Mercurial > pylearn

annotate pylearn/algorithms/tests/test_mcRBM.py @ 1508:b28e8730c948

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
fix test.
author Frederic Bastien <nouiz@nouiz.org>
date Mon, 12 Sep 2011 11:45:56 -0400
parents 2a6a6f16416c
children b709f6b53b17
rev   line source
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
1 import sys
1507
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
2
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
3 import numpy
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
4 import theano
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
5 from theano import tensor
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
6
1507
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
7 from pylearn.algorithms.mcRBM import mcRBM, mcRBMTrainer, mcRBM_withP, l2
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
8 #import pylearn.datasets.cifar10
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
9 import pylearn.dataset_ops.cifar10
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
10 from pylearn.shared.layers.logreg import LogisticRegression
1507
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
11 from pylearn.io import image_tiling
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
12 import pylearn.dataset_ops.image_patches
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
13
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
14
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
15 def _default_rbm_alloc(n_I, n_K=256, n_J=100):
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
16 return mcRBM.alloc(n_I, n_K, n_J)
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
17
1508
b28e8730c948 fix test.
Frederic Bastien <nouiz@nouiz.org>
parents: 1507
diff changeset
18 def _default_trainer_alloc(rbm, train_batch, batchsize, initial_lr_per_example,
b28e8730c948 fix test.
Frederic Bastien <nouiz@nouiz.org>
parents: 1507
diff changeset
19 l1_penalty, l1_penalty_start, persistent_chains):
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
20 return mcRBMTrainer.alloc(rbm, train_batch, batchsize, l1_penalty=l1_penalty,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
21 l1_penalty_start=l1_penalty_start,persistent_chains=persistent_chains)
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
22
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
23
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
24 def test_reproduce_ranzato_hinton_2010(dataset='MAR', as_unittest=True, n_train_iters=5000,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
25 rbm_alloc=_default_rbm_alloc, trainer_alloc=_default_trainer_alloc,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
26 lr_per_example=.075,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
27 l1_penalty=1e-3,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
28 l1_penalty_start=1000,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
29 persistent_chains=True,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
30 ):
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
31
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
32 batchsize = 128
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
33
1000
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
34 if dataset == 'MAR':
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
35 n_vis=105
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
36 n_patches=10240
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
37 epoch_size=n_patches
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
38 elif dataset=='cifar10patches8x8':
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
39 R,C= 8,8 # the size of image patches
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
40 n_vis=96 # pca components
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
41 epoch_size=batchsize*500
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
42 n_patches=epoch_size*20
1286
8905186b176c test_mcRBM - added code to iterate over tinyimages
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1284
diff changeset
43 elif dataset=='tinyimages_patches':
8905186b176c test_mcRBM - added code to iterate over tinyimages
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1284
diff changeset
44 R,C=8,8
8905186b176c test_mcRBM - added code to iterate over tinyimages
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1284
diff changeset
45 n_vis=81
8905186b176c test_mcRBM - added code to iterate over tinyimages
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1284
diff changeset
46 epoch_size=batchsize*500
8905186b176c test_mcRBM - added code to iterate over tinyimages
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1284
diff changeset
47 n_patches=epoch_size*20
1000
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
48 else:
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
49 R,C= 16,16 # the size of image patches
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
50 n_vis=R*C
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
51 n_patches=100000
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
52 epoch_size=n_patches
1000
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
53
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
54 def l2(X):
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
55 return numpy.sqrt((X**2).sum())
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
56
1000
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
57 if dataset == 'MAR':
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
58 tile = pylearn.dataset_ops.image_patches.save_filters_of_ranzato_hinton_2010
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
59 elif dataset == 'cifar10patches8x8':
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
60 def tile(X, fname):
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
61 _img = pylearn.datasets.cifar10.tile_rasterized_examples(
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
62 pylearn.preprocessing.pca.pca_whiten_inverse(
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
63 pylearn.dataset_ops.cifar10.random_cifar_patches_pca(
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
64 n_vis, None, 'float32', n_patches, R, C,),
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
65 X),
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
