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)
# try: use sub images
# cifar = datasets.SubImageSet(cifar, [28,28], 1)
# cifar_test = datasets.CenterRegionSet(cifar_test, [28,28])
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": 1600, "max_iter": 100})
), # does encoding
pipeline.SpatialPooler({"grid": (4, 4), "method": "max"}), # average pool
]
)
logging.info("Training the pipeline...")
conv.train(cifar, 400000)
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()
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, 0.005)
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 testFeatureMeanStd(self):
mat = np.random.rand(100,50)
m_test, std_test = classifier.feature_meanstd(mat)
# use the naive approach to compute the mean and std
mats = mpi.COMM.gather(mat)
if mpi.is_root():
mats = np.vstack(mats)
m = mats.mean(0)
std = mats.std(0)
else:
m = None
std = None
m = mpi.COMM.bcast(m)
std = mpi.COMM.bcast(std)
np.testing.assert_array_almost_equal(m, m_test)
np.testing.assert_array_almost_equal(std, std_test)
def bird_demo():
logging.info('Loading data...')
bird = visiondata.CUBDataset(FLAGS.root, is_training=True, crop=FLAGS.crop,
version=FLAGS.version, prefetch=True,
target_size = TARGET_SIZE)
bird_test = visiondata.CUBDataset(FLAGS.root, is_training=False, crop=FLAGS.crop,
version=FLAGS.version, prefetch=True,
target_size = TARGET_SIZE)
if FLAGS.mirrored:
bird = datasets.MirrorSet(bird)
conv = pipeline.ConvLayer([
pipeline.PatchExtractor([FLAGS.patch, FLAGS.patch], 1), # extracts patches
pipeline.MeanvarNormalizer({'reg': 10}), # normalizes the patches
pipeline.LinearEncoder({},
trainer = pipeline.ZcaTrainer({'reg': 0.1})),
pipeline.ThresholdEncoder({'alpha': 0.25, 'twoside': True},
trainer = pipeline.OMPTrainer(
{'k': FLAGS.k, 'max_iter':100})),
pipeline.SpatialPooler({'grid': 4, 'method': 'max'})
],
fixed_size = True)
logging.info('Training the pipeline...')
conv.train(bird, 400000, exhaustive = True)
logging.info('Extracting features...')
Xtrain = conv.process_dataset(bird, as_2d = True)
Ytrain = bird.labels().astype(np.int)
Xtest = conv.process_dataset(bird_test, as_2d = True)
Ytest = bird_test.labels().astype(np.int)
# normalization
m, std = classifier.feature_meanstd(Xtrain, reg = 0.01)
# to match Adam Coates' pipeline
Xtrain -= m
Xtrain /= std
Xtest -= m
Xtest /= std
w, b = classifier.l2svm_onevsall(Xtrain, Ytrain, 0.005,
fminargs={'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)
mpi.root_pickle((m, std, w, b, conv[-2].dictionary), 'debug_features.pickle')
def stl_demo():
"""Performs a demo classification on stl
"""
logging.info('Loading stl data...')
stl = visiondata.STL10Dataset(FLAGS.root, 'unlabeled', target_size=32)
stl_train = visiondata.STL10Dataset(FLAGS.root, 'train', target_size=32)
stl_test = visiondata.STL10Dataset(FLAGS.root, 'test', target_size=32)
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(stl, 400000, exhaustive = True)
logging.info('Extracting features...')
X = conv.process_dataset(stl, as_2d = False)
Xtrain = conv.process_dataset(stl_train, as_2d = False)
Ytrain = stl_train.labels().astype(np.int)
Xtest = conv.process_dataset(stl_test, as_2d = False)
Ytest = stl_test.labels().astype(np.int)
# before we do feature computation, try to do dimensionality reduction
X.resize(np.prod(X.shape[:-1]), X.shape[-1])
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(X, 0.01)
X -= m
X /= std
Xtrain -= m
Xtrain /= std
Xtest -= m
Xtest /= std
covmat = mathutil.mpi_cov(X)
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(X, current_dim, tol=current_dim * 0.01)
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
#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...')
conv.train(cifar, 400000, exhaustive = True)
"""
conv = pickle.load(open('cvpr_exemplar_centroids_conv.pickle'))
_, ap_result = pickle.load(open('cvpr_exemplar_centroids.pickle'))
logging.info('Extracting features...')
