Skip to content
Navigation Menu
{{ message }}
forked from tensorlayer/TensorLayer
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathfiles.py
More file actions
1255 lines (1080 loc) · 45.4 KB
/
Copy pathfiles.py
File metadata and controls
1255 lines (1080 loc) · 45.4 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
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#! /usr/bin/python
# -*- coding: utf8 -*-
import tensorflow as tf
import os
import numpy as np
import re
import sys
import tarfile
import gzip
import zipfile
from . import visualize
from . import nlp
import pickle
from six.moves import urllib
from six.moves import cPickle
from six.moves import zip
from tensorflow.python.platform import gfile
## Load dataset functions
def load_mnist_dataset(shape=(-1,784), path="data/mnist/"):
"""Automatically download MNIST dataset
and return the training, validation and test set with 50000, 10000 and 10000
digit images respectively.
Parameters
----------
shape : tuple
The shape of digit images, defaults is (-1,784)
path : string
The path that the data is downloaded to, defaults is ``data/mnist/``.
Examples
--------
>>> X_train, y_train, X_val, y_val, X_test, y_test = tl.files.load_mnist_dataset(shape=(-1,784))
>>> X_train, y_train, X_val, y_val, X_test, y_test = tl.files.load_mnist_dataset(shape=(-1, 28, 28, 1))
"""
# We first define functions for loading MNIST images and labels.
# For convenience, they also download the requested files if needed.
def load_mnist_images(path, filename):
filepath = maybe_download_and_extract(filename, path, 'http://yann.lecun.com/exdb/mnist/')
print(filepath)
# Read the inputs in Yann LeCun's binary format.
with gzip.open(filepath, 'rb') as f:
data = np.frombuffer(f.read(), np.uint8, offset=16)
# The inputs are vectors now, we reshape them to monochrome 2D images,
# following the shape convention: (examples, channels, rows, columns)
data = data.reshape(shape)
# The inputs come as bytes, we convert them to float32 in range [0,1].
# (Actually to range [0, 255/256], for compatibility to the version
# provided at http://deeplearning.net/data/mnist/mnist.pkl.gz.)
return data / np.float32(256)
def load_mnist_labels(path, filename):
filepath = maybe_download_and_extract(filename, path, 'http://yann.lecun.com/exdb/mnist/')
# Read the labels in Yann LeCun's binary format.
with gzip.open(filepath, 'rb') as f:
data = np.frombuffer(f.read(), np.uint8, offset=8)
# The labels are vectors of integers now, that's exactly what we want.
return data
# Download and read the training and test set images and labels.
print("Load or Download MNIST > {}".format(path))
X_train = load_mnist_images(path, 'train-images-idx3-ubyte.gz')
y_train = load_mnist_labels(path, 'train-labels-idx1-ubyte.gz')
X_test = load_mnist_images(path, 't10k-images-idx3-ubyte.gz')
y_test = load_mnist_labels(path, 't10k-labels-idx1-ubyte.gz')
# We reserve the last 10000 training examples for validation.
X_train, X_val = X_train[:-10000], X_train[-10000:]
y_train, y_val = y_train[:-10000], y_train[-10000:]
# We just return all the arrays in order, as expected in main().
# (It doesn't matter how we do this as long as we can read them again.)
X_train = np.asarray(X_train, dtype=np.float32)
y_train = np.asarray(y_train, dtype=np.int32)
X_val = np.asarray(X_val, dtype=np.float32)
y_val = np.asarray(y_val, dtype=np.int32)
X_test = np.asarray(X_test, dtype=np.float32)
y_test = np.asarray(y_test, dtype=np.int32)
return X_train, y_train, X_val, y_val, X_test, y_test
def load_cifar10_dataset(shape=(-1, 32, 32, 3), path='data/cifar10/', plotable=False, second=3):
"""The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes, with
6000 images per class. There are 50000 training images and 10000 test images.
The dataset is divided into five training batches and one test batch, each with
10000 images. The test batch contains exactly 1000 randomly-selected images from
each class. The training batches contain the remaining images in random order,
but some training batches may contain more images from one class than another.
Between them, the training batches contain exactly 5000 images from each class.
Parameters
----------
shape : tupe
The shape of digit images: e.g. (-1, 3, 32, 32) , (-1, 32, 32, 3) , (-1, 32, 32, 3)
plotable : True, False
Whether to plot some image examples.
second : int
If ``plotable`` is True, ``second`` is the display time.
path : string
The path that the data is downloaded to, defaults is ``data/cifar10/``.
