YOLOv8训练时根据results.cvs画出最终结果图

Guo9898

已于 2024-09-14 09:35:52 修改

阅读量2.2k

点赞数 6

分类专栏： Yolov8 文章标签： YOLO python 人工智能

于 2024-03-22 16:42:10 首次发布

本文链接：https://blog.csdn.net/Guo9898/article/details/136945625

版权

Yolov8 专栏收录该内容

11 篇文章

订阅专栏

博客涉及YOLO和Python在人工智能领域的应用，但具体内容缺失。YOLO是目标检测算法，Python是常用编程语言，二者结合可推动人工智能发展。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

import csv
import matplotlib.pyplot as plt

# 读取结果文件
results_file = r"F:\yolov8\ultralytics-main\runs\train\exp\results.csv"
data = {
    'box': [],
    'cls': [],
    'dfl': [],
    'p': [],
    'r': [],
    'val_box': [],
    'val_cls': [],
    'val_dfl': [],
    'map@0.5': [],
    'map@0.5:0.95': []
}

with open(results_file, 'r') as f:
    reader = csv.reader(f)
    next(reader)  # 跳过文件头部分
    for line in reader:
        data['box'].append(float(line[1]))
        data['cls'].append(float(line[2]))
        data['dfl'].append(float(line[3]))
        data['p'].append(float(line[4]))
        data['r'].append(float(line[5]))
        data['val_box'].append(float(line[8]))
        data['val_cls'].append(float(line[9]))
        data['val_dfl'].append(float(line[10]))
        data['map@0.5'].append(float(line[6]))
        data['map@0.5:0.95'].append(float(line[7]))

# 绘制图形
fig, axs = plt.subplots(2, 5, figsize=(20, 10))

# 训练损失
color = 'lightblue'  # 设置点和线的颜色
axs[0, 0].plot(data['box'], linewidth=2, color=color)
axs[0, 0].scatter(range(len(data['box'])), data['box'], s=30, linewidths=0, color=color, label='box_Loss')
axs[0, 0].set_xlabel('Epoch')
axs[0, 0].set_ylabel('box_Loss')
axs[0, 0].legend()

axs[0, 1].plot(data['cls'], linewidth=2, color=color)
axs[0, 1].scatter(range(len(data['cls'])), data['cls'], s=30, linewidths=0, color=color, label='cls_Loss')
axs[0, 1].set_xlabel('Epoch')
axs[0, 1].set_ylabel('cls_Loss')
axs[0, 1].legend()

axs[0, 2].plot(data['dfl'], linewidth=2, color=color)
axs[0, 2].scatter(range(len(data['dfl'])), data['dfl'], s=30, linewidths=0, color=color, label='dfl_Loss')
axs[0, 2].set_xlabel('Epoch')
axs[0, 2].set_ylabel('dfl_Loss')
axs[0, 2].legend()

axs[0, 3].plot(data['p'], linewidth=2, color=color)
axs[0, 3].scatter(range(len(data['p'])), data['p'], s=30, linewidths=0, color=color, label='Precision')
axs[0, 3].set_xlabel('Epoch')
axs[0, 3].set_ylabel('Precision')
axs[0, 3].legend()

axs[0, 4].plot(data['r'], linewidth=2, color=color)
axs[0, 4].scatter(range(len(data['r'])), data['r'], s=30, linewidths=0, color=color, label='Recall')
axs[0, 4].set_xlabel('Epoch')
axs[0, 4].set_ylabel('Recall')
axs[0, 4].legend()


# 验证损失
axs[1, 0].plot(data['val_box'], linewidth=2, color=color)
axs[1, 0].scatter(range(len(data['val_box'])), data['val_box'], s=30, linewidths=0, color=color, label='val_box')
axs[1, 0].set_xlabel('Epoch')
axs[1, 0].set_ylabel('val_box')
axs[1, 0].legend()

axs[1, 1].plot(data['val_cls'], linewidth=2, color=color)
axs[1, 1].scatter(range(len(data['val_cls'])), data['val_cls'], s=30, linewidths=0, color=color, label='val_cls')
axs[1, 1].set_xlabel('Epoch')
axs[1, 1].set_ylabel('val_cls')
axs[1, 1].legend()

axs[1, 2].plot(data['val_dfl'], linewidth=2, color=color)
axs[1, 2].scatter(range(len(data['val_dfl'])), data['val_dfl'], s=30, linewidths=0, color=color, label='val_dfl')
axs[1, 2].set_xlabel('Epoch')
axs[1, 2].set_ylabel('val_dfl')
axs[1, 2].legend()

axs[1, 3].plot(data['map@0.5'], linewidth=2, color=color)
axs[1, 3].scatter(range(len(data['map@0.5'])), data['map@0.5'], s=30, linewidths=0, color=color, label='map@0.5')
axs[1, 3].set_xlabel('Epoch')
axs[1, 3].set_ylabel('map@0.5')
axs[1, 3].legend()

axs[1, 4].plot(data['map@0.5:0.95'], linewidth=2, color=color)
axs[1, 4].scatter(range(len(data['map@0.5:0.95'])), data['map@0.5:0.95'], s=30, linewidths=0, color=color, label='map@0.5:0.95')
axs[1, 4].set_xlabel('Epoch')
axs[1, 4].set_ylabel('map@0.5:0.95')
axs[1, 4].legend()



# 删除空白的子图
# fig.delaxes(axs[0, 4])
# fig.delaxes(axs[1, 4])

fig.tight_layout()

plt.show()