深度学习常用评价指标汇总

Justin_JGT

已于 2024-04-03 10:52:26 修改

阅读量329

点赞数 1

分类专栏： python 深度学习文章标签：深度学习人工智能 pytorch python

于 2024-04-02 14:52:53 首次发布

本文链接：https://blog.csdn.net/Justin_JGT/article/details/137268063

版权

深度学习同时被 2 个专栏收录

11 篇文章 0 订阅

订阅专栏

python

9 篇文章 0 订阅

订阅专栏

一、2D图像分割任务

1.像素精度 (Pixel Accuracy, PA)

$PA = \frac{\sum_{i=0}^{k}P_{ii}}{\sum_{i=0}^{k}\sum_{j=0}^{k}P_{ij}}$

2.平均像素精度(mean Pixel Accuracy, mPA)

每个类内被正确分类像素数的比例，之后求所有类的平均，k为类别数，+1为背景

$mPA = \frac{1}{k+1}\sum_{i=0}^{k}\frac{P_{ii}}{\sum_{j=0}^{k}P_{ij}}$

3.平均交并比(mean Intersection over Union, mIoU)

计算两个集合的交集和并集之比，在每个类上求IoU，之后取平均

$mIoU = \frac{1}{k+1}\sum_{i=0}^{k}\frac{P_{ii}}{\sum_{j=0}^{k}P_{ij} + \sum_{j=0}^{k}P_{ji} - P_{ii}}$

二、3D点云分割任务

1.平均交并比

代码示例（两种方法代码）

"""计算一个批次下的mIoU
"""
import numpy as np


NUM_CLASSES = 17
total_seen_class = [0 for _ in range(NUM_CLASSES)]
total_intersection_class = [0 for _ in range(NUM_CLASSES)]
total_union_class = [0 for _ in range(NUM_CLASSES)]
# label为标签真值数组，pred为标签预测数组
for index in range(NUM_CLASSES):
    total_seen_class[index] += np.sum((label == index))                             # 求该index类总元素个数
    total_intersection_class[index] += np.sum((pred == index) & (label == index))   # 求真值为index且同样预测为index的元素个数，对应于IoU公式中的分子————交
    total_union_class[index] += np.sum(((pred == index) | (label == index)))        # 求真值为index或者预测为index的元素个数，对应于IoU公式中的分母————并
mIoU = np.mean(np.array(total_intersection_class) / (np.array(total_union_class, dtype=np.float) + 1e-6))



"""计算每一个批次batch的mIoU, acc
"""
import numpy as np

num_classes = 17
batchs = target.shape[0]

# 计算acc
correct = pred.eq(target.data).cpu().sum()

# 计算mIoU
shape_ious = []
for batch_idx in range(batchs):     # target.shape是batch大小
    parts = range(num_classes)
    class_ious = []
    for part in parts:
        I = np.sum(np.logical_and(pred[batch_idx] == part, target[batch_idx] == part))
        U = np.sum(np.logical_or(pred[batch_idx] == part, target[batch_idx] == part))
        if U == 0:
            iou = 1 #If the union of groundtruth and prediction points is empty, then count part IoU as 1
        else:
            iou = I / float(U)
        class_ious.append(iou)
    pass        # 该对象，每一类的IoU计算完毕
    shape_ious.append(np.mean(class_ious))
    mIoU = np.mean(shape_ious)
    acc = correct.item()/float(batchs * 50000)
pass