file_train = open(txtsavepath + '/train.txt', 'w')
file_val = open(txtsavepath + '/val.txt', 'w')
for i in list_index:
name = total_xml[i][:-4] + '\n'
if i in trainval:
file_trainval.write(name)
if i in train:
file_train.write(name)
else:
file_val.write(name)
else:
file_test.write(name)
file_trainval.close()
file_train.close()
file_val.close()
file_test.close()3.运行voc_label.py 代码内容：
import xml.etree.ElementTree as ET
import os
from os import getcwd
sets = ['train', 'val', 'test']
classes = ["banana", "snake fruit", "dragon fruit", "pineapple"] # 改成自己的类别
abs_path = os.getcwd()
print(abs_path)
def convert(size, box):
dw = 1. / (size[0])
dh = 1. / (size[1])
x = (box[0] + box[1]) / 2.0 - 1
y = (box[2] + box[3]) / 2.0 - 1
w = box[1] - box[0]
h = box[3] - box[2]
x = x * dw
w = w * dw
y = y * dh
h = h * dh
return x, y, w, h
def convert_annotation(image_id):
in_file = open('D:/ultralytics-main/ultralytics-main/paper_data/Annotations/%s.xml' % (image_id), encoding='UTF-8')
out_file = open('D:/ultralytics-main/ultralytics-main/paper_data/labels/%s.txt' % (image_id), 'w')
tree = ET.parse(in_file)
root = tree.getroot()
filename = root.find('filename').text
filenameFormat = filename.split(".")[1]
size = root.find('size')
w = int(size.find('width').text)
h = int(size.find('height').text)
for obj in root.iter('object'):
difficult = obj.find('difficult').text
cls = obj.find('name').text
if cls not in classes or int(difficult) == 1:
continue
cls_id = classes.index(cls)
xmlbox = obj.find('bndbox')
b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
float(xmlbox.find('ymax').text))
b1, b2, b3, b4 = b
# 标注越界修正
if b2 > w:
b2 = w
if b4 > h:
b4 = h
b = (b1, b2, b3, b4)
bb = convert((w, h), b)
out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
return filenameFormat
wd = getcwd()
for image_set in sets:
if not os.path.exists('D:/ultralytics-main/ultralytics-main/paper_data/labels/'):
os.makedirs('D:/ultralytics-main/ultralytics-main/paper_data/labels/')
image_ids = open('D:/ultralytics-main/ultralytics-main/paper_data/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
list_file = open('D:/ultralytics-main/ultralytics-main/paper_data/%s.txt' % (image_set),'w')
for image_id in image_ids:
filenameFormat = convert_annotation(image_id)
list_file.write( 'D:/ultralytics-main/ultralytics-main/paper_data/images/%s.%s\n' % (image_id,filenameFormat))
list_file.close()
4.命令窗代码：
yolo task=detect mode =train model=yolov8s.yaml data=D:\ultralytics-main\ultralytics-main\paper_data\ab.yaml epochs=100 batch=4运行结果：
D:\ultralytics-main\ultralytics-main>yolo task=detect mode =train model=yolov8s.yaml data=D:\ultralytics-main\ultralytics-main\paper_data\ab.yaml epochs=100 batch=4
from n params module arguments
0 -1 1 928 ultralytics.nn.modules.conv.Conv [3, 32, 3, 2]
1 -1 1 18560 ultralytics.nn.modules.conv.Conv [32, 64, 3, 2]
2 -1 1 29056 ultralytics.nn.modules.block.C2f [64, 64, 1, True]
3 -1 1 73984 ultralytics.nn.modules.conv.Conv [64, 128, 3, 2]
4 -1 2 197632 ultralytics.nn.modules.block.C2f [128, 128, 2, True]
5 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2]
6 -1 2 788480 ultralytics.nn.modules.block.C2f [256, 256, 2, True]
7 -1 1 1180672 ultralytics.nn.modules.conv.Conv [256, 512, 3, 2]
8 -1 1 1838080 ultralytics.nn.modules.block.C2f [512, 512, 1, True]
9 -1 1 656896 ultralytics.nn.modules.block.SPPF [512, 512, 5]
10 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
11 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1]
12 -1 1 591360 ultralytics.nn.modules.block.C2f [768, 256, 1]
13 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
14 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1]
15 -1 1 148224 ultralytics.nn.modules.block.C2f [384, 128, 1]
16 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2]
17 [-1, 12] 1 0 ultralytics.nn.modules.conv.Concat [1]
