Spaces:
Runtime error
Runtime error
File size: 13,141 Bytes
419718d | 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 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 | import numpy as np
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
import imageio
from PIL import Image
from matplotlib import pyplot as plt
from rgb_ind_convertor import *
import os
import sys
import glob
import time
def load_raw_images(path):
paths = path.split('\t')
image = imageio.imread(paths[0], mode='RGB')
wall = imageio.imread(paths[1], mode='L')
close = imageio.imread(paths[2], mode='L')
room = imageio.imread(paths[3], mode='RGB')
close_wall = imageio.imread(paths[4], mode='L')
# NOTE: imresize will rescale the image to range [0, 255], also cast data into uint8 or uint32
image = PIL.Image.fromarray(image).resize((512, 512), Image.BICUBIC)
wall = PIL.Image.fromarray(wall).resize((512, 512), Image.BICUBIC)
close = PIL.Image.fromarray(close).resize((512, 512), Image.BICUBIC)
close_wall = PIL.Image.fromarray(close_wall).resize((512, 512), Image.BICUBIC)
room = PIL.Image.fromarray(room).resize((512, 512), Image.BICUBIC)
room_ind = rgb2ind(room)
# make sure the dtype is uint8
image = np.array(image).astype(np.uint8)
wall = np.array(wall).astype(np.uint8)
close = np.array(close).astype(np.uint8)
close_wall = np.array(close_wall).astype(np.uint8)
room_ind = room_ind.astype(np.uint8)
# debug
# plt.subplot(231)
# plt.imshow(image)
# plt.subplot(233)
# plt.imshow(wall, cmap='gray')
# plt.subplot(234)
# plt.imshow(close, cmap='gray')
# plt.subplot(235)
# plt.imshow(room_ind)
# plt.subplot(236)
# plt.imshow(close_wall, cmap='gray')
# plt.show()
return image, wall, close, room_ind, close_wall
def _int64_feature(value):
return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))
def _bytes_feature(value):
return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
def write_record(paths, name='dataset.tfrecords'):
writer = tf.python_io.TFRecordWriter(name)
for i in range(len(paths)):
# Load the image
image, wall, close, room_ind, close_wall = load_raw_images(paths[i])
# Create a feature
feature = {'image': _bytes_feature(tf.compat.as_bytes(image.tostring())),
'wall': _bytes_feature(tf.compat.as_bytes(wall.tostring())),
'close': _bytes_feature(tf.compat.as_bytes(close.tostring())),
'room': _bytes_feature(tf.compat.as_bytes(room_ind.tostring())),
'close_wall': _bytes_feature(tf.compat.as_bytes(close_wall.tostring()))}
# Create an example protocol buffer
example = tf.train.Example(features=tf.train.Features(feature=feature))
# Serialize to string and write on the file
writer.write(example.SerializeToString())
writer.close()
def read_record(data_path, batch_size=1, size=512):
feature = {'image': tf.FixedLenFeature(shape=(), dtype=tf.string),
'wall': tf.FixedLenFeature(shape=(), dtype=tf.string),
'close': tf.FixedLenFeature(shape=(), dtype=tf.string),
'room': tf.FixedLenFeature(shape=(), dtype=tf.string),
'close_wall': tf.FixedLenFeature(shape=(), dtype=tf.string)}
# Create a list of filenames and pass it to a queue
filename_queue = tf.train.string_input_producer([data_path], num_epochs=None, shuffle=False, capacity=batch_size*128)
# Define a reader and read the next record
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
# Decode the record read by the reader
features = tf.parse_single_example(serialized_example, features=feature)
# Convert the image data from string back to the numbers
image = tf.decode_raw(features['image'], tf.uint8)
wall = tf.decode_raw(features['wall'], tf.uint8)
close = tf.decode_raw(features['close'], tf.uint8)
room = tf.decode_raw(features['room'], tf.uint8)
close_wall = tf.decode_raw(features['close_wall'], tf.uint8)
# Cast data
image = tf.cast(image, dtype=tf.float32)
wall = tf.cast(wall, dtype=tf.float32)
close = tf.cast(close, dtype=tf.float32)
# room = tf.cast(room, dtype=tf.float32)
close_wall = tf.cast(close_wall, dtype=tf.float32)
# Reshape image data into the original shape
image = tf.reshape(image, [size, size, 3])
wall = tf.reshape(wall, [size, size, 1])
close = tf.reshape(close, [size, size, 1])
room = tf.reshape(room, [size, size])
close_wall = tf.reshape(close_wall, [size, size, 1])
