Spaces:
Paused
Paused
File size: 3,783 Bytes
3c0c5aa 068408a 3c0c5aa 068408a 13f0309 3c0c5aa 068408a 3c0c5aa 068408a 3c0c5aa 068408a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 |
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#######################################################################################
# The MIT License
# Copyright (c) 2014 Hannes Schulz, University of Bonn <schulz@ais.uni-bonn.de>
# Copyright (c) 2013 Benedikt Waldvogel, University of Bonn <mail@bwaldvogel.de>
# Copyright (c) 2008-2009 Sebastian Nowozin <nowozin@gmail.com>
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in all
# copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
#######################################################################################
#
# Helper script to convert the NYU Depth v2 dataset Matlab file into a set of
# PNG and JPEG images.
#
# See https://github.com/deeplearningais/curfil/wiki/Training-and-Prediction-with-the-NYU-Depth-v2-Dataset
from __future__ import print_function
import h5py
import numpy as np
import os
import scipy.io
import sys
import cv2
from tqdm import tqdm
def convert_image(i, scene, depth, image, folder):
# depth is given in meters (Kinect has a range of around .5m and 4.5m but can sense also at 8m)
normalized_depth = cv2.normalize(depth, None, 0, 255, cv2.NORM_MINMAX)
cv2.imwrite("%s/%05d_depth.png" % (folder, i), normalized_depth)
image = image[:, :, ::-1]
image_black_boundary = np.zeros((480, 640, 3), dtype=np.uint8)
image_black_boundary[7:474, 7:632, :] = image[7:474, 7:632, :]
cv2.imwrite("%s/%05d.jpg" % (folder, i), image_black_boundary)
if __name__ == "__main__":
if len(sys.argv) < 4:
print("usage: %s <h5_file> <train_test_split> <out_folder>" % sys.argv[0], file=sys.stderr)
sys.exit(0)
h5_file = h5py.File(sys.argv[1], "r")
# h5py is not able to open that file. but scipy is
train_test = scipy.io.loadmat(sys.argv[2])
out_folder = sys.argv[3]
test_images = set([int(x) for x in train_test["testNdxs"]])
train_images = set([int(x) for x in train_test["trainNdxs"]])
print("%d training images" % len(train_images))
print("%d test images" % len(test_images))
depth = h5_file['depths']
print("reading", sys.argv[1])
images = h5_file['images']
scenes = [u''.join(chr(c[0]) for c in h5_file[obj_ref]) for obj_ref in h5_file['sceneTypes'][0]]
for i, image in tqdm(enumerate(images), desc="processing images", total=len(images)):
idx = int(i) + 1
if idx in train_images:
train_test = "train"
else:
assert idx in test_images, "index %d neither found in training set nor in test set" % idx
train_test = "test"
folder = "%s/%s/%s" % (out_folder, train_test, scenes[i])
if not os.path.exists(folder):
os.makedirs(folder)
convert_image(i, scenes[i], depth[i, :, :].T, image.T, folder)
print("Finished")
|