def testCifar100(self):
if not os.path.exists(_CIFAR100_FOLDER):
print 'Cifar 100 data not found, skipped'
return
cifar = visiondata.CifarDataset(_CIFAR100_FOLDER, is_training=True)
self.assertEqual(cifar.size_total(), 50000)
self.assertGreater(cifar.size(), 0)
self.assertEqual(cifar.dim(), (32, 32, 3))
self.assertEqual(cifar.num_channels(), 3)
for i in range(cifar.size()):
self.assertEqual(cifar.image(i).shape, (32, 32, 3))
self.assertGreaterEqual(cifar.label(i), 0)
self.assertLess(cifar.label(i), 100)
cifar = visiondata.CifarDataset(_CIFAR100_FOLDER, is_training=False)
self.assertEqual(cifar.size_total(), 10000)
self.assertGreater(cifar.size(), 0)
self.assertEqual(cifar.dim(), (32, 32, 3))
self.assertEqual(cifar.num_channels(), 3)
for i in range(cifar.size()):
self.assertEqual(cifar.image(i).shape, (32, 32, 3))
self.assertGreaterEqual(cifar.label(i), 0)
self.assertLess(cifar.label(i), 100)
'''
import cPickle as pickle
import logging
from iceberk import mpi, visiondata, pipeline, classifier, datasets, mathutil
from iceberk.experimental import code_ap
import numpy as np
fromdim = 3200
todim = 256
mpi.root_log_level(logging.DEBUG)
data_root = '/u/vis/x1/common/CIFAR/cifar-10-batches-py/'
logging.info('Loading cifar data...')
cifar = visiondata.CifarDataset(data_root, is_training=True)
"""
conv = pipeline.ConvLayer([
pipeline.PatchExtractor([8,8], 1), # extracts patches
pipeline.MeanvarNormalizer({'reg': 10}), # normalizes the patches
pipeline.LinearEncoder({},
trainer = pipeline.ZcaTrainer({'reg': 0.1})),
pipeline.ThresholdEncoder({'alpha': 0.25, 'twoside': False},
trainer = pipeline.NormalizedKmeansTrainer(
{'k': fromdim, 'max_iter':100})),
#trainer = pipeline.OMPNTrainer(
# {'k': 3200, 'num_active': 10, 'max_iter':100})),
pipeline.SpatialPooler({'grid': (2,2), 'method': 'max'}) # average pool
])
logging.info('Training the pipeline...')
def cifar_demo():
"""Performs a demo classification on cifar
"""
mpi.mkdir(FLAGS.output_dir)
logging.info('Loading cifar data...')
cifar = visiondata.CifarDataset(FLAGS.root, is_training=True)
cifar_test = visiondata.CifarDataset(FLAGS.root, is_training=False)
if FLAGS.trainer == "pink":
trainer = pinker.SpatialPinkTrainer({
'size': (FLAGS.patch, FLAGS.patch),
'reg': 0.1
})
else:
trainer = pipeline.ZcaTrainer({'reg': 0.1})
conv = pipeline.ConvLayer([
pipeline.PatchExtractor([FLAGS.patch, FLAGS.patch],
1), # extracts patches
pipeline.MeanvarNormalizer({'reg': 10}), # normalizes the patches
pipeline.LinearEncoder({}, trainer=trainer),
pipeline.ThresholdEncoder({
'alpha': 0.0,
'twoside': False
},
trainer=pipeline.OMPTrainer({
'k': FLAGS.fromdim,
'max_iter': 100
})),
pipeline.SpatialPooler({
'grid': (FLAGS.grid, FLAGS.grid),
'method': FLAGS.method
}) # average pool
])
logging.info('Training the pipeline...')
conv.train(cifar, 400000, exhaustive=True)
logging.info('Extracting features...')
