入门语义分割-Task1 赛题理解

1.挂载数据集

2.数据标签转化

import numpy as np
import pandas as pd
import cv2

# 将图片编码为rle格式
def rle_encode(im):
    '''
    im: numpy array, 1 - mask, 0 - background
    Returns run length as string formated
    '''
    pixels = im.flatten(order = 'F')
    pixels = np.concatenate([[0], pixels, [0]])
    runs = np.where(pixels[1:] != pixels[:-1])[0] + 1
    runs[1::2] -= runs[::2]
    return ' '.join(str(x) for x in runs)

# 将rle格式进行解码为图片
def rle_decode(mask_rle, shape=(512, 512)):
    '''
    mask_rle: run-length as string formated (start length)
    shape: (height,width) of array to return 
    Returns numpy array, 1 - mask, 0 - background

    '''
    s = mask_rle.split()
    starts, lengths = [np.asarray(x, dtype=int) for x in (s[0:][::2], s[1:][::2])]
    starts -= 1
    ends = starts + lengths
    img = np.zeros(shape[0]*shape[1], dtype=np.uint8)
    for lo, hi in zip(starts, ends):
        img[lo:hi] = 1
    return img.reshape(shape, order='F')

3.读取数据

import pandas as pd
import cv2
train_mask = pd.read_csv('train_mask.csv', sep='\t', names=['name', 'mask'])

# 读取第一张图，并将对于的rle解码为mask矩阵
img = cv2.imread('train/'+ train_mask['name'].iloc[0])
mask = rle_decode(train_mask['mask'].iloc[0])

print(rle_encode(mask) == train_mask['mask'].iloc[0])
# 结果为True

4.评价指标
赛题使用Dice coefficient来衡量选手结果与真实标签的差异性，Dice coefficient可以按像素差异性来比较结果的差异性。Dice coefficient的具体计算方式如下：

                                2∗|X∩Y|/|X|+|Y|

其中X是预测结果，Y为真实标签的结果。当X与Y完全相同时Dice coefficient为1，排行榜使用所有测试集图片的平均Dice coefficient来衡量，分数值越大越好。

标签：coefficient,Task1,rle,mask,赛题,语义,shape,train,np
来源： https://blog.csdn.net/qq_40420929/article/details/113896587