Semantic segmentation-Data Set preparation

# Semantic Segmentation Data Set preparation

DataSet data Set downloadPascal VOC-dataset augmented Pascal VOC DataSet

# 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
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

Data Conversions ConversionAugmented PASCAL VOC Data set Ground truth labels is in the format of Matlab data files and needs to be converted:
STEP1 defines the mat2png script; Step2 converts the mat into 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.berkel ey.edu/~bharath2/codes/sbd/download.html # ' Gtcls ' key is for class segmentation # ' Gtinst ' key was for instance Segmentati On Def Mat2png_hariharan (Mat_file, key= ' Gtcls '): Mat = Scipy.io.loadmat (Mat_file, Mat_dtype=true, Squeeze_me=true, str Uct_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_MAT2

    PNG (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 is 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_path\n "in Put_path denotes path containing Matlab files for conversion.\n ' Output_path denotes PATH where converted Png fil
        Es 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

The Softmax loss function of Caffe can only accept one-dimensional ground truth labels. However, the ground truth labels in original PASCAL VOC 2012 is preserved in the form of RGB images and therefore requires dimensionality reduction:
STEP1 definition convert python script: convert_labels.py; Step2 convert Ground truth labels to 1D.

#!/usr/bin/env python #Martin kersner, m.kersner@gmail.com #2016/01/25 from __future__ import print_function I mport 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, 12
             8, 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, 1
             28, 128): 14, (192, 128, 128): 15, (0, 64, 0): 16, (128, 64, 0): 17,

(0, 192, 0): (+, 192, 0): +, (0, +): +} 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_palet Te () 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_argumen TS (sys.argv) # Create dir for converted labels if not Os.path.isdir (path_converted): Os.makedirs (Path_con
            verted) 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.shap  e) > 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, ther 
               Efore " "Shouldn ' is processed by this script.\n" "Exiting.", File=sys.stderr) exit () def proc Ess_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_path \ n ' PATH points to directory with segmentation image labels.\n ' list_file denotes text FILE containing n Ames of images in path.\n "Names do not include extension of images.\n" New_path points to directory whe
        Re converted labels'll 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/