66 img_shape=(R,C))
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
67 image_tiling.save_tiled_raster_images(_img, fname)
1286
8905186b176c test_mcRBM - added code to iterate over tinyimages
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1284
diff changeset
68 elif dataset == 'tinyimages_patches':
8905186b176c test_mcRBM - added code to iterate over tinyimages
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1284
diff changeset
69 tile = pylearn.dataset_ops.tinyimages.save_filters
1000
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
70 else:
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
71 def tile(X, fname):
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
72 _img = image_tiling.tile_raster_images(X,
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
73 img_shape=(R,C),
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
74 min_dynamic_range=1e-2)
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
75 image_tiling.save_tiled_raster_images(_img, fname)
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
76
1507
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
77 batch_idx = tensor.iscalar()
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
78 batch_range =batch_idx * batchsize + numpy.arange(batchsize)
1000
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
79
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
80 if dataset == 'MAR':
1286
8905186b176c test_mcRBM - added code to iterate over tinyimages
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1284
diff changeset
81 train_batch = pylearn.dataset_ops.image_patches.ranzato_hinton_2010_op(batch_range)
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
82 elif dataset == 'cifar10patches8x8':
1286
8905186b176c test_mcRBM - added code to iterate over tinyimages
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1284
diff changeset
83 train_batch = pylearn.dataset_ops.cifar10.cifar10_patches(
8905186b176c test_mcRBM - added code to iterate over tinyimages
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1284
diff changeset
84 batch_range, 'train', n_patches=n_patches, patch_size=(R,C),
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
85 pca_components=n_vis)
1286
8905186b176c test_mcRBM - added code to iterate over tinyimages
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1284
diff changeset
86 elif dataset == 'tinyimages_patches':
8905186b176c test_mcRBM - added code to iterate over tinyimages
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1284
diff changeset
87 train_batch = pylearn.dataset_ops.tinyimages.tinydataset_op(batch_range)
1000
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
88 else:
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
89 train_batch = pylearn.dataset_ops.image_patches.image_patches(
1507
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
90 s_idx = (batch_idx * batchsize + numpy.arange(batchsize)),
1000
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
91 dims = (n_patches,R,C),
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
92 center=True,
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
93 unitvar=True,
1507
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
94 dtype=theano.config.floatX,
1000
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
95 rasterized=True)
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
96
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
97 if not as_unittest:
1507
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
98 imgs_fn = theano.function([batch_idx], outputs=train_batch)
1000
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
99
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
100 trainer = trainer_alloc(
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
101 rbm_alloc(n_I=n_vis),
1267
075c193afd1b refactoring mcRBM
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1000
diff changeset
102 train_batch,
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
103 batchsize,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
104 initial_lr_per_example=lr_per_example,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
105 l1_penalty=l1_penalty,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
106 l1_penalty_start=l1_penalty_start,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
107 persistent_chains=persistent_chains)
1267
075c193afd1b refactoring mcRBM
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1000
diff changeset
108 rbm=trainer.rbm
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
109
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
110 if persistent_chains:
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
111 grads = trainer.contrastive_grads()
1507
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
112 learn_fn = theano.function([batch_idx],
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
113 outputs=[grads[0].norm(2), grads[0].norm(2), grads[1].norm(2)],
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
114 updates=trainer.cd_updates())
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
115 else:
1507
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
116 learn_fn = theano.function([batch_idx], outputs=[], updates=trainer.cd_updates())
1267
075c193afd1b refactoring mcRBM
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1000
diff changeset
117
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
118 if persistent_chains:
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
119 smplr = trainer.sampler
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
120 else:
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
121 smplr = trainer._last_cd1_sampler
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
122
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
123 if dataset == 'cifar10patches8x8':
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
124 cPickle.dump(
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
125 pylearn.dataset_ops.cifar10.random_cifar_patches_pca(
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
126 n_vis, None, 'float32', n_patches, R, C,),
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
127 open('test_mcRBM.pca.pkl','w'))
1000
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
128
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
129 print "Learning..."
