语义分割进行训练时，对于 Caffe 深度框架，需要的数据集处理. 语义分割数据集准备
<h2>Dataset 数据集下载</h2>
# augmented PASCAL VOC
cd $DATASETS
wget http://www.eecs.berkeley.edu/Research/Projects/CS/vision/grouping/semantic_contours/benchmark.tgz # 1.3 GB
tar -zxvf benchmark.tgz
mv benchmark_RELEASE VOC_aug
# original PASCAL VOC 2012
wget http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar # 2 GB
tar -xvf VOCtrainval_11-May-2012.tar
mv VOCdevkit/VOC2012 VOC2012_orig && rm -r VOCdevkit
<h2>Data conversions 数据转换</h2>
- augmented PASCAL VOC 数据集的 ground truth labels 是以 Matlab data files的格式存在的，需要进行转换：
- Step1 定义 mat2png 脚本；
- Step2 转换 mat 成 png.
#!/usr/bin/env python
# Martin Kersner, m.kersner@gmail.com
# 2016/03/17
from future import print_function
import os
import sys
import glob
import scipy.io
from PIL import Image as PILImage
# Mat to png conversion for http://www.cs.berkeley.edu/~bharath2/codes/SBD/download.html
# 'GTcls' key is for class segmentation
# 'GTinst' key is for instance segmentation
def mat2png_hariharan(mat_file, key='GTcls'):
mat = scipy.io.loadmat(mat_file, mat_dtype=True, squeeze_me=True, struct_as_record=False)
return mat[key].Segmentation
def main():
input_path, output_path = process_arguments(sys.argv)
if os.path.isdir(input_path) and os.path.isdir(output_path):
mat_files = glob.glob(os.path.join(input_path, '*.mat'))
convert_mat2png(mat_files, output_path)
else:
help('Input or output path does not exist!n')
def process_arguments(argv):
num_args = len(argv)
input_path = None
output_path = None
if num_args == 3:
input_path = argv[1]
output_path = argv[2]
else:
help()
return input_path, output_path
def convert_mat2png(mat_files, output_path):
if not mat_files:
help('Input directory does not contain any Matlab files!n')
for mat in mat_files:
numpy_img = mat2png_hariharan(mat)
pil_img = PILImage.fromarray(numpy_img)
pil_img.save(os.path.join(output_path, modify_image_name(mat, 'png')))
# Extract name of image from given path, replace its extension with specified one
# and return new name only, not path.
def modify_image_name(path, ext):
return os.path.basename(path).split('.')[0] + '.' + ext
def help(msg=''):
print(msg +
'Usage: python mat2png.py INPUT_PATH OUTPUT_PATHn'
'INPUT_PATH denotes path containing Matlab files for conversion.n'
'OUTPUT_PATH denotes path where converted Png files ar going to be saved.'
, file=sys.stderr)
exit()
if name == '__main__':
main()
cd $DATASETS/VOC_aug/dataset
mkdir cls_png
cd $DATASETSDIR
./mat2png.py $DATASETS/VOC_aug/dataset/cls $DATASETS/VOC_aug/dataset/cls_png
- Caffe的softmax loss函数只能接受一维的 ground truth labels. 但 original PASCAL VOC 2012中的 ground truth labels 是以RGB图像的形式保存的，因此需要降维：
- Step1 定义转换python脚本：convert_labels.py；
- Step2 转换 ground truth labels 为 1D.
#!/usr/bin/env python
#Martin Kersner, m.kersner@gmail.com
#2016/01/25
from future import print_function
import os
import sys
import numpy as np
from skimage.io import imread, imsave
def pascal_palette():
palette = {( 0, 0, 0) : 0 ,
(128, 0, 0) : 1 ,
( 0, 128, 0) : 2 ,
(128, 128, 0) : 3 ,
( 0, 0, 128) : 4 ,
(128, 0, 128) : 5 ,
( 0, 128, 128) : 6 ,
(128, 128, 128) : 7 ,
( 64, 0, 0) : 8 ,
(192, 0, 0) : 9 ,
( 64, 128, 0) : 10,
(192, 128, 0) : 11,
( 64, 0, 128) : 12,
(192, 0, 128) : 13,
( 64, 128, 128) : 14,
(192, 128, 128) : 15,
( 0, 64, 0) : 16,
(128, 64, 0) : 17,
( 0, 192, 0) : 18,
(128, 192, 0) : 19,
( 0, 64, 128) : 20 }
return palette
def convert_from_color_segmentation(arr_3d):
arr_2d = np.zeros((arr_3d.shape[0], arr_3d.shape[1]), dtype=np.uint8)
palette = pascal_palette()
for c, i in palette.items():
m = np.all(arr_3d == np.array(c).reshape(1, 1, 3), axis=2)
arr_2d[m] = i
return arr_2d
def main():
##
ext = '.png'
##
path, txt_file, path_converted = process_arguments(sys.argv)
# Create dir for converted labels
if not os.path.isdir(path_converted):
os.makedirs(path_converted)
with open(txt_file, 'rb') as f:
for img_name in f:
img_base_name = img_name.strip()
img_name = os.path.join(path, img_base_name) + ext
img = imread(img_name)
if (len(img.shape) > 2):
img = convert_from_color_segmentation(img)
imsave(os.path.join(path_converted, img_base_name) + ext, img)
else:
print(img_name + " is not composed of three dimensions, therefore "
"shouldn't be processed by this script.n"
"Exiting." , file=sys.stderr)
exit()
def process_arguments(argv):
if len(argv) != 4:
help()
path = argv[1]
list_file = argv[2]
new_path = argv[3]
return path, list_file, new_path
def help():
print('Usage: python convert_labels.py PATH LIST_FILE NEW_PATHn'
'PATH points to directory with segmentation image labels.n'
'LIST_FILE denotes text file containing names of images in PATH.n'
'Names do not include extension of images.n'
'NEW_PATH points to directory where converted labels will be stored.'
, file=sys.stderr)
exit()
if name == '__main__':
main()
cd $DATASETS/VOC2012_orig
mkdir SegmentationClass_1D
cd $DATASETSDIR
./convert_labels.py $DATASETS/VOC2012_orig/SegmentationClass/ \
$DATASETS/VOC2012_orig/ImageSets/Segmentation/trainval.txt \
$DATASETS/VOC2012_orig/SegmentationClass_1D/