介绍
在机器视觉领域的深度学习中，每个数据集都有一份标注好的数据用于训练神经网络。
为了节省空间，很多数据集的标注文件使用RLE的格式。
但是神经网络的输入一定是一张图片，为此必须把RLE格式的文件转变为图像格式。
图像格式主要又分为 .jpg 和 .png 两种格式，其中label数据一定不能使用 .jpg，因为它因为压缩算算法的原因，会造成图像失真，图像各个像素的值可能会发生变化。分割任务的数据集的 label 图像中每一个像素都代表了该像素点所属的类别，所以这样的失真是无法接受的。为此只能使用 .png 格式作为label，pascol voc 和 coco 数据集正是这样做的。
1.PNG2RLE
PNG格式转RLE格式
#!---- coding: utf- ---- import numpy as np
def rle_encode(binary_mask):
'''
binary_mask: numpy array, 1 - mask, 0 - background
Returns run length as string formated
'''
pixels = binary_mask.flatten()
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)
2.RLE2PNG
RLE格式转PNG格式
#!--*-- coding: utf- --*--
import numpy as np
def rle_decode(mask_rle, shape):
'''
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
binary_mask = np.zeros(shape[0] * shape[1], dtype=np.uint8)
for lo, hi in zip(starts, ends):
binary_mask[lo:hi] = 1
return binary_mask.reshape(shape)
3.示例
'''
RLE: Run-Length Encode
'''
from PIL import Image
import numpy as np
def __main__():
maskfile = '/path/to/test.png'
mask = np.array(Image.open(maskfile))
binary_mask = mask.copy()
binary_mask[binary_mask <= 127] = 0
binary_mask[binary_mask > 127] = 1
# encode
rle_mask = rle_encode(binary_mask)
# decode
binary_mask_decode = self.rle_decode(rle_mask, binary_mask.shape[:2])
4.完整代码如下
'''
RLE: Run-Length Encode
'''
#!--*-- coding: utf- --*--
import numpy as np
from PIL import Image
import matplotlib.pyplot as plt
# M1:
class general_rle(object):
'''
ref.: https://www.kaggle.com/stainsby/fast-tested-rle
'''
def __init__(self):
pass
def rle_encode(self, binary_mask):
pixels = binary_mask.flatten()
# We avoid issues with '1' at the start or end (at the corners of
# the original image) by setting those pixels to '0' explicitly.
# We do not expect these to be non-zero for an accurate mask,
# so this should not harm the score.
pixels[0] = 0
pixels[-1] = 0
runs = np.where(pixels[1:] != pixels[:-1])[0] + 2
runs[1::2] = runs[1::2] - runs[:-1:2]
return runs
def rle_to_string(self, runs):
return ' '.join(str(x) for x in runs)
def check(self):
test_mask = np.asarray([[0, 0, 0, 0],
[0, 0, 1, 1],
[0, 0, 1, 1],
[0, 0, 0, 0]])
assert rle_to_string(rle_encode(test_mask)) == '7 2 11 2'
# M2:
class binary_mask_rle(object):
'''
ref.: https://www.kaggle.com/paulorzp/run-length-encode-and-decode
'''
def __init__(self):
pass
def rle_encode(self, binary_mask):
'''
binary_mask: numpy array, 1 - mask, 0 - background
Returns run length as string formated
'''
pixels = binary_mask.flatten()
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)
def rle_decode(self, mask_rle, shape):
'''
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
binary_mask = np.zeros(shape[0] * shape[1], dtype=np.uint8)
for lo, hi in zip(starts, ends):
binary_mask[lo:hi] = 1
return binary_mask.reshape(shape)
def check(self):
maskfile = '/path/to/test.png'
mask = np.array(Image.open(maskfile))
binary_mask = mask.copy()
binary_mask[binary_mask <= 127] = 0
binary_mask[binary_mask > 127] = 1
# encode
rle_mask = self.rle_encode(binary_mask)
# decode
binary_mask2 = self.rle_decode(rle_mask, binary_mask.shape[:2])到此这篇关于Python实现RLE格式与PNG格式互转的文章就介绍到这了,更多相关Python RLE转PNG内容请搜索编程网以前的文章或继续浏览下面的相关文章希望大家以后多多支持编程网！