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
130 last_epoch = -1
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
131 for jj in xrange(n_train_iters):
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
132 epoch = jj*batchsize / epoch_size
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
133
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
134 print_jj = epoch != last_epoch
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
135 last_epoch = epoch
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
136
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
137 if as_unittest and epoch == 5:
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
138 U = rbm.U.value
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
139 W = rbm.W.value
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
140 def allclose(a,b):
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
141 return numpy.allclose(a,b,rtol=1.01,atol=1e-3)
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
142 print ""
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
143 print "--------------"
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
144 print "assert allclose(l2(U), %f)"%l2(U)
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
145 print "assert allclose(l2(W), %f)"%l2(W)
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
146 print "assert allclose(U.min(), %f)"%U.min()
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
147 print "assert allclose(U.max(), %f)"%U.max()
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
148 print "assert allclose(W.min(),%f)"%W.min()
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
149 print "assert allclose(W.max(), %f)"%W.max()
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
150 print "--------------"
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
151
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
152 assert allclose(l2(U), 21.351664)
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
153 assert allclose(l2(W), 6.275828)
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
154 assert allclose(U.min(), -1.176703)
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
155 assert allclose(U.max(), 0.859802)
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
156 assert allclose(W.min(),-0.223128)
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
157 assert allclose(W.max(), 0.227558 )
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
158
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
159 break
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
160
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
161 if print_jj:
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
162 if not as_unittest:
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
163 tile(imgs_fn(jj), "imgs_%06i.png"%jj)
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
164 if persistent_chains:
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
165 tile(smplr.positions.value, "sample_%06i.png"%jj)
1000
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
166 tile(rbm.U.value.T, "U_%06i.png"%jj)
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
167 tile(rbm.W.value.T, "W_%06i.png"%jj)
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
168
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
169 print 'saving samples', jj, 'epoch', jj/(epoch_size/batchsize)
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
170
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
171 print 'l2(U)', l2(rbm.U.value),
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
172 print 'l2(W)', l2(rbm.W.value),
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
173 print 'l1_penalty',
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
174 try:
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
175 print trainer.effective_l1_penalty.value
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
176 except:
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
177 print trainer.effective_l1_penalty
1000
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
178
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
179 print 'U min max', rbm.U.value.min(), rbm.U.value.max(),
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
180 print 'W min max', rbm.W.value.min(), rbm.W.value.max(),
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
181 print 'a min max', rbm.a.value.min(), rbm.a.value.max(),
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
182 print 'b min max', rbm.b.value.min(), rbm.b.value.max(),
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
183 print 'c min max', rbm.c.value.min(), rbm.c.value.max()
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
184
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
185 if persistent_chains:
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
186 print 'parts min', smplr.positions.value.min(),
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
187 print 'max',smplr.positions.value.max(),
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
188 print 'HMC step', smplr.stepsize.value,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
189 print 'arate', smplr.avg_acceptance_rate.value
1000
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
190
1267
075c193afd1b refactoring mcRBM
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1000
diff changeset
191
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
192 l2_of_Ugrad = learn_fn(jj)
1000
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
193
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
194 if persistent_chains and print_jj:
1000
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
195 print 'l2(U_grad)', float(l2_of_Ugrad[0]),
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
196 print 'l2(U_inc)', float(l2_of_Ugrad[1]),
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
197 print 'l2(W_inc)', float(l2_of_Ugrad[2]),
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
198 #print 'FE+', float(l2_of_Ugrad[2]),
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
199 #print 'FE+[0]', float(l2_of_Ugrad[3]),
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
200 #print 'FE+[1]', float(l2_of_Ugrad[4]),
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
201 #print 'FE+[2]', float(l2_of_Ugrad[5]),
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
202 #print 'FE+[3]', float(l2_of_Ugrad[6])
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
203
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
204 if not as_unittest:
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
205 if jj % 2000 == 0:
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
206 print ''
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
207 print 'Saving rbm...'