Examples
--------
>>> X_train, y_train, X_test, y_test = tl.files.load_cifar10_dataset(shape=(-1, 32, 32, 3), plotable=True)
References
----------
- `CIFAR website <https://www.cs.toronto.edu/~kriz/cifar.html>`_
- `Data download link <https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz>`_
- `Code references <https://teratail.com/questions/28932>`_
"""
print("Load or Download cifar10 > {}".format(path))
#Helper function to unpickle the data
def unpickle(file):
fp = open(file, 'rb')
if sys.version_info.major == 2:
data = pickle.load(fp)
elif sys.version_info.major == 3:
data = pickle.load(fp, encoding='latin-1')
fp.close()
return data
filename = 'cifar-10-python.tar.gz'
url = 'https://www.cs.toronto.edu/~kriz/'
#Download and uncompress file
maybe_download_and_extract(filename, path, url, extract=True)
#Unpickle file and fill in data
X_train = None
y_train = []
for i in range(1,6):
data_dic = unpickle(os.path.join(path, 'cifar-10-batches-py/', "data_batch_{}".format(i)))
if i == 1:
X_train = data_dic['data']
else:
X_train = np.vstack((X_train, data_dic['data']))
y_train += data_dic['labels']
test_data_dic = unpickle(os.path.join(path, 'cifar-10-batches-py/', "test_batch"))
X_test = test_data_dic['data']
y_test = np.array(test_data_dic['labels'])
if shape == (-1, 3, 32, 32):
X_test = X_test.reshape(shape)
X_train = X_train.reshape(shape)
elif shape == (-1, 32, 32, 3):
X_test = X_test.reshape(shape, order='F')
X_train = X_train.reshape(shape, order='F')
X_test = np.transpose(X_test, (0, 2, 1, 3))
X_train = np.transpose(X_train, (0, 2, 1, 3))
else:
X_test = X_test.reshape(shape)
X_train = X_train.reshape(shape)
y_train = np.array(y_train)
if plotable == True:
print('\nCIFAR-10')
import matplotlib.pyplot as plt
fig = plt.figure(1)
print('Shape of a training image: X_train[0]',X_train[0].shape)
plt.ion() # interactive mode
count = 1
for row in range(10):
for col in range(10):
a = fig.add_subplot(10, 10, count)
if shape == (-1, 3, 32, 32):
# plt.imshow(X_train[count-1], interpolation='nearest')
plt.imshow(np.transpose(X_train[count-1], (1, 2, 0)), interpolation='nearest')
# plt.imshow(np.transpose(X_train[count-1], (2, 1, 0)), interpolation='nearest')
elif shape == (-1, 32, 32, 3):
plt.imshow(X_train[count-1], interpolation='nearest')
# plt.imshow(np.transpose(X_train[count-1], (1, 0, 2)), interpolation='nearest')
else:
raise Exception("Do not support the given 'shape' to plot the image examples")
plt.gca().xaxis.set_major_locator(plt.NullLocator()) # 不显示刻度(tick)
plt.gca().yaxis.set_major_locator(plt.NullLocator())
count = count + 1
plt.draw() # interactive mode
plt.pause(3) # interactive mode
print("X_train:",X_train.shape)
print("y_train:",y_train.shape)
print("X_test:",X_test.shape)
print("y_test:",y_test.shape)
X_train = np.asarray(X_train, dtype=np.float32)
X_test = np.asarray(X_test, dtype=np.float32)
y_train = np.asarray(y_train, dtype=np.int32)
y_test = np.asarray(y_test, dtype=np.int32)
return X_train, y_train, X_test, y_test
def load_ptb_dataset(path='data/ptb/'):
"""Penn TreeBank (PTB) dataset is used in many LANGUAGE MODELING papers,
including "Empirical Evaluation and Combination of Advanced Language
Modeling Techniques", "Recurrent Neural Network Regularization".
It consists of 929k training words, 73k validation words, and 82k test
words. It has 10k words in its vocabulary.
Parameters
----------
path : : string
The path that the data is downloaded to, defaults is ``data/ptb/``.