18 -1 1 493056 ultralytics.nn.modules.block.C2f [384, 256, 1]
19 -1 1 590336 ultralytics.nn.modules.conv.Conv [256, 256, 3, 2]
20 [-1, 9] 1 0 ultralytics.nn.modules.conv.Concat [1]
21 -1 1 1969152 ultralytics.nn.modules.block.C2f [768, 512, 1]
22 [15, 18, 21] 1 2147008 ultralytics.nn.modules.head.Detect [80, [128, 256, 512]]
YOLOv8s summary: 225 layers, 11166560 parameters, 11166544 gradients, 28.8 GFLOPs
New https://pypi.org/project/ultralytics/8.0.221 available Update with 'pip install -U ultralytics'
Ultralytics YOLOv8.0.200 Python-3.10.7 torch-2.0.1+cpu CPU (AMD Ryzen 7 4800U with Radeon Graphics)
engine\trainer: task=detect, mode=train, model=yolov8s.yaml, data=D:\ultralytics-main\ultralytics-main\paper_data\ab.yaml, epochs=100, patience=50, batch=4, 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, 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, show=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, vid_stride=1, stream_buffer=False, line_width=None, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, boxes=True, 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, mosaic=1.0, mixup=0.0, copy_paste=0.0, cfg=None, tracker=botsort.yaml, save_dir=runs\detect\train
Overriding model.yaml nc=80 with nc=4
from n params module arguments
0 -1 1 928 ultralytics.nn.modules.conv.Conv [3, 32, 3, 2]
1 -1 1 18560 ultralytics.nn.modules.conv.Conv [32, 64, 3, 2]
2 -1 1 29056 ultralytics.nn.modules.block.C2f [64, 64, 1, True]
3 -1 1 73984 ultralytics.nn.modules.conv.Conv [64, 128, 3, 2]
4 -1 2 197632 ultralytics.nn.modules.block.C2f [128, 128, 2, True]
5 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2]
6 -1 2 788480 ultralytics.nn.modules.block.C2f [256, 256, 2, True]
7 -1 1 1180672 ultralytics.nn.modules.conv.Conv [256, 512, 3, 2]
8 -1 1 1838080 ultralytics.nn.modules.block.C2f [512, 512, 1, True]
9 -1 1 656896 ultralytics.nn.modules.block.SPPF [512, 512, 5]
10 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
11 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1]
12 -1 1 591360 ultralytics.nn.modules.block.C2f [768, 256, 1]
13 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest']
14 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1]
15 -1 1 148224 ultralytics.nn.modules.block.C2f [384, 128, 1]
16 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2]
17 [-1, 12] 1 0 ultralytics.nn.modules.conv.Concat [1]
18 -1 1 493056 ultralytics.nn.modules.block.C2f [384, 256, 1]
19 -1 1 590336 ultralytics.nn.modules.conv.Conv [256, 256, 3, 2]
20 [-1, 9] 1 0 ultralytics.nn.modules.conv.Concat [1]
21 -1 1 1969152 ultralytics.nn.modules.block.C2f [768, 512, 1]
22 [15, 18, 21] 1 2117596 ultralytics.nn.modules.head.Detect [4, [128, 256, 512]]
YOLOv8s summary: 225 layers, 11137148 parameters, 11137132 gradients, 28.7 GFLOPs
TensorBoard: Start with 'tensorboard --logdir runs\detect\train', view at http://localhost:6006/
Freezing layer 'model.22.dfl.conv.weight'
train: Scanning D:\ultralytics-main\ultralytics-main\paper_data\labels... 177 images, 0 backgrounds, 0 corrupt: 100%|██
train: New cache created: D:\ultralytics-main\ultralytics-main\paper_data\labels.cache
val: Scanning D:\ultralytics-main\ultralytics-main\paper_data\labels... 23 images, 0 backgrounds, 0 corrupt: 100%|█████
val: New cache created: D:\ultralytics-main\ultralytics-main\paper_data\labels.cache
Plotting labels to runs\detect\train\labels.jpg...
optimizer: 'optimizer=auto' found, ignoring 'lr0=0.01' and 'momentum=0.937' and determining best 'optimizer', 'lr0' and 'momentum' automatically...
optimizer: AdamW(lr=0.00125, momentum=0.9) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0005), 63 bias(decay=0.0)
Image sizes 640 train, 640 val
Using 0 dataloader workers
Logging results to runs\detect\train
Starting training for 100 epochs...