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
208 cPickle.dump(rbm, open('mcRBM.rbm.%06i.pkl'%jj, 'w'), -1)
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
209 if persistent_chains:
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
210 print 'Saving sampler...'
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
211 cPickle.dump(smplr, open('mcRBM.smplr.%06i.pkl'%jj, 'w'), -1)
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
212
1000
d4a14c6c36e0 mcRBM - post code-review #1 with Guillaume
James Bergstra <bergstrj@iro.umontreal.ca>
parents:
diff changeset
213
1273
7bb5dd98e671 mcRBM - added hack to main script to pickle final model and sampler
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1272
diff changeset
214 if not as_unittest:
7bb5dd98e671 mcRBM - added hack to main script to pickle final model and sampler
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1272
diff changeset
215 return rbm, smplr
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
216
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
217
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
218 def run_classif_experiment(checkpoint):
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
219
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
220 R,C=8,8
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
221 n_vis=74
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
222 # PRETRAIN
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
223 #
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
224 # extract 1 million 8x8 patches from TinyImages
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
225 # pre-process them the right way
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
226 # find 74 dims of PCA
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
227 # filter patches through PCA
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
228 whitened_patches, pca_dct = pylearn.dataset_ops.tinyimages.main(n_imgs=100000,
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
229 max_components=n_vis, seed=234)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
230 #
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
231 # Set up mcRBM Trainer
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
232 # Initialize P using topological 3x3 overlapping patches thing
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
233 # start learning P matrix after 2 passes through dataset
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
234 #
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
235 rbm_filename = 'mcRBM.rbm.%06i.pkl'%46000
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
236 try:
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
237 open(rbm_filename).close()
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
238 load_mcrbm = True
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
239 except:
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
240 load_mcrbm = False
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
241
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
242 if load_mcrbm:
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
243 print 'loading mcRBM from file', rbm_filename
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
244 rbm = cPickle.load(open(rbm_filename))
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
245
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
246 else:
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
247 print "Training mcRBM"
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
248 batchsize=128
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
249 epoch_size=len(whitened_patches)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
250 tile = pylearn.dataset_ops.tinyimages.save_filters
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
251 train_batch = theano.tensor.matrix()
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
252 trainer = mcRBMTrainer.alloc_for_P(
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
253 rbm=mcRBM_withP.alloc_topo_P(n_I=n_vis, n_J=81),
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
254 visible_batch=train_batch,
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
255 batchsize=batchsize,
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
256 initial_lr_per_example=0.05,
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
257 l1_penalty=1e-3,
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
258 l1_penalty_start=sys.maxint,
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
259 p_training_start=2*epoch_size//batchsize,
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
260 persistent_chains=False)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
261 rbm=trainer.rbm
1507
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
262 learn_fn = theano.function([train_batch], outputs=[], updates=trainer.cd_updates())
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
263 smplr = trainer._last_cd1_sampler
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
264
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
265 ii = 0
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
266 for i_epoch in range(6):
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
267 for i_batch in xrange(epoch_size // batchsize):
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
268 batch_vals = whitened_patches[i_batch*batchsize:(i_batch+1)*batchsize]
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
269 learn_fn(batch_vals)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
270
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
271 if (ii % 1000) == 0:
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
272 #tile(imgs_fn(ii), "imgs_%06i.png"%ii)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
273 tile(rbm.U.value.T, "U_%06i.png"%ii)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
274 tile(rbm.W.value.T, "W_%06i.png"%ii)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
275
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
276 print 'saving samples', ii, 'epoch', i_epoch, i_batch
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
277
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
278 print 'l2(U)', l2(rbm.U.value),
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
279 print 'l2(W)', l2(rbm.W.value),
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
280 print 'l1_penalty',
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
281 try:
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
282 print trainer.effective_l1_penalty.value
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
283 except:
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
284 print trainer.effective_l1_penalty
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
285
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
286 print 'U min max', rbm.U.value.min(), rbm.U.value.max(),
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
287 print 'W min max', rbm.W.value.min(), rbm.W.value.max(),
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
288 print 'a min max', rbm.a.value.min(), rbm.a.value.max(),
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
289 print 'b min max', rbm.b.value.min(), rbm.b.value.max(),
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
290 print 'c min max', rbm.c.value.min(), rbm.c.value.max()
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
291
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
292 print 'HMC step', smplr.stepsize.value,
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
293 print 'arate', smplr.avg_acceptance_rate.value
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
294 print 'P min max', rbm.P.value.min(), rbm.P.value.max(),
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
295 print 'P_lr', trainer.p_lr.value
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
296 print ''
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
297 print 'Saving rbm...'