Returns
--------
train_data, valid_data, test_data, vocabulary size
Examples
--------
>>> train_data, valid_data, test_data, vocab_size = tl.files.load_ptb_dataset()
References
---------------
- ``tensorflow.models.rnn.ptb import reader``
- `Manual download <http://www.fit.vutbr.cz/~imikolov/rnnlm/simple-examples.tgz>`_
"""
print("Load or Download Penn TreeBank (PTB) dataset > {}".format(path))
#Maybe dowload and uncompress tar, or load exsisting files
filename = 'simple-examples.tgz'
url = 'http://www.fit.vutbr.cz/~imikolov/rnnlm/'
maybe_download_and_extract(filename, path, url, extract=True)
data_path = os.path.join(path, 'simple-examples', 'data')
train_path = os.path.join(data_path, "ptb.train.txt")
valid_path = os.path.join(data_path, "ptb.valid.txt")
test_path = os.path.join(data_path, "ptb.test.txt")
word_to_id = nlp.build_vocab(nlp.read_words(train_path))
train_data = nlp.words_to_word_ids(nlp.read_words(train_path), word_to_id)
valid_data = nlp.words_to_word_ids(nlp.read_words(valid_path), word_to_id)
test_data = nlp.words_to_word_ids(nlp.read_words(test_path), word_to_id)
vocabulary = len(word_to_id)
# print(nlp.read_words(train_path)) # ... 'according', 'to', 'mr.', '<unk>', '<eos>']
# print(train_data) # ... 214, 5, 23, 1, 2]
# print(word_to_id) # ... 'beyond': 1295, 'anti-nuclear': 9599, 'trouble': 1520, '<eos>': 2 ... }
# print(vocabulary) # 10000
# exit()
return train_data, valid_data, test_data, vocabulary
def load_matt_mahoney_text8_dataset(path='data/mm_test8/'):
"""Download a text file from Matt Mahoney's website
if not present, and make sure it's the right size.
Extract the first file enclosed in a zip file as a list of words.
This dataset can be used for Word Embedding.
Parameters
----------
path : : string
The path that the data is downloaded to, defaults is ``data/mm_test8/``.
Returns
--------
word_list : a list
a list of string (word).\n
e.g. [.... 'their', 'families', 'who', 'were', 'expelled', 'from', 'jerusalem', ...]
Examples
--------
>>> words = tl.files.load_matt_mahoney_text8_dataset()
>>> print('Data size', len(words))
"""
print("Load or Download matt_mahoney_text8 Dataset> {}".format(path))
filename = 'text8.zip'
url = 'http://mattmahoney.net/dc/'
maybe_download_and_extract(filename, path, url, expected_bytes=31344016)
with zipfile.ZipFile(os.path.join(path, filename)) as f:
word_list = f.read(f.namelist()[0]).split()
for idx, word in enumerate(word_list):
word_list[idx] = word_list[idx].decode()
return word_list
def load_imdb_dataset(path='data/imdb/', nb_words=None, skip_top=0,
maxlen=None, test_split=0.2, seed=113,
start_char=1, oov_char=2, index_from=3):
"""Load IMDB dataset
Parameters
----------
path : : string
The path that the data is downloaded to, defaults is ``data/imdb/``.
Examples
--------
>>> X_train, y_train, X_test, y_test = tl.files.load_imdb_dataset(
... nb_words=20000, test_split=0.2)
>>> print('X_train.shape', X_train.shape)
... (20000,) [[1, 62, 74, ... 1033, 507, 27],[1, 60, 33, ... 13, 1053, 7]..]
>>> print('y_train.shape', y_train.shape)
... (20000,) [1 0 0 ..., 1 0 1]
References
-----------
- `Modified from keras. <https://github.com/fchollet/keras/blob/master/keras/datasets/imdb.py>`_
"""
filename = "imdb.pkl"
url = 'https://s3.amazonaws.com/text-datasets/'
maybe_download_and_extract(filename, path, url)
if filename.endswith(".gz"):
f = gzip.open(os.path.join(path, filename), 'rb')
else:
f = open(os.path.join(path, filename), 'rb')
X, labels = cPickle.load(f)
f.close()
np.random.seed(seed)
np.random.shuffle(X)
np.random.seed(seed)
np.random.shuffle(labels)
if start_char is not None:
X = [[start_char] + [w + index_from for w in x] for x in X]
elif index_from:
X = [[w + index_from for w in x] for x in X]
if maxlen:
new_X = []
new_labels = []
for x, y in zip(X, labels):
if len(x) < maxlen:
new_X.append(x)
new_labels.append(y)
X = new_X
labels = new_labels
if not X:
raise Exception('After filtering for sequences shorter than maxlen=' +
str(maxlen) + ', no sequence was kept. '
'Increase maxlen.')