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
1/100 0G 3.429 4.168 4.378 3 640: 100%|██████████| 45/45 [02:23<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.00059 0.0375 0.000461 7.53e-05
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
2/100 0G 3.26 3.453 4.037 12 640: 100%|██████████| 45/45 [02:23<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.000574 0.05 0.00124 0.000297
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
3/100 0G 3.067 3.385 3.94 7 640: 100%|██████████| 45/45 [02:41<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.00482 0.505 0.0869 0.0272
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
4/100 0G 3.03 3.142 3.756 12 640: 100%|██████████| 45/45 [02:34<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.439 0.389 0.107 0.0437
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
5/100 0G 2.853 2.94 3.59 2 640: 100%|██████████| 45/45 [02:34<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:07<0
all 23 69 0.286 0.126 0.0346 0.00849
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
6/100 0G 2.774 2.647 3.502 12 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.635 0.269 0.118 0.0222
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
7/100 0G 2.664 2.496 3.34 12 640: 100%|██████████| 45/45 [02:26<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.304 0.516 0.431 0.161
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
8/100 0G 2.581 2.298 3.141 10 640: 100%|██████████| 45/45 [02:36<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.532 0.429 0.48 0.213
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
9/100 0G 2.444 2.123 3.049 3 640: 100%|██████████| 45/45 [02:37<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.55 0.768 0.699 0.329
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
10/100 0G 2.34 2.029 2.918 3 640: 100%|██████████| 45/45 [03:30<00:00, 4.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.857 0.478 0.75 0.294
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
11/100 0G 2.303 1.961 2.841 12 640: 100%|██████████| 45/45 [02:36<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.739 0.561 0.831 0.352
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
12/100 0G 2.301 1.988 2.786 5 640: 100%|██████████| 45/45 [02:41<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.779 0.508 0.761 0.367
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
13/100 0G 2.286 1.873 2.751 4 640: 100%|██████████| 45/45 [02:47<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.81 0.768 0.924 0.496
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
14/100 0G 2.281 1.782 2.702 3 640: 100%|██████████| 45/45 [02:40<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.735 0.81 0.906 0.432
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
15/100 0G 2.171 1.689 2.609 5 640: 100%|██████████| 45/45 [02:42<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.754 0.922 0.918 0.511
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
16/100 0G 2.198 1.684 2.616 5 640: 100%|██████████| 45/45 [02:43<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.864 0.668 0.846 0.481
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
17/100 0G 2.157 1.609 2.566 11 640: 100%|██████████| 45/45 [02:42<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.777 0.91 0.93 0.484
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
18/100 0G 2.109 1.533 2.518 5 640: 100%|██████████| 45/45 [02:45<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.851 0.876 0.973 0.532
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
19/100 0G 1.95 1.426 2.4 5 640: 100%|██████████| 45/45 [02:46<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.953 0.947 0.979 0.569
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
20/100 0G 1.985 1.427 2.459 3 640: 100%|██████████| 45/45 [02:45<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.946 0.95 0.983 0.603
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
21/100 0G 1.967 1.424 2.393 4 640: 100%|██████████| 45/45 [02:45<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.926 0.959 0.975 0.586
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
22/100 0G 1.945 1.43 2.378 4 640: 100%|██████████| 45/45 [02:46<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.868 0.95 0.972 0.528
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
23/100 0G 1.909 1.325 2.316 9 640: 100%|██████████| 45/45 [02:45<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.732 0.833 0.733 0.446
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
24/100 0G 1.952 1.385 2.383 8 640: 100%|██████████| 45/45 [02:49<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.871 0.99 0.987 0.6
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
25/100 0G 1.82 1.329 2.279 4 640: 100%|██████████| 45/45 [02:38<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.967 0.975 0.991 0.551
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
26/100 0G 1.843 1.321 2.254 6 640: 100%|██████████| 45/45 [02:37<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.945 0.963 0.974 0.621
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
27/100 0G 1.723 1.285 2.181 3 640: 100%|██████████| 45/45 [02:40<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.937 0.93 0.976 0.633
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
28/100 0G 1.737 1.251 2.179 11 640: 100%|██████████| 45/45 [02:42<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.818 0.912 0.982 0.625
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
29/100 0G 1.685 1.253 2.149 12 640: 100%|██████████| 45/45 [02:39<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.907 0.95 0.962 0.662
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
30/100 0G 1.633 1.148 2.095 3 640: 100%|██████████| 45/45 [02:38<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.92 0.988 0.99 0.672
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
31/100 0G 1.625 1.167 2.05 6 640: 100%|██████████| 45/45 [02:37<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.923 0.984 0.966 0.625
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
32/100 0G 1.618 1.195 2.096 3 640: 100%|██████████| 45/45 [02:38<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.838 0.993 0.969 0.676