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
298 cPickle.dump(rbm, open('mcRBM.rbm.%06i.pkl'%ii, 'w'), -1)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
299
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
300 ii += 1
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
301
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
302
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
303 # extract convolutional features from the CIFAR10 data
1333
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
304 feat_filename = 'mcrbm_features.npy'
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
305 feat_filename = 'cifar10.features.46000.npy'
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
306 try:
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
307 open(feat_filename).close()
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
308 load_features = True
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
309 except:
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
310 load_features = False
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
311
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
312 if load_features:
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
313 print 'Loading features from', feat_filename
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
314 all_features = numpy.load(feat_filename, mmap_mode='r')
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
315 else:
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
316 batchsize=100
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
317 feat_idx = tensor.lscalar()
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
318 feat_idx_range = feat_idx * batchsize + tensor.arange(batchsize)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
319 train_batch_x, train_batch_y = pylearn.dataset_ops.cifar10.cifar10(
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
320 feat_idx_range,
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
321 split='all',
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
322 dtype='uint8',
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
323 rasterized=False,
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
324 color='rgb')
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
325
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
326 WINDOW_SIZE=8
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
327 WINDOW_STRIDE=4
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
328
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
329 # put these into shared vars because support for big matrix constants is bad,
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
330 # (comparing them is slow)
1507
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
331 pca_eigvecs = theano.shared(pca_dct['eig_vecs'].astype('float32'))
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
332 pca_eigvals = theano.shared(pca_dct['eig_vals'].astype('float32'))
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
333 pca_mean = theano.shared(pca_dct['mean'].astype('float32'))
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
334
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
335 def theano_pca_whiten(X):
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
336 #copying preprepcessing.pca.pca_whiten
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
337 return tensor.true_div(
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
338 tensor.dot(X-pca_mean, pca_eigvecs),
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
339 tensor.sqrt(pca_eigvals)+1e-8)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
340
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
341 h_list = []
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
342 g_list = []
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
343 for r_offset in range(0, 32-WINDOW_SIZE+1, WINDOW_STRIDE):
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
344 for c_offset in range(0, 32-WINDOW_SIZE+1, WINDOW_STRIDE):
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
345 window = train_batch_x[:, r_offset:r_offset+WINDOW_SIZE,
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
346 c_offset:c_offset+WINDOW_SIZE, :]
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
347 assert window.dtype=='uint8'
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
348
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
349 #rasterize the patches
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
350 raster_window = tensor.flatten(tensor.cast(window, 'float32'),2)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
351
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
352 #subtract off the mean of each image
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
353 raster_window = raster_window - raster_window.mean(axis=1).reshape((batchsize,1))
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
354
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
355 h,g = rbm.expected_h_g_given_v(theano_pca_whiten(raster_window))
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
356
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
357 h_list.append(h)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
358 g_list.append(g)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
359
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
360 hg = tensor.concatenate(h_list + g_list, axis=1)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
361
1507
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
362 feat_fn = theano.function([feat_idx], hg)
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
363 features = numpy.empty((60000, 11025), dtype='float32')
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
364 for i in xrange(60000//batchsize):
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
365 if i % 100 == 0:
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
366 print("feature batch %i"%i)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
367 features[i*batchsize:(i+1)*batchsize] = feat_fn(i)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
368
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
369 print("saving features to %s"%feat_filename)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
370 numpy.save(feat_filename, features)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
371 all_features = features
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
372 del features
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
373
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
