forked from tensorlayer/TensorLayer
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathvisualize.py
More file actions
436 lines (369 loc) · 14.1 KB
/
Copy pathvisualize.py
File metadata and controls
436 lines (369 loc) · 14.1 KB
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
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
# -*- coding: utf-8 -*-
import os
import matplotlib
import numpy as np
# save/read image(s)
import scipy.misc
from . import prepro
from . import _logging as logging
# Uncomment the following line if you got: _tkinter.TclError: no display name and no $DISPLAY environment variable
# matplotlib.use('Agg')
def read_image(image, path=''):
"""Read one image.
Parameters
-----------
image : str
file name.
path : str
path.
Returns
-------
numpy array
Image
"""
return scipy.misc.imread(os.path.join(path, image))
def read_images(img_list, path='', n_threads=10, printable=True):
"""Returns all images in list by given path and name of each image file.
Parameters
-------------
img_list : list of str
the image file names.
path : str
image folder path.
n_threads : int
number of threads to read image.
printable : boolean
print information when reading images.
Returns
-------
list of numpy array
The read images
"""
imgs = []
for idx in range(0, len(img_list), n_threads):
b_imgs_list = img_list[idx:idx + n_threads]
b_imgs = prepro.threading_data(b_imgs_list, fn=read_image, path=path)
# logging.info(b_imgs.shape)
imgs.extend(b_imgs)
if printable:
logging.info('read %d from %s' % (len(imgs), path))
return imgs
def save_image(image, image_path=''):
"""Save a image.
Parameters
-----------
image : numpy array
[w, h, c]
image_path : str
path
"""
try: # RGB
scipy.misc.imsave(image_path, image)
except: # Greyscale
scipy.misc.imsave(image_path, image[:, :, 0])
def save_images(images, size, image_path=''):
"""Save multiple images into one single image.
Parameters
-----------
images : numpy array
(batch, w, h, c)
size : list of 2 ints
row and column number.
number of images should be equal or less than size[0] * size[1]
image_path : str
save path
Returns
-------
numpy array
The single image
Examples
---------
>>> images = np.random.rand(64, 100, 100, 3)
>>> tl.visualize.save_images(images, [8, 8], 'temp.png')
"""
if len(images.shape) == 3: # Greyscale [batch, h, w] --> [batch, h, w, 1]
images = images[:, :, :, np.newaxis]
def merge(images, size):
h, w = images.shape[1], images.shape[2]
img = np.zeros((h * size[0], w * size[1], 3))
for idx, image in enumerate(images):
i = idx % size[1]
j = idx // size[1]
img[j * h:j * h + h, i * w:i * w + w, :] = image
return img
def imsave(images, size, path):
return scipy.misc.imsave(path, merge(images, size))
assert len(images) <= size[0] * size[1], "number of images should be equal or less than size[0] * size[1] {}".format(len(images))
return imsave(images, size, image_path)
def draw_boxes_and_labels_to_image(image, classes=[], coords=[], scores=[], classes_list=[], is_center=True, is_rescale=True, save_name=None):
"""Draw bboxes and class labels on image. Return or save the image with bboxes, example in the docs of ``tl.prepro``.
Parameters
-----------
image : numpy array
RGB image in numpy.array, [height, width, channel].
classes : list of int
a list of class ID (int).
coords : list of int
a list of list for coordinates.
- Should be [x, y, x2, y2] (up-left and botton-right format)
- If [x_center, y_center, w, h] (set is_center to True).
scores : list of float
a list of score (float). (Optional)
classes_list : list of str
for converting ID to string on image.
is_center : boolean
If coords is [x_center, y_center, w, h], set it to True for converting [x_center, y_center, w, h] to [x, y, x2, y2] (up-left and botton-right).
If coords is [x1, x2, y1, y2], set it to False.
is_rescale : boolean
If True, the input coordinates are the portion of width and high, this API will scale the coordinates to pixel unit internally.
If False, feed the coordinates with pixel unit format.
save_name : None or str
The name of image file (i.e. image.png), if None, not to save image.
Returns
-------
numpy array
The saved image
References
-----------
- OpenCV rectangle and putText.
- `scikit-image <http://scikit-image.org/docs/dev/api/skimage.draw.html#skimage.draw.rectangle>`__.