Xtrain = conv.process_dataset(cifar, as_2d = False)
# we simply use all the features to compute the covmat
Xtrain.resize(np.prod(Xtrain.shape[:-1]), Xtrain.shape[-1])
m, std = classifier.feature_meanstd(Xtrain, 0.01)
Xtrain -= m
Xtrain /= std
covmat = mathutil.mpi_cov(Xtrain)
# do subsampling
"""
ap_result = code_ap.code_af(Xtrain, todim)
"""
sel = ap_result[0]
sel = mpi.COMM.bcast(sel)
Cpred = covmat[sel]
Csel = Cpred[:,sel]
Crecon = np.dot(Cpred.T, np.dot(np.linalg.pinv(Csel), Cpred))
Crecon = (Crecon + Crecon.T) / 2
eigval = np.linalg.eigvals(covmat)
def Train(self,feat_list=None,type='logreg',gamma=0.0,domeanstd=True,special_bias=None,add_bias=True, weight=None, class_instance=None, method='sigmoid',factor=10.0,arch=[10],
cv_feats=None, cv_special_bias=None,cv_class_instance=None):
if feat_list==None:
feat_list=self.features
self.feat_list=feat_list
self._gamma=gamma
self._type=type
self._special_bias = special_bias
self._add_bias = add_bias
Xtrain_feats = np.ascontiguousarray(np.hstack((self._Xtrain[feat] for feat in feat_list)))
self.m, self.std = classifier.feature_meanstd(Xtrain_feats)
if domeanstd==False: #hacky, overwrite the things we computed
self.m[:] = 0
self.std[:] = 1
Xtrain_feats -= self.m
Xtrain_feats /= self.std
if special_bias != None:
Xtrain_feats = np.ascontiguousarray(np.hstack((Xtrain_feats, special_bias)))
#CV
if cv_feats!=None:
cv_feats = np.ascontiguousarray(np.hstack((cv_feats[feat] for feat in feat_list)))
cv_feats -= self.m
cv_feats /= self.std
if special_bias != None:
cv_feats = np.ascontiguousarray(np.hstack((cv_feats, cv_special_bias)))
'''Classifier stage'''
if type=='linsvm':
self.w, self.b = classifier.svm_onevsall(Xtrain_feats, self._Ytrain, self._gamma, weight = weight, special_bias=special_bias, add_bias=add_bias)
return (self.w,self.b)
elif type=='logreg':
self.w, self.b = l2logreg_onevsall(Xtrain_feats, self._Ytrain, self._gamma, weight = weight, special_bias=special_bias, add_bias=add_bias)
return (self.w,self.b)
elif type=='logreg_atwv':
self.w, self.b = Train_atwv(Xtrain_feats,class_instance=class_instance,weight=weight,special_bias=special_bias, add_bias=add_bias, method=method,
factor=factor, gamma=self._gamma, cv_class_instance=cv_class_instance, cv_feats=cv_feats)
elif type=='nn_atwv':
self._arch = arch
self._weights_nn = Train_atwv_nn(Xtrain_feats,class_instance=class_instance,weight=weight,special_bias=special_bias, add_bias=add_bias,
arch=self._arch, method=method, factor=factor, gamma=self._gamma, cv_class_instance=cv_class_instance, cv_feats=cv_feats)
#self._weights_nn = Train_atwv_nn(Xtrain_feats,class_instance=class_instance,weight=self._weights_nn,special_bias=special_bias, add_bias=add_bias,
# arch=self._arch, method=method, factor=factor*10.0)
elif type=='nn_debug':
if mpi.COMM.Get_size() > 1:
print 'Warning!!! Running NN training with MPI with more than one Node!'
#FIXME: Collect X and Y at root to avoid this
# prob = mpi.COMM.gather(prob)
# if mpi.is_root():
# np.vstack(prob)
# #Train
# mpi.COMM.Bcast(self._nn)
# mpi.distribute(prob)
DS = ClassificationDataSet( Xtrain_feats.shape[1], 1, nb_classes=2 )
#for i in range(Xtrain_feats.shape[0]):
# DS.addSample( Xtrain_feats[i,:], [self._Ytrain[i]] )
DS.setField('input', Xtrain_feats)
DS.setField('target', self._Ytrain[:,np.newaxis])
DS._convertToOneOfMany()
self._nn = buildNetwork(DS.indim, 10, DS.outdim, outclass=SoftmaxLayer, fast=True)
self._nn_trainer = BackpropTrainer( self._nn, dataset=DS, momentum=0.1, verbose=True, weightdecay=gamma, learningrate=0.01, lrdecay=1.0)
self._nn_trainer.trainOnDataset(DS,epochs=8)
self._nn_trainer = BackpropTrainer( self._nn, dataset=DS, momentum=0.1, verbose=True, weightdecay=gamma, learningrate=0.001, lrdecay=1.0)
self._nn_trainer.trainOnDataset(DS,epochs=8)
self._nn_trainer = BackpropTrainer( self._nn, dataset=DS, momentum=0.1, verbose=True, weightdecay=gamma, learningrate=0.0001, lrdecay=1.0)
self._nn_trainer.trainOnDataset(DS,epochs=5)
return self._nn
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)
def bird_demo():
logging.info('Loading data...')