Xtrain = conv.process_dataset(cifar, as_2d=False)
Ytrain = cifar.labels().astype(np.int)
Xtest = conv.process_dataset(cifar_test, as_2d=False)
Ytest = cifar_test.labels().astype(np.int)
# before we do feature computation, try to do dimensionality reduction
Xtrain.resize(np.prod(Xtrain.shape[:-1]), Xtrain.shape[-1])
Xtest.resize(np.prod(Xtest.shape[:-1]), Xtest.shape[-1])
m, std = classifier.feature_meanstd(Xtrain, 0.01)
Xtrain -= m
Xtrain /= std
Xtest -= m
Xtest /= std
covmat = mathutil.mpi_cov(Xtrain)
if False:
# directly do dimensionality reduction
eigval, eigvec = np.linalg.eigh(covmat)
U = eigvec[:, -FLAGS.todim:]
Xtrain = np.dot(Xtrain, U)
Xtest = np.dot(Xtest, U)
else:
# do subsampling
import code_ap
temp = code_ap.code_af(Xtrain, FLAGS.todim)
sel = temp[0]
sel = mpi.COMM.bcast(sel)
Cpred = covmat[sel]
Csel = Cpred[:, sel]
W = np.linalg.solve(Csel, Cpred)
# perform svd
U, D, _ = np.linalg.svd(W, full_matrices=0)
U *= D
Xtrain = np.dot(Xtrain[:, sel], U)
Xtest = np.dot(Xtest[:, sel], U)
Xtrain.resize(Ytrain.shape[0], Xtrain.size / Ytrain.shape[0])
Xtest.resize(Ytest.shape[0], Xtest.size / Ytest.shape[0])
"""
# This part is used to do post-pooling over all features nystrom subsampling
# normalization
Xtrain.resize(Xtrain.shape[0], np.prod(Xtrain.shape[1:]))
Xtest.resize(Xtest.shape[0], np.prod(Xtest.shape[1:]))
m, std = classifier.feature_meanstd(Xtrain, reg = 0.01)
# to match Adam Coates' pipeline
Xtrain -= m
Xtrain /= std
Xtest -= m
Xtest /= std
covmat = mathutil.mpi_cov(Xtrain)
eigval, eigvec = np.linalg.eigh(covmat)
U = eigvec[:, -(200*FLAGS.grid*FLAGS.grid):]
#U = eigvec[:,-400:] * np.sqrt(eigval[-400:])
Xtrain = np.dot(Xtrain, U)
Xtest = np.dot(Xtest, U)
"""
w, b = classifier.l2svm_onevsall(Xtrain,
Ytrain,
0.002,
fminargs={
'disp': 0,
'maxfun': 1000
})
accu_train = classifier.Evaluator.accuracy(Ytrain, np.dot(Xtrain, w) + b)
accu_test = classifier.Evaluator.accuracy(Ytest, np.dot(Xtest, w) + b)
logging.info('Training accuracy: %f' % accu_train)
logging.info('Testing accuracy: %f' % accu_test)
import cPickle as pickle
import logging
from iceberk import visiondata, pipeline, mpi, classifier, mathutil
import numpy as np
import os
from jiayq.experiments.feature_selection import pcfs
if mpi.is_root():
logging.getLogger().setLevel(logging.DEBUG)
logging.info('Loading cifar data...')
cifar = visiondata.CifarDataset('/u/vis/x1/common/CIFAR/cifar-10-batches-py', \
is_training=True)
cifar_test = visiondata.CifarDataset(
'/u/vis/x1/common/CIFAR/cifar-10-batches-py', \
is_training=False)
try:
conv = pickle.load(open('cifar_conv.pickle'))
logging.info('Skipping first layer training')
except Exception, e:
conv = pipeline.ConvLayer([
pipeline.PatchExtractor([6, 6], 1), # extracts patches
pipeline.MeanvarNormalizer({'reg': 10}), # normalizes the patches
pipeline.LinearEncoder({}, trainer=pipeline.ZcaTrainer(
{'reg': 0.1})), # Does whitening
pipeline.ThresholdEncoder({
'alpha': 0.0,
'twoside': False
},
def cifar_demo():
"""Performs a demo classification on cifar
"""
mpi.mkdir(FLAGS.output_dir)
logging.info('Loading cifar data...')
cifar = visiondata.CifarDataset(FLAGS.root, is_training=True)
cifar_test = visiondata.CifarDataset(FLAGS.root, is_training=False)
conv = pipeline.ConvLayer([
pipeline.PatchExtractor([6, 6], 1), # extracts patches
pipeline.MeanvarNormalizer({'reg': 10}), # normalizes the patches
pipeline.LinearEncoder({}, trainer=pipeline.ZcaTrainer(
{'reg': 0.1})), # Does whitening
pipeline.ThresholdEncoder({
'alpha': 0.25,
'twoside': True
},
trainer=pipeline.OMPTrainer({
'k': 800,
'max_iter': 100
})), # does encoding
pipeline.SpatialPooler({
'grid': (2, 2),
'method': 'ave'
}) # average pool
])
logging.info('Training the pipeline...')
conv.train(cifar, 50000)
logging.info('Dumping the pipeline...')
if mpi.is_root():
with open(os.path.join(FLAGS.output_dir, FLAGS.model_file),
'w') as fid:
pickle.dump(conv, fid)
fid.close()
with open(os.path.join(FLAGS.output_dir, FLAGS.model_file), 'r') as fid:
conv = pickle.load(fid)
logging.info('Extracting features...')