"""
assert len(coords) == len(classes), "number of coordinates and classes are equal"
if len(scores) > 0:
assert len(scores) == len(classes), "number of scores and classes are equal"
import cv2
# don't change the original image, and avoid error https://stackoverflow.com/questions/30249053/python-opencv-drawing-errors-after-manipulating-array-with-numpy
image = image.copy()
imh, imw = image.shape[0:2]
thick = int((imh + imw) // 430)
for i in range(len(coords)):
if is_center:
x, y, x2, y2 = prepro.obj_box_coord_centroid_to_upleft_butright(coords[i])
else:
x, y, x2, y2 = coords[i]
if is_rescale: # scale back to pixel unit if the coords are the portion of width and high
x, y, x2, y2 = prepro.obj_box_coord_scale_to_pixelunit([x, y, x2, y2], (imh, imw))
cv2.rectangle(
image,
(int(x), int(y)),
(int(x2), int(y2)), # up-left and botton-right
[0, 255, 0],
thick)
cv2.putText(
image,
classes_list[classes[i]] + ((" %.2f" % (scores[i])) if (len(scores) != 0) else " "),
(int(x), int(y)), # button left
0,
1.5e-3 * imh, # bigger = larger font
[0, 0, 256], # self.meta['colors'][max_indx],
int(thick / 2) + 1) # bold
if save_name is not None:
# cv2.imwrite('_my.png', image)
save_image(image, save_name)
# if len(coords) == 0:
# logging.info("draw_boxes_and_labels_to_image: no bboxes exist, cannot draw !")
return image
def frame(I=None, second=5, saveable=True, name='frame', cmap=None, fig_idx=12836):
"""Display a frame(image). Make sure OpenAI Gym render() is disable before using it.
Parameters
----------
I : numpy.array
The image
second : int
The display second(s) for the image(s), if saveable is False.
saveable : boolean
Save or plot the figure.
name : str
A name to save the image, if saveable is True.
cmap : None or string
'gray' for greyscale, None for default, etc.
fig_idx : int
matplotlib figure index.
Examples
--------
>>> env = gym.make("Pong-v0")
>>> observation = env.reset()
>>> tl.visualize.frame(observation)
"""
import matplotlib.pyplot as plt
if saveable is False:
plt.ion()
fig = plt.figure(fig_idx) # show all feature images
if len(I.shape) and I.shape[-1] == 1: # (10,10,1) --> (10,10)
I = I[:, :, 0]
plt.imshow(I, cmap)
plt.title(name)
# plt.gca().xaxis.set_major_locator(plt.NullLocator()) # distable tick
# plt.gca().yaxis.set_major_locator(plt.NullLocator())
if saveable:
plt.savefig(name + '.pdf', format='pdf')
else:
plt.draw()
plt.pause(second)
def CNN2d(CNN=None, second=10, saveable=True, name='cnn', fig_idx=3119362):
"""Display a group of RGB or Greyscale CNN masks.
Parameters
----------
CNN : numpy.array
The image. e.g: 64 5x5 RGB images can be (5, 5, 3, 64).
second : int
The display second(s) for the image(s), if saveable is False.
saveable : boolean
Save or plot the figure.
name : str
A name to save the image, if saveable is True.
fig_idx : int
matplotlib figure index.
Examples
--------
>>> tl.visualize.CNN2d(network.all_params[0].eval(), second=10, saveable=True, name='cnn1_mnist', fig_idx=2012)
"""
import matplotlib.pyplot as plt
# logging.info(CNN.shape) # (5, 5, 3, 64)
# exit()
n_mask = CNN.shape[3]
n_row = CNN.shape[0]
n_col = CNN.shape[1]
n_color = CNN.shape[2]
row = int(np.sqrt(n_mask))
col = int(np.ceil(n_mask / row))
plt.ion() # active mode
fig = plt.figure(fig_idx)
count = 1
for ir in range(1, row + 1):
for ic in range(1, col + 1):
if count > n_mask:
break
a = fig.add_subplot(col, row, count)
# logging.info(CNN[:,:,:,count-1].shape, n_row, n_col) # (5, 1, 32) 5 5
# exit()
# plt.imshow(
# np.reshape(CNN[count-1,:,:,:], (n_row, n_col)),
# cmap='gray', interpolation="nearest") # theano
if n_color == 1:
plt.imshow(np.reshape(CNN[:, :, :, count - 1], (n_row, n_col)), cmap='gray', interpolation="nearest")
elif n_color == 3:
plt.imshow(np.reshape(CNN[:, :, :, count - 1], (n_row, n_col, n_color)), cmap='gray', interpolation="nearest")
else:
raise Exception("Unknown n_color")
plt.gca().xaxis.set_major_locator(plt.NullLocator()) # distable tick
plt.gca().yaxis.set_major_locator(plt.NullLocator())
count = count + 1
if saveable:
plt.savefig(name + '.pdf', format='pdf')
else:
plt.draw()
plt.pause(second)
def images2d(images=None, second=10, saveable=True, name='images', dtype=None, fig_idx=3119362):
"""Display a group of RGB or Greyscale images.