374
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
375 # CLASSIFY FEATURES
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
376
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
377 if 0:
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
378 # nothing to load
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
379 pass
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
380 else:
1333
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
381 batchsize=100
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
382
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
383 if feat_filename.startswith('cifar'):
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
384 learnrate = 0.002
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
385 l1_regularization = 0.004
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
386 anneal_epoch=100
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
387 n_epochs = 500
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
388 else:
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
389 learnrate = 0.005
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
390 l1_regularization = 0.004
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
391 n_epochs = 100
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
392 anneal_epoch=20
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
393
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
394 x_i = tensor.matrix()
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
395 y_i = tensor.ivector()
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
396 lr = tensor.scalar()
1333
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
397 #l1_regularization = float(sys.argv[1]) #1.e-3
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
398 #l2_regularization = float(sys.argv[2]) #1.e-3*0
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
399
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
400 feature_logreg = LogisticRegression.new(x_i,
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
401 n_in = 11025, n_out=10,
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
402 dtype=x_i.dtype)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
403
1333
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
404 # marc'aurelio does this...
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
405 feature_logreg.w.value = numpy.random.RandomState(44).randn(11025,10)*.02
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
406
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
407 traincost = feature_logreg.nll(y_i).sum()
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
408 traincost = traincost + abs(feature_logreg.w).sum() * l1_regularization
1333
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
409 #traincost = traincost + (feature_logreg.w**2).sum() * l2_regularization
1507
2a6a6f16416c fix import.
Frederic Bastien <nouiz@nouiz.org>
parents: 1335
diff changeset
410 train_logreg_fn = theano.function([x_i, y_i, lr],
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
411 [feature_logreg.nll(y_i).mean(),
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
412 feature_logreg.errors(y_i).mean()],
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
413 updates=pylearn.gd.sgd.sgd_updates(
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
414 params=feature_logreg.params,
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
415 grads=tensor.grad(traincost, feature_logreg.params),
1333
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
416 stepsizes=[lr,lr/10.]))
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
417
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
418 all_labels = pylearn.dataset_ops.cifar10.all_data_labels('uint8')[1]
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
419 pylearn.dataset_ops.cifar10.all_data_labels.forget() # clear memo cache
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
420 assert len(all_labels)==60000
1333
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
421 if 0:
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
422 print "Using validation set"
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
423 train_labels = all_labels[:40000]
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
424 valid_labels = all_labels[40000:50000]
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
425 test_labels = all_labels[50000:60000]
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
426 train_features = all_features[:40000]
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
427 valid_features = all_features[40000:50000]
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
428 test_features = all_features[50000:60000]
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
429 else:
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
430 print "NOT USING validation set"
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
431 train_labels = all_labels[:50000]
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
432 valid_labels = None
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
433 test_labels = all_labels[50000:60000]
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
434 train_features = all_features[:50000]
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
435 valid_features = None
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
436 test_features = all_features[50000:60000]
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
437
1333
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
438 if 1:
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
439 print "Computing mean and std.dev"
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
440 train_mean = train_features.mean(axis=0)
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
441 train_std = train_features.std(axis=0)+1e-4
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
442 preproc = lambda x: (x-train_mean)/(0.1+train_std)
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
443 else:
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
444 print "Not centering data"
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
445 preproc = lambda x:x
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
446
1333
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
447 for epoch in xrange(n_epochs):
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
448 print 'epoch', epoch
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
449 # validate
1333
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
450 # Marc'Aurelio, you crazy!!