Xtrain = conv.process_dataset(cifar, as_2d=True)
mpi.dump_matrix_multi(
Xtrain, os.path.join(FLAGS.output_dir, FLAGS.feature_file + '_train'))
Ytrain = cifar.labels().astype(np.int)
Xtest = conv.process_dataset(cifar_test, as_2d=True)
mpi.dump_matrix_multi(
Xtest, os.path.join(FLAGS.output_dir, FLAGS.feature_file + '_test'))
Ytest = cifar_test.labels().astype(np.int)
# normalization
m, std = classifier.feature_meanstd(Xtrain)
Xtrain -= m
Xtrain /= std
Xtest -= m
Xtest /= std
w, b = classifier.l2svm_onevsall(Xtrain, Ytrain, 0.01)
if mpi.is_root():
with open(os.path.join(FLAGS.output_dir, FLAGS.svm_file), 'w') as fid:
pickle.dump({'m': m, 'std': std, 'w': w, 'b': b}, fid)
accu = np.sum(Ytrain == (np.dot(Xtrain,w)+b).argmax(axis=1)) \
/ float(len(Ytrain))
accu_test = np.sum(Ytest == (np.dot(Xtest,w)+b).argmax(axis=1)) \
/ float(len(Ytest))
logging.info('Training accuracy: %f' % accu)
logging.info('Testing accuracy: %f' % accu_test)
def cifar_demo():
"""Performs a demo classification on cifar
"""
mpi.mkdir(FLAGS.output_dir)
logging.info('Loading cifar data...')
cifar = visiondata.CifarDataset(FLAGS.root, is_training=True)
cifar_test = visiondata.CifarDataset(FLAGS.root, is_training=False)
conv = pipeline.ConvLayer([
pipeline.PatchExtractor([6, 6], 1), # extracts patches
pipeline.MeanvarNormalizer({'reg': 10}), # normalizes the patches
pipeline.LinearEncoder({}, trainer=pipeline.ZcaTrainer({'reg': 0.1})),
pipeline.ThresholdEncoder({
'alpha': 0.25,
'twoside': False
},
trainer=pipeline.NormalizedKmeansTrainer({
'k':
FLAGS.fromdim,
'max_iter':
100
})),
pipeline.SpatialPooler({
'grid': (FLAGS.grid, FLAGS.grid),
'method': FLAGS.method
}) # average pool
])
logging.info('Training the pipeline...')
conv.train(cifar, 400000, exhaustive=True)
logging.info('Extracting features...')
Xtrain = conv.process_dataset(cifar, as_2d=False)
Ytrain = cifar.labels().astype(np.int)
Xtest = conv.process_dataset(cifar_test, as_2d=False)
Ytest = cifar_test.labels().astype(np.int)
# before we do feature computation, try to do dimensionality reduction
Xtrain.resize(np.prod(Xtrain.shape[:-1]), Xtrain.shape[-1])
Xtest.resize(np.prod(Xtest.shape[:-1]), Xtest.shape[-1])
m, std = classifier.feature_meanstd(Xtrain, 0.01)
Xtrain -= m
Xtrain /= std
Xtest -= m
Xtest /= std
covmat = mathutil.mpi_cov(Xtrain)
current_dim = FLAGS.fromdim
if FLAGS.svd == 1:
eigval, eigvec = np.linalg.eigh(covmat)
while current_dim >= 100:
if current_dim < FLAGS.fromdim:
if FLAGS.svd == 1:
# directly do dimensionality reduction
U = eigvec[:, -current_dim:]
Xtrain_red = np.dot(Xtrain, U)
Xtest_red = np.dot(Xtest, U)
else:
# do subsampling
temp = code_ap.code_af(Xtrain, current_dim)
logging.info("selected %d dims" % len(temp[0]))
sel = temp[0]
sel = mpi.COMM.bcast(sel)
Cpred = covmat[sel]
Csel = Cpred[:, sel]
W = np.linalg.solve(Csel, Cpred)
# perform svd
U, D, _ = np.linalg.svd(W, full_matrices=0)
U *= D
Xtrain_red = np.dot(Xtrain[:, sel], U)
Xtest_red = np.dot(Xtest[:, sel], U)
Xtrain_red.resize(Ytrain.shape[0],
Xtrain_red.size / Ytrain.shape[0])
Xtest_red.resize(Ytest.shape[0], Xtest_red.size / Ytest.shape[0])
else:
Xtrain_red = Xtrain.copy()
Xtest_red = Xtest.copy()
Xtrain_red.resize(Ytrain.shape[0],
Xtrain_red.size / Ytrain.shape[0])
Xtest_red.resize(Ytest.shape[0], Xtest_red.size / Ytest.shape[0])
w, b = classifier.l2svm_onevsall(Xtrain_red,
Ytrain,
0.005,
fminargs={
'disp': 0,
'maxfun': 1000
})
accu_train = classifier.Evaluator.accuracy(Ytrain,
np.dot(Xtrain_red, w) + b)
accu_test = classifier.Evaluator.accuracy(Ytest,
np.dot(Xtest_red, w) + b)
logging.info('%d - %d, Training accuracy: %f' %
(FLAGS.fromdim, current_dim, accu_train))
logging.info('%d - %d, Testing accuracy: %f' %
(FLAGS.fromdim, current_dim, accu_test))
current_dim /= 2