# Any preprocessing here ...
# normalize
image = tf.divide(image, tf.constant(255.0))
wall = tf.divide(wall, tf.constant(255.0))
close = tf.divide(close, tf.constant(255.0))
close_wall = tf.divide(close_wall, tf.constant(255.0))
# Genereate one hot room label
room_one_hot = tf.one_hot(room, 9, axis=-1)
# Creates batches by randomly shuffling tensors
images, walls, closes, rooms, close_walls = tf.train.shuffle_batch([image, wall, close, room_one_hot, close_wall],
batch_size=batch_size, capacity=batch_size*128, num_threads=1, min_after_dequeue=batch_size*32)
# images, walls = tf.train.shuffle_batch([image, wall],
# batch_size=batch_size, capacity=batch_size*128, num_threads=1, min_after_dequeue=batch_size*32)
return {'images': images, 'walls': walls, 'closes': closes, 'rooms': rooms, 'close_walls': close_walls}
# return {'images': images, 'walls': walls}
# ------------------------------------------------------------------------------------------------------------------------------------- *
# Following are only for segmentation task, merge all label into one
def load_seg_raw_images(path):
paths = path.split('\t')
image = imageio.imread(paths[0], mode='RGB')
close = imageio.imread(paths[2], mode='L')
room = imageio.imread(paths[3], mode='RGB')
close_wall = imageio.imread(paths[4], mode='L')
# NOTE: imresize will rescale the image to range [0, 255], also cast data into uint8 or uint32
image = PIL.Image.fromarray(image).resize((512, 512), Image.BICUBIC)
close = PIL.Image.fromarray(close).resize((512, 512), Image.BICUBIC) / 255
close_wall = PIL.Image.fromarray(close_wall).resize((512, 512), Image.BICUBIC) / 255
room = PIL.Image.fromarray(room).resize((512, 512), Image.BICUBIC)
room_ind = rgb2ind(room)
# merge result
d_ind = (close>0.5).astype(np.uint8)
cw_ind = (close_wall>0.5).astype(np.uint8)
room_ind[cw_ind==1] = 10
room_ind[d_ind==1] = 9
# make sure the dtype is uint8
image = np.array(image).astype(np.uint8)
room_ind = room_ind.astype(np.uint8)
# debug
# merge = ind2rgb(room_ind, color_map=floorplan_fuse_map)
# plt.subplot(131)
# plt.imshow(image)
# plt.subplot(132)
# plt.imshow(room_ind)
# plt.subplot(133)
# plt.imshow(merge/256.)
# plt.show()
return image, room_ind
def write_seg_record(paths, name='dataset.tfrecords'):
writer = tf.python_io.TFRecordWriter(name)
for i in range(len(paths)):
# Load the image
image, room_ind = load_seg_raw_images(paths[i])
# Create a feature
feature = {'image': _bytes_feature(tf.compat.as_bytes(image.tostring())),
'label': _bytes_feature(tf.compat.as_bytes(room_ind.tostring()))}
# Create an example protocol buffer
example = tf.train.Example(features=tf.train.Features(feature=feature))
# Serialize to string and write on the file
writer.write(example.SerializeToString())
writer.close()
def read_seg_record(data_path, batch_size=1, size=512):
feature = {'image': tf.FixedLenFeature(shape=(), dtype=tf.string),
'label': tf.FixedLenFeature(shape=(), dtype=tf.string)}
# Create a list of filenames and pass it to a queue
filename_queue = tf.train.string_input_producer([data_path], num_epochs=None, shuffle=False, capacity=batch_size*128)
# Define a reader and read the next record
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
# Decode the record read by the reader
features = tf.parse_single_example(serialized_example, features=feature)
# Convert the image data from string back to the numbers
image = tf.decode_raw(features['image'], tf.uint8)
label = tf.decode_raw(features['label'], tf.uint8)
# Cast data
image = tf.cast(image, dtype=tf.float32)
# Reshape image data into the original shape
image = tf.reshape(image, [size, size, 3])
label = tf.reshape(label, [size, size])
# Any preprocessing here ...
# normalize
image = tf.divide(image, tf.constant(255.0))
# Genereate one hot room label
label_one_hot = tf.one_hot(label, 11, axis=-1)
# Creates batches by randomly shuffling tensors
images, labels = tf.train.shuffle_batch([image, label_one_hot],
batch_size=batch_size, capacity=batch_size*128, num_threads=1, min_after_dequeue=batch_size*32)
# images, walls = tf.train.shuffle_batch([image, wall],
# batch_size=batch_size, capacity=batch_size*128, num_threads=1, min_after_dequeue=batch_size*32)
return {'images': images, 'labels': labels}
# --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- *
# ------------------------------------------------------------------------------------------------------------------------------------- *
# Following are only for multi-task network. Two labels(boundary and room.)
def load_bd_rm_images(path):
paths = path.split('\t')
image = imageio.imread(paths[0], mode='RGB')
close = imageio.imread(paths[2], mode='L')
room = imageio.imread(paths[3], mode='RGB')
close_wall = imageio.imread(paths[4], mode='L')
# NOTE: imresize will rescale the image to range [0, 255], also cast data into uint8 or uint32
image = PIL.Image.fromarray(image).resize((512, 512), Image.BICUBIC)
close = PIL.Image.fromarray(close).resize((512, 512), Image.BICUBIC) / 255.