if not nb_words:
nb_words = max([max(x) for x in X])
# by convention, use 2 as OOV word
# reserve 'index_from' (=3 by default) characters: 0 (padding), 1 (start), 2 (OOV)
if oov_char is not None:
X = [[oov_char if (w >= nb_words or w < skip_top) else w for w in x] for x in X]
else:
nX = []
for x in X:
nx = []
for w in x:
if (w >= nb_words or w < skip_top):
nx.append(w)
nX.append(nx)
X = nX
X_train = np.array(X[:int(len(X) * (1 - test_split))])
y_train = np.array(labels[:int(len(X) * (1 - test_split))])
X_test = np.array(X[int(len(X) * (1 - test_split)):])
y_test = np.array(labels[int(len(X) * (1 - test_split)):])
return X_train, y_train, X_test, y_test
def load_nietzsche_dataset(path='data/nietzsche/'):
"""Load Nietzsche dataset.
Returns a string.
Parameters
----------
path : string
The path that the data is downloaded to, defaults is ``data/nietzsche/``.
Examples
--------
>>> see tutorial_generate_text.py
>>> words = tl.files.load_nietzsche_dataset()
>>> words = basic_clean_str(words)
>>> words = words.split()
"""
print("Load or Download nietzsche dataset > {}".format(path))
filename = "nietzsche.txt"
url = 'https://s3.amazonaws.com/text-datasets/'
filepath = maybe_download_and_extract(filename, path, url)
with open(filepath, "r") as f:
words = f.read()
return words
def load_wmt_en_fr_dataset(path='data/wmt_en_fr/'):
"""It will download English-to-French translation data from the WMT'15
Website (10^9-French-English corpus), and the 2013 news test from
the same site as development set.
Returns the directories of training data and test data.
Parameters
----------
path : string
The path that the data is downloaded to, defaults is ``data/wmt_en_fr/``.
References
----------
- Code modified from /tensorflow/models/rnn/translation/data_utils.py
Notes
-----
Usually, it will take a long time to download this dataset.
"""
# URLs for WMT data.
_WMT_ENFR_TRAIN_URL = "http://www.statmt.org/wmt10/"
_WMT_ENFR_DEV_URL = "http://www.statmt.org/wmt15/"
def gunzip_file(gz_path, new_path):
"""Unzips from gz_path into new_path."""
print("Unpacking %s to %s" % (gz_path, new_path))
with gzip.open(gz_path, "rb") as gz_file:
with open(new_path, "wb") as new_file:
for line in gz_file:
new_file.write(line)
def get_wmt_enfr_train_set(path):
"""Download the WMT en-fr training corpus to directory unless it's there."""
filename = "training-giga-fren.tar"
maybe_download_and_extract(filename, path, _WMT_ENFR_TRAIN_URL, extract=True)
train_path = os.path.join(path, "giga-fren.release2.fixed")
gunzip_file(train_path + ".fr.gz", train_path + ".fr")
gunzip_file(train_path + ".en.gz", train_path + ".en")
return train_path
def get_wmt_enfr_dev_set(path):
"""Download the WMT en-fr training corpus to directory unless it's there."""
filename = "dev-v2.tgz"
dev_file = maybe_download_and_extract(filename, path, _WMT_ENFR_DEV_URL, extract=False)
dev_name = "newstest2013"
dev_path = os.path.join(path, "newstest2013")
if not (gfile.Exists(dev_path + ".fr") and gfile.Exists(dev_path + ".en")):
print("Extracting tgz file %s" % dev_file)
with tarfile.open(dev_file, "r:gz") as dev_tar:
fr_dev_file = dev_tar.getmember("dev/" + dev_name + ".fr")
en_dev_file = dev_tar.getmember("dev/" + dev_name + ".en")
fr_dev_file.name = dev_name + ".fr" # Extract without "dev/" prefix.
en_dev_file.name = dev_name + ".en"
dev_tar.extract(fr_dev_file, path)
dev_tar.extract(en_dev_file, path)
return dev_path
print("Load or Download WMT English-to-French translation > {}".format(path))
train_path = get_wmt_enfr_train_set(path)
dev_path = get_wmt_enfr_dev_set(path)
return train_path, dev_path
def load_flickr25k_dataset(tag='sky', path="data/flickr25k", n_threads=50, printable=False):
"""Returns a list of images by a given tag from Flick25k dataset,
it will download Flickr25k from `the official website <http://press.liacs.nl/mirflickr/mirdownload.html>`_
at the first time you use it.
Parameters
------------
tag : string or None
If you want to get images with tag, use string like 'dog', 'red', see `Flickr Search <https://www.flickr.com/search/>`_.