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
33/100 0G 1.679 1.207 2.118 5 640: 100%|██████████| 45/45 [02:37<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.991 0.75 0.977 0.662
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
34/100 0G 1.521 1.172 2.013 6 640: 100%|██████████| 45/45 [02:37<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.953 1 0.988 0.695
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
35/100 0G 1.484 1.047 1.95 10 640: 100%|██████████| 45/45 [02:38<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.968 0.981 0.99 0.702
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
36/100 0G 1.507 1.1 1.988 11 640: 100%|██████████| 45/45 [02:36<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.92 0.948 0.983 0.709
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
37/100 0G 1.514 1.123 1.951 5 640: 100%|██████████| 45/45 [02:36<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.914 0.938 0.975 0.677
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
38/100 0G 1.497 1.079 1.974 4 640: 100%|██████████| 45/45 [02:37<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.877 0.993 0.977 0.69
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
39/100 0G 1.467 1.046 1.931 5 640: 100%|██████████| 45/45 [02:36<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.908 0.971 0.952 0.664
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
40/100 0G 1.442 1.052 1.913 8 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.973 0.979 0.991 0.712
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
41/100 0G 1.432 1.035 1.93 7 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.952 0.945 0.993 0.729
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
42/100 0G 1.352 0.9914 1.854 4 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.956 0.998 0.99 0.735
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
43/100 0G 1.361 0.9737 1.854 3 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.942 0.976 0.988 0.719
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
44/100 0G 1.35 1.028 1.874 4 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.941 0.967 0.993 0.736
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
45/100 0G 1.318 0.9836 1.853 2 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.81 1 0.976 0.727
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
46/100 0G 1.321 0.972 1.833 5 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.862 0.991 0.969 0.718
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
47/100 0G 1.322 0.9708 1.828 4 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.928 1 0.99 0.767
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
48/100 0G 1.35 0.9472 1.809 3 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.97 0.975 0.993 0.774
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
49/100 0G 1.316 0.9418 1.778 2 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.959 0.988 0.992 0.759
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
50/100 0G 1.296 0.9306 1.794 5 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.964 0.975 0.992 0.766
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
51/100 0G 1.289 0.9222 1.748 11 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.972 1 0.994 0.746
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
52/100 0G 1.301 0.9169 1.757 6 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.974 1 0.991 0.777
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
53/100 0G 1.3 0.9216 1.784 3 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.984 1 0.995 0.763
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
54/100 0G 1.243 0.9061 1.744 9 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.972 1 0.995 0.747
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
55/100 0G 1.248 0.9066 1.755 4 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.927 0.968 0.991 0.759
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
56/100 0G 1.184 0.8523 1.699 4 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.966 0.988 0.994 0.789
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
57/100 0G 1.21 0.8508 1.678 3 640: 100%|██████████| 45/45 [02:34<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.946 0.997 0.988 0.756
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
58/100 0G 1.23 0.8597 1.706 8 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.896 0.973 0.988 0.763
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
59/100 0G 1.22 0.8403 1.682 3 640: 100%|██████████| 45/45 [02:34<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.927 1 0.994 0.807
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
60/100 0G 1.22 0.8524 1.684 1 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.981 0.995 0.995 0.788
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
61/100 0G 1.192 0.8089 1.639 8 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.982 1 0.995 0.807
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
62/100 0G 1.131 0.7906 1.644 4 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.924 0.972 0.993 0.771
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
63/100 0G 1.104 0.8165 1.632 12 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.98 0.995 0.995 0.794
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
64/100 0G 1.115 0.787 1.59 4 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.964 0.986 0.994 0.794
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
65/100 0G 1.137 0.8069 1.592 3 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.976 1 0.995 0.817
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
66/100 0G 1.1 0.7912 1.622 11 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.925 0.981 0.995 0.795
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
67/100 0G 1.147 0.7932 1.616 8 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.983 1 0.995 0.815
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
68/100 0G 1.041 0.737 1.543 8 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.952 0.984 0.994 0.792
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
69/100 0G 1.12 0.794 1.594 3 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.917 0.988 0.994 0.796
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