close_wall = PIL.Image.fromarray(close_wall).resize((512, 512), Image.BICUBIC) / 255.
room = PIL.Image.fromarray(room).resize((512, 512), Image.BICUBIC)
room_ind = rgb2ind(room)
# merge result
d_ind = (close>0.5).astype(np.uint8)
cw_ind = (close_wall>0.5).astype(np.uint8)
cw_ind[cw_ind==1] = 2
cw_ind[d_ind==1] = 1
# make sure the dtype is uint8
image = np.array(image).astype(np.uint8)
room_ind = room_ind.astype(np.uint8)
cw_ind = cw_ind.astype(np.uint8)
# debugging
# merge = ind2rgb(room_ind, color_map=floorplan_fuse_map)
# rm = ind2rgb(room_ind)
# bd = ind2rgb(cw_ind, color_map=floorplan_boundary_map)
# plt.subplot(131)
# plt.imshow(image)
# plt.subplot(132)
# plt.imshow(rm/256.)
# plt.subplot(133)
# plt.imshow(bd/256.)
# plt.show()
return image, cw_ind, room_ind, d_ind
def write_bd_rm_record(paths, name='dataset.tfrecords'):
writer = tf.python_io.TFRecordWriter(name)
for i in range(len(paths)):
# Load the image
image, cw_ind, room_ind, d_ind = load_bd_rm_images(paths[i])
# Create a feature
feature = {'image': _bytes_feature(tf.compat.as_bytes(image.tostring())),
'boundary': _bytes_feature(tf.compat.as_bytes(cw_ind.tostring())),
'room': _bytes_feature(tf.compat.as_bytes(room_ind.tostring())),
'door': _bytes_feature(tf.compat.as_bytes(d_ind.tostring()))}
# Create an example protocol buffer
example = tf.train.Example(features=tf.train.Features(feature=feature))
# Serialize to string and write on the file
writer.write(example.SerializeToString())
writer.close()
def read_bd_rm_record(data_path, batch_size=1, size=512):
feature = {'image': tf.FixedLenFeature(shape=(), dtype=tf.string),
'boundary': tf.FixedLenFeature(shape=(), dtype=tf.string),
'room': tf.FixedLenFeature(shape=(), dtype=tf.string),
'door': tf.FixedLenFeature(shape=(), dtype=tf.string)}
# Create a list of filenames and pass it to a queue
filename_queue = tf.train.string_input_producer([data_path], num_epochs=None, shuffle=False, capacity=batch_size*128)
# Define a reader and read the next record
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
# Decode the record read by the reader
features = tf.parse_single_example(serialized_example, features=feature)
# Convert the image data from string back to the numbers
image = tf.decode_raw(features['image'], tf.uint8)
boundary = tf.decode_raw(features['boundary'], tf.uint8)
room = tf.decode_raw(features['room'], tf.uint8)
door = tf.decode_raw(features['door'], tf.uint8)
# Cast data
image = tf.cast(image, dtype=tf.float32)
# Reshape image data into the original shape
image = tf.reshape(image, [size, size, 3])
boundary = tf.reshape(boundary, [size, size])
room = tf.reshape(room, [size, size])
door = tf.reshape(door, [size, size])
# Any preprocessing here ...
# normalize
image = tf.divide(image, tf.constant(255.0))
# Genereate one hot room label
label_boundary = tf.one_hot(boundary, 3, axis=-1)
label_room = tf.one_hot(room, 9, axis=-1)
# Creates batches by randomly shuffling tensors
images, label_boundaries, label_rooms, label_doors = tf.train.shuffle_batch([image, label_boundary, label_room, door],
batch_size=batch_size, capacity=batch_size*128, num_threads=1, min_after_dequeue=batch_size*32)
# images, walls = tf.train.shuffle_batch([image, wall],
# batch_size=batch_size, capacity=batch_size*128, num_threads=1, min_after_dequeue=batch_size*32)
return {'images': images, 'label_boundaries': label_boundaries, 'label_rooms': label_rooms, 'label_doors': label_doors}
|