If you want to get all images, set to ``None``.
path : string
The path that the data is downloaded to, defaults is ``data/flickr25k/``.
n_threads : int, number of thread to read image.
printable : bool, print infomation when reading images, default is ``False``.
Examples
-----------
- Get images with tag of sky
>>> images = tl.files.load_flickr25k_dataset(tag='sky')
- Get all images
>>> images = tl.files.load_flickr25k_dataset(tag=None, n_threads=100, printable=True)
"""
filename = 'mirflickr25k.zip'
url = 'http://press.liacs.nl/mirflickr/mirflickr25k/'
## download dataset
if folder_exists(path+"/mirflickr") is False:
print("[*] Flickr25k is nonexistent in {}".format(path))
maybe_download_and_extract(filename, path, url, extract=True)
del_file(path+'/'+filename)
## return images by the given tag.
# 1. image path list
folder_imgs = path+"/mirflickr"
path_imgs = load_file_list(path=folder_imgs, regx='\\.jpg', printable=False)
path_imgs.sort(key=natural_keys)
# print(path_imgs[0:10])
# 2. tag path list
folder_tags = path+"/mirflickr/meta/tags"
path_tags = load_file_list(path=folder_tags, regx='\\.txt', printable=False)
path_tags.sort(key=natural_keys)
# print(path_tags[0:10])
# 3. select images
if tag is None:
print("[Flickr25k] reading all images")
else:
print("[Flickr25k] reading images with tag: {}".format(tag))
images_list = []
for idx in range(0, len(path_tags)):
tags = read_file(folder_tags+'/'+path_tags[idx]).split('\n')
# print(idx+1, tags)
if tag is None or tag in tags:
images_list.append(path_imgs[idx])
images = visualize.read_images(images_list, folder_imgs, n_threads=n_threads, printable=printable)
return images
def load_flickr1M_dataset(tag='sky', size=10, path="data/flickr1M", n_threads=50, printable=False):
"""Returns a list of images by a given tag from Flickr1M dataset,
it will download Flickr1M from `the official website <http://press.liacs.nl/mirflickr/mirdownload.html>`_
at the first time you use it.
Parameters
------------
tag : string or None
If you want to get images with tag, use string like 'dog', 'red', see `Flickr Search <https://www.flickr.com/search/>`_.
If you want to get all images, set to ``None``.
size : int 1 to 10.
1 means 100k images ... 5 means 500k images, 10 means all 1 million images. Default is 10.
path : string
The path that the data is downloaded to, defaults is ``data/flickr25k/``.
n_threads : int, number of thread to read image.
printable : bool, print infomation when reading images, default is ``False``.
Examples
----------
- Use 200k images
>>> images = tl.files.load_flickr1M_dataset(tag='zebra', size=2)
- Use 1 Million images
>>> images = tl.files.load_flickr1M_dataset(tag='zebra')
"""
print("[Flickr1M] using {}% of images = {}".format(size*10, size*100000))
images_zip = ['images0.zip', 'images1.zip', 'images2.zip', 'images3.zip',
'images4.zip', 'images5.zip', 'images6.zip', 'images7.zip',
'images8.zip', 'images9.zip']
tag_zip = 'tags.zip'
url = 'http://press.liacs.nl/mirflickr/mirflickr1m/'
## download dataset
for image_zip in images_zip[0:size]:
image_folder = image_zip.split(".")[0]
# print(path+"/"+image_folder)
if folder_exists(path+"/"+image_folder) is False:
# print(image_zip)
print("[Flickr1M] {} is missing in {}".format(image_folder, path))
maybe_download_and_extract(image_zip, path, url, extract=True)
del_file(path+'/'+image_zip)
os.system("mv {} {}".format(path+'/images',path+'/'+image_folder))
else:
print("[Flickr1M] {} exists in {}".format(image_folder, path))
## download tag
if folder_exists(path+"/tags") is False:
print("[Flickr1M] tag files is nonexistent in {}".format(path))
maybe_download_and_extract(tag_zip, path, url, extract=True)
del_file(path+'/'+tag_zip)
else:
print("[Flickr1M] tags exists in {}".format(path))
## 1. image path list
images_list = []
images_folder_list = []
for i in range(0, size):
images_folder_list += load_folder_list(path=path+'/images%d'%i)
images_folder_list.sort(key=lambda s : int(s.split('/')[-1])) # folder/images/ddd
# print(images_folder_list)
# exit()
for folder in images_folder_list[0:size*10]:
tmp = load_file_list(path=folder, regx='\\.jpg', printable=False)
tmp.sort(key=lambda s : int(s.split('.')[-2])) # ddd.jpg
# print(tmp[0::570])
images_list.extend([folder+'/'+x for x in tmp])
# print('IM', len(images_list), images_list[0::6000])
## 2. tag path list
tag_list = []
