
用代码yolov5生成改进前后map曲线对比图,map0.5,map0.5:0.95,很简单,小白都能看懂!
yolov5
yolov5 - Ultralytics YOLOv8的前身,是一个用于目标检测、图像分割和图像分类任务的先进模型。
项目地址:https://gitcode.com/gh_mirrors/yo/yolov5

·
用代码yolov5生成map曲线对比图,map0.5,map0.5:0.95
map曲线对比图
重点csv文件在runs/train/exp中!!
import pandas as pd
import matplotlib.pyplot as plt
# Function to clean column names
def clean_column_names(df):
df.columns = df.columns.str.strip()
df.columns = df.columns.str.replace('\s+', '_', regex=True)
#nonoresult.csv表示原始的结果图,csv文件在runs/train/exp中
original_results = pd.read_csv("noresult.csv")
#yesyesresult.csv表示提高后的结果图,csv文件在runs/train/exp中
improved_results = pd.read_csv("yesresult.csv")
# Clean column names
clean_column_names(original_results)
clean_column_names(improved_results)
# Plot mAP@0.5 curves
plt.figure()
#lable属性为曲线名称,自己可以定义
plt.plot(original_results['metrics/mAP_0.5'], label="Original YOLOv5")
plt.plot(improved_results['metrics/mAP_0.5'], label="Improved YOLOv5")
plt.xlabel("Epoch")
plt.ylabel("mAP@0.5")
plt.legend()
plt.title("mAP@0.5 Comparison")
plt.savefig("mAP_0.5_comparison.png")
# Plot mAP@0.5:0.95 curves
plt.figure()
plt.plot(original_results['metrics/mAP_0.5:0.95'], label="Original YOLOv5")
plt.plot(improved_results['metrics/mAP_0.5:0.95'], label="Improved YOLOv5")
plt.xlabel("Epoch")
plt.ylabel("mAP@0.5:0.95")
plt.legend()
#图的标题
plt.title("mAP@0.5:0.95 Comparison")
#图片名称
plt.savefig("mAP_0.5_0.95_comparison.png")




yolov5 - Ultralytics YOLOv8的前身,是一个用于目标检测、图像分割和图像分类任务的先进模型。
最近提交(Master分支:2 个月前 )
6981c274
Refactor code for speed and clarity
Co-authored-by: UltralyticsAssistant <web@ultralytics.com> 1 个月前
f003c3df
This commit resolves an issue where the save-csv command did not write the CSV header. The code now correctly saves the header in the CSV file.
Signed-off-by: Ali Ghanbari <alighanbari446@gmail.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com> 1 个月前
更多推荐
所有评论(0)