70/100 0G 1.075 0.7553 1.556 10 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.982 0.99 0.995 0.823
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
71/100 0G 1.097 0.766 1.601 2 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.987 1 0.995 0.821
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
72/100 0G 1.086 0.7548 1.564 3 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.982 1 0.995 0.846
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
73/100 0G 1.059 0.7505 1.536 6 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.988 1 0.995 0.812
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
74/100 0G 1.055 0.7771 1.559 4 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.984 0.999 0.995 0.822
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
75/100 0G 1.037 0.7189 1.547 3 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.978 0.997 0.995 0.821
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
76/100 0G 1.072 0.7336 1.542 5 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.994 0.993 0.995 0.819
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
77/100 0G 1.04 0.7151 1.522 9 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.987 0.977 0.995 0.823
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
78/100 0G 1.002 0.6845 1.496 7 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.985 1 0.995 0.832
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
79/100 0G 0.9976 0.7083 1.511 3 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.974 1 0.994 0.817
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
80/100 0G 1.024 0.6866 1.471 3 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.961 0.997 0.995 0.827
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
81/100 0G 1.003 0.708 1.517 8 640: 100%|██████████| 45/45 [02:34<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.98 0.987 0.995 0.822
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
82/100 0G 1.005 0.6982 1.483 9 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.982 1 0.995 0.839
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
83/100 0G 1.011 0.6994 1.488 5 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.979 0.997 0.995 0.84
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
84/100 0G 1.003 0.6665 1.473 4 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.979 0.99 0.995 0.829
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
85/100 0G 1.028 0.7083 1.524 6 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.988 1 0.995 0.845
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
86/100 0G 0.9896 0.6647 1.497 4 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.988 1 0.995 0.841
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
87/100 0G 0.9701 0.6515 1.461 7 640: 100%|██████████| 45/45 [02:34<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.99 1 0.995 0.848
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
88/100 0G 0.977 0.6523 1.443 12 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.991 1 0.995 0.847
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
89/100 0G 0.9417 0.6477 1.455 6 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.988 0.998 0.995 0.832
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
90/100 0G 0.9462 0.6527 1.432 7 640: 100%|██████████| 45/45 [02:35<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.99 1 0.995 0.855
Closing dataloader mosaic
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
91/100 0G 0.8118 0.5889 1.335 3 640: 100%|██████████| 45/45 [02:34<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.975 1 0.995 0.85
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
92/100 0G 0.785 0.5849 1.29 3 640: 100%|██████████| 45/45 [02:34<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.932 0.993 0.995 0.836
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
93/100 0G 0.782 0.5619 1.257 3 640: 100%|██████████| 45/45 [161:44:16<00:00,
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.983 0.99 0.995 0.856
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
94/100 0G 0.7927 0.5596 1.321 3 640: 100%|██████████| 45/45 [03:07<00:00, 4.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.986 1 0.995 0.847
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
95/100 0G 0.7747 0.566 1.286 3 640: 100%|██████████| 45/45 [02:58<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.988 1 0.995 0.856
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
96/100 0G 0.7517 0.5521 1.297 3 640: 100%|██████████| 45/45 [02:51<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.989 1 0.995 0.852
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
97/100 0G 0.7576 0.5551 1.271 3 640: 100%|██████████| 45/45 [02:45<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.989 1 0.995 0.857
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
98/100 0G 0.7792 0.5597 1.302 3 640: 100%|██████████| 45/45 [02:53<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:06<0
all 23 69 0.988 1 0.995 0.86
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
99/100 0G 0.7342 0.5362 1.279 3 640: 100%|██████████| 45/45 [02:34<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.989 1 0.995 0.859
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
100/100 0G 0.7403 0.5395 1.291 3 640: 100%|██████████| 45/45 [02:31<00:00, 3.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.988 1 0.995 0.867
100 epochs completed in 166.267 hours.
Optimizer stripped from runs\detect\train\weights\last.pt, 22.5MB
Optimizer stripped from runs\detect\train\weights\best.pt, 22.5MB
Validating runs\detect\train\weights\best.pt...
Ultralytics YOLOv8.0.200 Python-3.10.7 torch-2.0.1+cpu CPU (AMD Ryzen 7 4800U with Radeon Graphics)
YOLOv8s summary (fused): 168 layers, 11127132 parameters, 0 gradients, 28.4 GFLOPs
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:05<0
all 23 69 0.988 1 0.995 0.867
banana 23 13 0.979 1 0.995 0.94
snake fruit 23 23 0.997 1 0.995 0.777
dragon fruit 23 13 0.985 1 0.995 0.888
pineapple 23 20 0.992 1 0.995 0.865
Speed: 2.2ms preprocess, 220.0ms inference, 0.0ms loss, 0.6ms postprocess per image
Results saved to runs\detect\train
Learn more at https://docs.ultralytics.com/modes/train
扫一扫
955
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