tag_folder_list = load_folder_list(path+"/tags")
tag_folder_list.sort(key=lambda s : int(s.split('/')[-1])) # folder/images/ddd
for folder in tag_folder_list[0:size*10]:
# print(folder)
tmp = load_file_list(path=folder, regx='\\.txt', printable=False)
tmp.sort(key=lambda s : int(s.split('.')[-2])) # ddd.txt
tmp = [folder+'/'+s for s in tmp]
tag_list += tmp
# print('T', len(tag_list), tag_list[0::6000])
# exit()
## 3. select images
print("[Flickr1M] searching tag: {}".format(tag))
select_images_list = []
for idx in range(0, len(tag_list)):
tags = read_file(tag_list[idx]).split('\n')
if tag in tags:
select_images_list.append(images_list[idx])
# print(idx, tags, tag_list[idx], images_list[idx])
print("[Flickr1M] reading images with tag: {}".format(tag))
images = visualize.read_images(select_images_list, '', n_threads=n_threads, printable=printable)
return images
def load_cyclegan_dataset(filename='summer2winter_yosemite', path='data/cyclegan'):
"""Load image data from CycleGAN's database, see `this link <https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/>`_.
Parameters
------------
filename : string
The dataset you want, see `this link <https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/>`_.
path : string
The path that the data is downloaded to, defaults is `data/cyclegan`
Examples
---------
>>> im_train_A, im_train_B, im_test_A, im_test_B = load_cyclegan_dataset(filename='summer2winter_yosemite')
"""
url = 'https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/'
if folder_exists(path+"/"+filename) is False:
print("[*] {} is nonexistent in {}".format(filename, path))
maybe_download_and_extract(filename+'.zip', path, url, extract=True)
del_file(path+'/'+filename+'.zip')
def load_image_from_folder(path):
path_imgs = load_file_list(path=path, regx='\\.jpg', printable=False)
return visualize.read_images(path_imgs, path=path, n_threads=10, printable=False)
im_train_A = load_image_from_folder(path+"/"+filename+"/trainA")
im_train_B = load_image_from_folder(path+"/"+filename+"/trainB")
im_test_A = load_image_from_folder(path+"/"+filename+"/testA")
im_test_B = load_image_from_folder(path+"/"+filename+"/testB")
def if_2d_to_3d(images): # [h, w] --> [h, w, 3]
for i in range(len(images)):
if len(images[i].shape) == 2:
images[i] = images[i][:, :, np.newaxis]
images[i] = np.tile(images[i], (1, 1, 3))
return images
im_train_A = if_2d_to_3d(im_train_A)
im_train_B = if_2d_to_3d(im_train_B)
im_test_A = if_2d_to_3d(im_test_A)
im_test_B = if_2d_to_3d(im_test_B)
return im_train_A, im_train_B, im_test_A, im_test_B
## Load and save network list npz
def save_npz(save_list=[], name='model.npz', sess=None):
"""Input parameters and the file name, save parameters into .npz file. Use tl.utils.load_npz() to restore.
Parameters
----------
save_list : a list
Parameters want to be saved.
name : a string or None
The name of the .npz file.
sess : None or Session
Examples
--------
>>> tl.files.save_npz(network.all_params, name='model_test.npz', sess=sess)
... File saved to: model_test.npz
>>> load_params = tl.files.load_npz(name='model_test.npz')
... Loading param0, (784, 800)
... Loading param1, (800,)
... Loading param2, (800, 800)
... Loading param3, (800,)
... Loading param4, (800, 10)
... Loading param5, (10,)
>>> put parameters into a TensorLayer network, please see assign_params()
Notes
-----
If you got session issues, you can change the value.eval() to value.eval(session=sess)
References
----------
- `Saving dictionary using numpy <http://stackoverflow.com/questions/22315595/saving-dictionary-of-header-information-using-numpy-savez>`_
"""
## save params into a list
save_list_var = []
if sess:
save_list_var = sess.run(save_list)
else:
try:
for k, value in enumerate(save_list):
save_list_var.append(value.eval())
except:
print(" Fail to save model, Hint: pass the session into this function, save_npz(network.all_params, name='model.npz', sess=sess)")
np.savez(name, params=save_list_var)
save_list_var = None
del save_list_var
print("[*] %s saved" % name)
## save params into a dictionary
# rename_dict = {}
# for k, value in enumerate(save_dict):
# rename_dict.update({'param'+str(k) : value.eval()})
# np.savez(name, **rename_dict)
# print('Model is saved to: %s' % name)
def load_npz(path='', name='model.npz'):
"""Load the parameters of a Model saved by tl.files.save_npz().