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
451 # the division by batchsize is done in the cost function
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
452 e_lr = learnrate / (batchsize*max(1.0, numpy.floor(max(1., epoch/float(anneal_epoch))-2)))
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
453
1333
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
454 if valid_features is not None:
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
455 l01s = []
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
456 nlls = []
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
457 for i in xrange(10000/batchsize):
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
458 x_i = valid_features[i*batchsize:(i+1)*batchsize]
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
459 y_i = valid_labels[i*batchsize:(i+1)*batchsize]
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
460
1333
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
461 #lr=0.0 -> no learning, safe for validation set
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
462 nll, l01 = train_logreg_fn(preproc(x_i), y_i, 0.0)
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
463 nlls.append(nll)
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
464 l01s.append(l01)
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
465 print 'validate log_reg', numpy.mean(nlls), numpy.mean(l01s)
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
466
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
467 # test
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
468
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
469 l01s = []
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
470 nlls = []
1333
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
471 for i in xrange(len(test_features)//batchsize):
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
472 x_i = test_features[i*batchsize:(i+1)*batchsize]
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
473 y_i = test_labels[i*batchsize:(i+1)*batchsize]
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
474
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
475 #lr=0.0 -> no learning, safe for validation set
1333
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
476 nll, l01 = train_logreg_fn(preproc(x_i), y_i, 0.0)
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
477 nlls.append(nll)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
478 l01s.append(l01)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
479 print 'test log_reg', numpy.mean(nlls), numpy.mean(l01s)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
480
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
481 #train
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
482 l01s = []
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
483 nlls = []
1333
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
484 for i in xrange(len(train_features)//batchsize):
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
485 x_i = train_features[i*batchsize:(i+1)*batchsize]
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
486 y_i = train_labels[i*batchsize:(i+1)*batchsize]
1333
c7b2da4e2df6 modifs to test_mcRBM to reproduce mcRBM classif results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
487 nll, l01 = train_logreg_fn(preproc(x_i), y_i, e_lr)
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
488 nlls.append(nll)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
489 l01s.append(l01)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
490 print 'train log_reg', numpy.mean(nlls), numpy.mean(l01s)
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
491
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
492
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
493
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
494
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
495 import pickle as cPickle
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
496 #import cPickle
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
497 if __name__ == '__main__':
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
498 if 0:
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
499 #learning 16 x 16 pinwheel filters from official cifar patches (MAR)
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
500 rbm,smplr = test_reproduce_ranzato_hinton_2010(
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
501 as_unittest=False,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
502 n_train_iters=5000,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
503 rbm_alloc=lambda n_I : mcRBM_withP.alloc_topo_P(n_I, n_J=81),
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
504 trainer_alloc=mcRBMTrainer.alloc_for_P,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
505 dataset='MAR'
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
506 )
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
507
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
508 if 0:
1286
8905186b176c test_mcRBM - added code to iterate over tinyimages
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1284
diff changeset
509 # pretraining settings
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
510 rbm,smplr = test_reproduce_ranzato_hinton_2010(
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
511 as_unittest=False,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
512 n_train_iters=60000,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
513 rbm_alloc=lambda n_I : mcRBM_withP.alloc_topo_P(n_I, n_J=81),
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
514 trainer_alloc=mcRBMTrainer.alloc_for_P,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
515 lr_per_example=0.05,
1286
8905186b176c test_mcRBM - added code to iterate over tinyimages
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1284
diff changeset
516 dataset='tinyimages_patches',
1284
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
517 l1_penalty=1e-3,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
518 l1_penalty_start=30000,
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
519 #l1_penalty_start=350, #DEBUG
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
520 persistent_chains=False
1817485d586d mcRBM - many changes incl. adding support for pooling matrix
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1273
diff changeset
521 )
1323
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
522
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
523 if 1:
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
524 def checkpoint():
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
525 return checkpoint
d6726417cf57 adding training script for test_mcRBM to reproduce classification results
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1286
diff changeset
526 run_classif_experiment(checkpoint=checkpoint)
1332
837768915081 added test idea to test_mcRBM
James Bergstra <bergstrj@iro.umontreal.ca>
parents: 1323
diff changeset
527