Parameters
----------
images : numpy.array
The images.
second : int
The display second(s) for the image(s), if saveable is False.
saveable : boolean
Save or plot the figure.
name : str
A name to save the image, if saveable is True.
dtype : None or numpy data type
The data type for displaying the images.
fig_idx : int
matplotlib figure index.
Examples
--------
>>> X_train, y_train, X_test, y_test = tl.files.load_cifar10_dataset(shape=(-1, 32, 32, 3), plotable=False)
>>> tl.visualize.images2d(X_train[0:100,:,:,:], second=10, saveable=False, name='cifar10', dtype=np.uint8, fig_idx=20212)
"""
import matplotlib.pyplot as plt
# logging.info(images.shape) # (50000, 32, 32, 3)
# exit()
if dtype:
images = np.asarray(images, dtype=dtype)
n_mask = images.shape[0]
n_row = images.shape[1]
n_col = images.shape[2]
n_color = images.shape[3]
row = int(np.sqrt(n_mask))
col = int(np.ceil(n_mask / row))
plt.ion() # active mode
fig = plt.figure(fig_idx)
count = 1
for ir in range(1, row + 1):
for ic in range(1, col + 1):
if count > n_mask:
break
a = fig.add_subplot(col, row, count)
# logging.info(images[:,:,:,count-1].shape, n_row, n_col) # (5, 1, 32) 5 5
# plt.imshow(
# np.reshape(images[count-1,:,:,:], (n_row, n_col)),
# cmap='gray', interpolation="nearest") # theano
if n_color == 1:
plt.imshow(np.reshape(images[count - 1, :, :], (n_row, n_col)), cmap='gray', interpolation="nearest")
# plt.title(name)
elif n_color == 3:
plt.imshow(images[count - 1, :, :], cmap='gray', interpolation="nearest")
# plt.title(name)
else:
raise Exception("Unknown n_color")
plt.gca().xaxis.set_major_locator(plt.NullLocator()) # distable tick
plt.gca().yaxis.set_major_locator(plt.NullLocator())
count = count + 1
if saveable:
plt.savefig(name + '.pdf', format='pdf')
else:
plt.draw()
plt.pause(second)
def tsne_embedding(embeddings, reverse_dictionary, plot_only=500, second=5, saveable=False, name='tsne', fig_idx=9862):
"""Visualize the embeddings by using t-SNE.
Parameters
----------
embeddings : matrix
The images.
reverse_dictionary : dictionary
id_to_word, mapping id to unique word.
plot_only : int
The number of examples to plot, choice the most common words.
second : int
The display second(s) for the image(s), if saveable is False.
saveable : boolean
Save or plot the figure.
name : str
A name to save the image, if saveable is True.
fig_idx : int
matplotlib figure index.
Examples
--------
>>> see 'tutorial_word2vec_basic.py'
>>> final_embeddings = normalized_embeddings.eval()
>>> tl.visualize.tsne_embedding(final_embeddings, labels, reverse_dictionary,
... plot_only=500, second=5, saveable=False, name='tsne')
"""
import matplotlib.pyplot as plt
def plot_with_labels(low_dim_embs, labels, figsize=(18, 18), second=5, saveable=True, name='tsne', fig_idx=9862):
assert low_dim_embs.shape[0] >= len(labels), "More labels than embeddings"
if saveable is False:
plt.ion()
plt.figure(fig_idx)
plt.figure(figsize=figsize) #in inches
for i, label in enumerate(labels):
x, y = low_dim_embs[i, :]
plt.scatter(x, y)
plt.annotate(label, xy=(x, y), xytext=(5, 2), textcoords='offset points', ha='right', va='bottom')
if saveable:
plt.savefig(name + '.pdf', format='pdf')
else:
plt.draw()
plt.pause(second)
try:
from sklearn.manifold import TSNE
import matplotlib.pyplot as plt
from six.moves import xrange
tsne = TSNE(perplexity=30, n_components=2, init='pca', n_iter=5000)
# plot_only = 500
low_dim_embs = tsne.fit_transform(embeddings[:plot_only, :])
labels = [reverse_dictionary[i] for i in xrange(plot_only)]
plot_with_labels(low_dim_embs, labels, second=second, saveable=saveable, \
name=name, fig_idx=fig_idx)
except ImportError:
logging.info("Please install sklearn and matplotlib to visualize embeddings.")