Parameters
----------
path : a string
Folder path to .npz file.
name : a string or None
The name of the .npz file.
Returns
--------
params : list
A list of parameters in order.
Examples
--------
- See save_npz and assign_params
References
----------
- `Saving dictionary using numpy <http://stackoverflow.com/questions/22315595/saving-dictionary-of-header-information-using-numpy-savez>`_
"""
## if save_npz save params into a dictionary
# d = np.load( path+name )
# params = []
# print('Load Model')
# for key, val in sorted( d.items() ):
# params.append(val)
# print('Loading %s, %s' % (key, str(val.shape)))
# return params
## if save_npz save params into a list
d = np.load( path+name )
# for val in sorted( d.items() ):
# params = val
# return params
return d['params']
# print(d.items()[0][1]['params'])
# exit()
# return d.items()[0][1]['params']
def assign_params(sess, params, network):
"""Assign the given parameters to the TensorLayer network.
Parameters
----------
sess : TensorFlow Session. Automatically run when sess is not None.
params : a list
A list of parameters in order.
network : a :class:`Layer` class
The network to be assigned
Returns
--------
ops : list
A list of tf ops in order that assign params. Support sess.run(ops) manually.
Examples
--------
>>> Save your network as follow:
>>> tl.files.save_npz(network.all_params, name='model_test.npz')
>>> network.print_params()
...
... Next time, load and assign your network as follow:
>>> tl.layers.initialize_global_variables(sess)
>>> load_params = tl.files.load_npz(name='model_test.npz')
>>> tl.files.assign_params(sess, load_params, network)
>>> network.print_params()
References
----------
- `Assign value to a TensorFlow variable <http://stackoverflow.com/questions/34220532/how-to-assign-value-to-a-tensorflow-variable>`_
"""
ops = []
for idx, param in enumerate(params):
ops.append(network.all_params[idx].assign(param))
if sess is not None:
sess.run(ops)
return ops
def load_and_assign_npz(sess=None, name=None, network=None):
"""Load model from npz and assign to a network.
Parameters
-------------
sess : TensorFlow Session
name : string
Model path.
network : a :class:`Layer` class
The network to be assigned
Returns
--------
Returns False if faild to model is not exist.
Examples
---------
>>> tl.files.load_and_assign_npz(sess=sess, name='net.npz', network=net)
"""
assert network is not None
assert sess is not None
if not os.path.exists(name):
print("[!] Load {} failed!".format(name))
return False
else:
params = load_npz(name=name)
assign_params(sess, params, network)
print("[*] Load {} SUCCESS!".format(name))
return network
## Load and save network dict npz
def save_npz_dict(save_list=[], name='model.npz', sess=None):
"""Input parameters and the file name, save parameters as a dictionary into .npz file.
Use ``tl.files.load_and_assign_npz_dict()`` to restore.
Parameters
----------
save_list : a list to tensor for parameters
Parameters want to be saved.
name : a string
The name of the .npz file.
sess : Session
"""
assert sess is not None
save_list_names = [tensor.name for tensor in save_list]
save_list_var = sess.run(save_list)
save_var_dict = {save_list_names[idx]: val for idx, val in enumerate(save_list_var)}
np.savez(name, **save_var_dict)
save_list_var = None
save_var_dict = None
del save_list_var
del save_var_dict
print("[*] Model saved in npz_dict %s" % name)
def load_and_assign_npz_dict(name='model.npz', sess=None):
"""Restore the parameters saved by ``tl.files.save_npz_dict()``.
Parameters
----------
name : a string
The name of the .npz file.
sess : Session
"""
assert sess is not None
if not os.path.exists(name):
print("[!] Load {} failed!".format(name))
return False
params = np.load(name)
if len(params.keys()) != len(set(params.keys())):
raise Exception("Duplication in model npz_dict %s" % name)
ops = list()
for key in params.keys():
try:
# tensor = tf.get_default_graph().get_tensor_by_name(key)
# varlist = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope=key)
varlist = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope=key)
if len(varlist) > 1:
raise Exception("[!] Multiple candidate variables to be assigned for name %s" % key)
elif len(varlist) == 0:
raise KeyError
else:
ops.append(varlist[0].assign(params[key]))
print("[*] params restored: %s" % key)
except KeyError:
print("[!] Warning: Tensor named %s not found in network." % key)
sess.run(ops)
print("[*] Model restored from npz_dict %s" % name)
# def save_npz_dict(save_list=[], name='model.npz', sess=None):
# """Input parameters and the file name, save parameters as a dictionary into .npz file. Use tl.utils.load_npz_dict() to restore.
