- 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
- 🍖 原作者：K同学啊 | 接辅导、项目定制
- 🚀 文章来源：K同学的学习圈子
一、下载YOLOv8
官网地址：【YOLOv8开源地址】
二、准备工作
在主目录下创建paper_data文件夹，将自己的数据集放入此文件夹。
数据集：
在paper_data文件夹下创建一个包含main空文件夹的ImageSets文件夹。
在paper_data下创建一个split_train_val.py文件，其内容如下：
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='E:/BaiduNetdiskDownload/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='E:/BaiduNetdiskDownload/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()
运行后生成.txt文件。
再创建一个voc_label.py文件，其内容如下：
import xml.etree.ElementTree as ET
import os
from os import getcwd
sets = ['train', 'val', 'test']
classes = ["banana", "snake fruit", "dragon fruit", "pineapple"]
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('E:/BaiduNetdiskDownload/ultralytics-main/paper_data/Annotations/%s.xml' % (image_id), encoding='UTF-8')
out_file = open('E:/BaiduNetdiskDownload/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('E:/BaiduNetdiskDownload/ultralytics-main/paper_data/labels/'):
os.makedirs('E:/BaiduNetdiskDownload/ultralytics-main/paper_data/labels/')
image_ids = open(
'E:/BaiduNetdiskDownload/ultralytics-main/paper_data/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
list_file = open('E:/BaiduNetdiskDownload/ultralytics-main/paper_data/%s.txt' % (image_set), 'w')
for image_id in image_ids:
filenameFormat = convert_annotation(image_id)
list_file.write('E:/BaiduNetdiskDownload/ultralytics-main/paper_data/images/%s.%s\n' % (image_id, filenameFormat))
list_file.close()
运行。
最后生成一个ab.yaml文件，内容如下：
train: ./train.txt
val: ./val.txt
nc: 4
names: ["banana", "snake fruit", "dragon fruit", "pineapple"]
三、运行
在此文件夹下打开cmd，激活环境后在cmd中输入：
yolo task=detect mode =train model=yolov8s.yaml data=E:\BaiduNetdiskDownload\ultralytics-main\paper_data\ab.yaml epochs=100 batch=4
打印如下：
Microsoft Windows [版本 10.0.22621.3007]
(c) Microsoft Corporation。保留所有权利。
E:\BaiduNetdiskDownload\ultralytics-main>conda activate pytorch_env
(pytorch_env) E:\BaiduNetdiskDownload\ultralytics-main>yolo task=detect mode =train model=yolov8s.yaml data=E:\BaiduNetdiskDownload\ultralytics-main\paper_data\ab.yaml epochs=10 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/8.1.2 available 😃 Update with 'pip install -U ultralytics'
Ultralytics YOLOv8.0.221 🚀 Python-3.8.17 torch-2.1.2+cpu CPU (12th Gen Intel Core(TM) i7-12700H)
engine\trainer: task=detect, mode=train, model=yolov8s.yaml, data=E:\BaiduNetdiskDownload\ultralytics-main\paper_data\ab.yaml, epochs=10, patience=50, batch=4, imgsz=640, save=True, save_period=-1, cache=False, device=None, workers=8, project=None, name=train7, 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, vid_stride=1, stream_buffer=False, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, 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, mosaic=1.0, mixup=0.0, copy_paste=0.0, cfg=None, tracker=botsort.yaml, save_dir=runs\detect\train7
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\train7', view at http://localhost:6006/
Freezing layer 'model.22.dfl.conv.weight'
train: Scanning E:\BaiduNetdiskDownload\ultralytics-main\paper_data\labels... 177 images, 0 backgrounds, 0 corrupt: 100
train: New cache created: E:\BaiduNetdiskDownload\ultralytics-main\paper_data\labels.cache
val: Scanning E:\BaiduNetdiskDownload\ultralytics-main\paper_data\labels... 23 images, 0 backgrounds, 0 corrupt: 100%|█
val: New cache created: E:\BaiduNetdiskDownload\ultralytics-main\paper_data\labels.cache
Plotting labels to runs\detect\train7\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\train7
Starting training for 10 epochs...
Closing dataloader mosaic
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
1/10 0G 2.987 4.406 4.395 2 640: 100%|██████████| 45/45 [00:59<00:00, 1.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:02<0
all 23 69 0.000383 0.0278 0.000283 6.28e-05
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
2/10 0G 3.041 3.887 4.048 3 640: 100%|██████████| 45/45 [00:58<00:00, 1.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:02<0
all 23 69 0.000473 0.0139 0.00025 2.5e-05
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
3/10 0G 2.812 3.653 3.851 3 640: 100%|██████████| 45/45 [00:58<00:00, 1.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:02<0
all 23 69 0.00465 0.292 0.0793 0.0374
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
4/10 0G 2.716 3.417 3.687 3 640: 100%|██████████| 45/45 [00:58<00:00, 1.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:02<0
all 23 69 0.0418 0.323 0.105 0.0329
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
5/10 0G 2.638 3.253 3.546 3 640: 100%|██████████| 45/45 [01:00<00:00, 1.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:02<0
all 23 69 0.0551 0.213 0.0887 0.0242
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
6/10 0G 2.479 2.913 3.448 3 640: 100%|██████████| 45/45 [01:00<00:00, 1.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:02<0
all 23 69 0.261 0.434 0.364 0.15
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
7/10 0G 2.373 2.639 3.285 3 640: 100%|██████████| 45/45 [00:57<00:00, 1.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:02<0
all 23 69 0.698 0.47 0.494 0.169
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
8/10 0G 2.271 2.438 3.179 3 640: 100%|██████████| 45/45 [00:57<00:00, 1.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:02<0
all 23 69 0.666 0.348 0.459 0.176
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
9/10 0G 2.194 2.293 3.013 3 640: 100%|██████████| 45/45 [00:56<00:00, 1.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:02<0
all 23 69 0.467 0.679 0.638 0.307
Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size
10/10 0G 2.092 2.183 2.91 3 640: 100%|██████████| 45/45 [00:56<00:00, 1.
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:02<0
all 23 69 0.605 0.6 0.701 0.364
10 epochs completed in 0.170 hours.
Optimizer stripped from runs\detect\train7\weights\last.pt, 22.5MB
Optimizer stripped from runs\detect\train7\weights\best.pt, 22.5MB
Validating runs\detect\train7\weights\best.pt...
Ultralytics YOLOv8.0.221 🚀 Python-3.8.17 torch-2.1.2+cpu CPU (12th Gen Intel Core(TM) i7-12700H)
YOLOv8s summary (fused): 168 layers, 11127132 parameters, 0 gradients, 28.4 GFLOPs
Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 3/3 [00:02<0
all 23 69 0.604 0.6 0.703 0.362
banana 23 13 0.47 0.846 0.806 0.49
snake fruit 23 23 0.678 0.275 0.404 0.139
dragon fruit 23 15 0.721 1 0.987 0.566
pineapple 23 18 0.548 0.278 0.615 0.254
Speed: 0.7ms preprocess, 78.0ms inference, 0.0ms loss, 1.8ms postprocess per image
Results saved to runs\detect\train7
💡 Learn more at https://docs.ultralytics.com/modes/train
（注：环境有些小异常，没有调用GPU，所以使用cpu时epoch数设的较小，见谅。）
1172
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
