-
Notifications
You must be signed in to change notification settings - Fork 7
/
image_tiler.py
executable file
·162 lines (131 loc) · 5.75 KB
/
image_tiler.py
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
""" This file contains different utility functions that are not connected
in anyway to the networks presented in the tutorials, but rather help in
processing the outputs into a more understandable way.
For example ``tile_raster_images`` helps in generating a easy to grasp
image from a set of samples or weights.
"""
import numpy, os, cPickle
from PIL import Image
def load_mnist():
path = '.'
data = cPickle.load(open(os.path.join(path,'mnist.pkl'), 'r'))
return data
def scale_to_unit_interval(ndar, eps=1e-8):
""" Scales all values in the ndarray ndar to be between 0 and 1 """
ndar = ndar.copy()
ndar -= ndar.min()
ndar *= 1.0 / (ndar.max() + eps)
return ndar
def tile_raster_images(X, img_shape, tile_shape, tile_spacing=(0, 0),
scale_rows_to_unit_interval=True,
output_pixel_vals=True):
"""
Transform an array with one flattened image per row, into an array in
which images are reshaped and layed out like tiles on a floor.
This function is useful for visualizing datasets whose rows are images,
and also columns of matrices for transforming those rows
(such as the first layer of a neural net).
:type X: a 2-D ndarray or a tuple of 4 channels, elements of which can
be 2-D ndarrays or None;
:param X: a 2-D array in which every row is a flattened image.
:type img_shape: tuple; (height, width)
:param img_shape: the original shape of each image
:type tile_shape: tuple; (rows, cols)
:param tile_shape: the number of images to tile (rows, cols)
:param output_pixel_vals: if output should be pixel values (i.e. int8
values) or floats
:param scale_rows_to_unit_interval: if the values need to be scaled before
being plotted to [0,1] or not
:returns: array suitable for viewing as an image.
(See:`PIL.Image.fromarray`.)
:rtype: a 2-d array with same dtype as X.
"""
assert len(img_shape) == 2
assert len(tile_shape) == 2
assert len(tile_spacing) == 2
# The expression below can be re-written in a more C style as
# follows :
#
# out_shape = [0,0]
# out_shape[0] = (img_shape[0]+tile_spacing[0])*tile_shape[0] -
# tile_spacing[0]
# out_shape[1] = (img_shape[1]+tile_spacing[1])*tile_shape[1] -
# tile_spacing[1]
out_shape = [(ishp + tsp) * tshp - tsp for ishp, tshp, tsp
in zip(img_shape, tile_shape, tile_spacing)]
if isinstance(X, tuple):
assert len(X) == 4
# Create an output numpy ndarray to store the image
if output_pixel_vals:
out_array = numpy.zeros((out_shape[0], out_shape[1], 4),
dtype='uint8')
else:
out_array = numpy.zeros((out_shape[0], out_shape[1], 4),
dtype=X.dtype)
#colors default to 0, alpha defaults to 1 (opaque)
if output_pixel_vals:
channel_defaults = [0, 0, 0, 255]
else:
channel_defaults = [0., 0., 0., 1.]
for i in xrange(4):
if X[i] is None:
# if channel is None, fill it with zeros of the correct
# dtype
dt = out_array.dtype
if output_pixel_vals:
dt = 'uint8'
out_array[:, :, i] = numpy.zeros(out_shape,
dtype=dt) + channel_defaults[i]
else:
# use a recurrent call to compute the channel and store it
# in the output
out_array[:, :, i] = tile_raster_images(
X[i], img_shape, tile_shape, tile_spacing,
scale_rows_to_unit_interval, output_pixel_vals)
return out_array
else:
# if we are dealing with only one channel
H, W = img_shape
Hs, Ws = tile_spacing
# generate a matrix to store the output
dt = X.dtype
if output_pixel_vals:
dt = 'uint8'
out_array = numpy.zeros(out_shape, dtype=dt)
for tile_row in xrange(tile_shape[0]):
for tile_col in xrange(tile_shape[1]):
if tile_row * tile_shape[1] + tile_col < X.shape[0]:
this_x = X[tile_row * tile_shape[1] + tile_col]
if scale_rows_to_unit_interval:
# if we should scale values to be between 0 and 1
# do this by calling the `scale_to_unit_interval`
# function
this_img = scale_to_unit_interval(
this_x.reshape(img_shape))
else:
this_img = this_x.reshape(img_shape)
# add the slice to the corresponding position in the
# output array
c = 1
if output_pixel_vals:
c = 255
out_array[
tile_row * (H + Hs): tile_row * (H + Hs) + H,
tile_col * (W + Ws): tile_col * (W + Ws) + W
] = this_img * c
return out_array
def visualize_mnist():
(train_X, train_Y), (valid_X, valid_Y), (test_X, test_Y) = load_mnist()
design_matrix = train_X
images = design_matrix[0:2500, :]
channel_length = 28 * 28
to_visualize = images
image_data = tile_raster_images(to_visualize,
img_shape=[28,28],
tile_shape=[50,50],
tile_spacing=(2,2))
im_new = Image.fromarray(numpy.uint8(image_data))
im_new.save('samples_mnist.png')
os.system('eog samples_mnist.png')
if __name__ == '__main__':
visualize_mnist()