#
# Parameters
# ----------
# save_list : a list
# Parameters want to be saved.
# name : a string or None
# The name of the .npz file.
# sess : None or Session
#
# Notes
# -----
# This function tries to avoid a potential broadcasting error raised by numpy.
#
# """
# ## save params into a list
# save_list_var = []
# if sess:
# save_list_var = sess.run(save_list)
# else:
# try:
# for k, value in enumerate(save_list):
# save_list_var.append(value.eval())
# except:
# print(" Fail to save model, Hint: pass the session into this function, save_npz_dict(network.all_params, name='model.npz', sess=sess)")
# save_var_dict = {str(idx):val for idx, val in enumerate(save_list_var)}
# np.savez(name, **save_var_dict)
# save_list_var = None
# save_var_dict = None
# del save_list_var
# del save_var_dict
# print("[*] %s saved" % name)
#
# def load_npz_dict(path='', name='model.npz'):
# """Load the parameters of a Model saved by tl.files.save_npz_dict().
#
# Parameters
# ----------
# path : a string
# Folder path to .npz file.
# name : a string or None
# The name of the .npz file.
#
# Returns
# --------
# params : list
# A list of parameters in order.
# """
# d = np.load( path+name )
# saved_list_var = [val[1] for val in sorted(d.items(), key=lambda tup: int(tup[0]))]
# return saved_list_var
## Load and save network ckpt
def save_ckpt(sess=None, mode_name='model.ckpt', save_dir='checkpoint', var_list=[], global_step=None, printable=False):
"""Save parameters into ckpt file.
Parameters
------------
sess : Session.
mode_name : string, name of the model, default is ``model.ckpt``.
save_dir : string, path / file directory to the ckpt, default is ``checkpoint``.
var_list : list of variables, if not given, save all global variables.
global_step : int or None, step number.
printable : bool, if True, print all params info.
Examples
---------
- see ``tl.files.load_ckpt()``.
"""
assert sess is not None
ckpt_file = os.path.join(save_dir, mode_name)
if var_list == []:
var_list = tf.global_variables()
print("[*] save %s n_params: %d" % (ckpt_file, len(var_list)))
if printable:
for idx, v in enumerate(var_list):
print(" param {:3}: {:15} {}".format(idx, v.name, str(v.get_shape())))
saver = tf.train.Saver(var_list)
saver.save(sess, ckpt_file, global_step=global_step)
def load_ckpt(sess=None, mode_name='model.ckpt', save_dir='checkpoint', var_list=[], is_latest=True, printable=False):
"""Load parameters from ckpt file.
Parameters
------------
sess : Session.
mode_name : string, name of the model, default is ``model.ckpt``.
Note that if ``is_latest`` is True, this function will get the ``mode_name`` automatically.
save_dir : string, path / file directory to the ckpt, default is ``checkpoint``.
var_list : list of variables, if not given, save all global variables.
is_latest : bool, if True, load the latest ckpt, if False, load the ckpt with the name of ```mode_name``.
printable : bool, if True, print all params info.
Examples
----------
- Save all global parameters.
>>> tl.files.save_ckpt(sess=sess, mode_name='model.ckpt', save_dir='model', printable=True)
- Save specific parameters.
>>> tl.files.save_ckpt(sess=sess, mode_name='model.ckpt', var_list=net.all_params, save_dir='model', printable=True)
- Load latest ckpt.
>>> tl.files.load_ckpt(sess=sess, var_list=net.all_params, save_dir='model', printable=True)
- Load specific ckpt.
>>> tl.files.load_ckpt(sess=sess, mode_name='model.ckpt', var_list=net.all_params, save_dir='model', is_latest=False, printable=True)
"""
assert sess is not None
if is_latest:
ckpt_file = tf.train.latest_checkpoint(save_dir)
else:
ckpt_file = os.path.join(save_dir, mode_name)
if var_list == []:
var_list = tf.global_variables()
print("[*] load %s n_params: %d" % (ckpt_file, len(var_list)))
if printable:
You can’t perform that action at this time.