bird = visiondata.CUBDataset(FLAGS.root,
is_training=True,
crop=FLAGS.crop,
version=FLAGS.version,
prefetch=True,
target_size=TARGET_SIZE)
bird_test = visiondata.CUBDataset(FLAGS.root,
is_training=False,
crop=FLAGS.crop,
version=FLAGS.version,
prefetch=True,
target_size=TARGET_SIZE)
if FLAGS.mirrored:
bird = datasets.MirrorSet(bird)
conv = pipeline.ConvLayer(
[
pipeline.PatchExtractor([FLAGS.patch, FLAGS.patch],
1), # extracts patches
pipeline.MeanvarNormalizer({'reg': 10}), # normalizes the patches
pipeline.LinearEncoder({},
trainer=pipeline.ZcaTrainer({'reg': 0.1})),
pipeline.ThresholdEncoder({
'alpha': 0.25,
'twoside': True
},
trainer=pipeline.OMPTrainer(
{
'k': FLAGS.k,
'max_iter': 100
})),
pipeline.SpatialPooler({
'grid': 4,
'method': 'max'
})
],
fixed_size=True)
logging.info('Training the pipeline...')
conv.train(bird, 400000, exhaustive=True)
logging.info('Extracting features...')
Xtrain = conv.process_dataset(bird, as_2d=True)
Ytrain = bird.labels().astype(np.int)
Xtest = conv.process_dataset(bird_test, as_2d=True)
Ytest = bird_test.labels().astype(np.int)
# normalization
m, std = classifier.feature_meanstd(Xtrain, reg=0.01)
# to match Adam Coates' pipeline
Xtrain -= m
Xtrain /= std
Xtest -= m
Xtest /= std
w, b = classifier.l2svm_onevsall(Xtrain,
Ytrain,
0.005,
fminargs={'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)
mpi.root_pickle((m, std, w, b, conv[-2].dictionary),
'debug_features.pickle')
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]
Xtrain_red = np.ascontiguousarray(Xtrain[:, sel])
Xtest_red = np.ascontiguousarray(Xtest[:, sel])
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
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 stl_demo():
"""Performs a demo classification on stl
"""
logging.info('Loading stl data...')
stl = visiondata.STL10Dataset(FLAGS.root, 'unlabeled', target_size=32)
stl_train = visiondata.STL10Dataset(FLAGS.root, 'train', target_size=32)
stl_test = visiondata.STL10Dataset(FLAGS.root, 'test', target_size=32)
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(stl, 400000, exhaustive=True)
logging.info('Extracting features...')
X = conv.process_dataset(stl, as_2d=False)
Xtrain = conv.process_dataset(stl_train, as_2d=False)
Ytrain = stl_train.labels().astype(np.int)
Xtest = conv.process_dataset(stl_test, as_2d=False)
Ytest = stl_test.labels().astype(np.int)
# before we do feature computation, try to do dimensionality reduction
X.resize(np.prod(X.shape[:-1]), X.shape[-1])
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(X, 0.01)
X -= m
X /= std
Xtrain -= m
Xtrain /= std
Xtest -= m
Xtest /= std
covmat = mathutil.mpi_cov(X)
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(X, current_dim, tol=current_dim * 0.01)
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
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)
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]
Xtrain_red = np.ascontiguousarray(Xtrain[:, sel])
Xtest_red = np.ascontiguousarray(Xtest[:, sel])
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
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': 100, '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('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()
logging.info('Extracting features...')
Xtrain = conv.process_dataset(cifar, as_2d = True)
Ytrain = cifar.labels().astype(np.int)
Xtest = conv.process_dataset(cifar_test, as_2d = True)
Ytest = cifar_test.labels().astype(np.int)
# normalization
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[:,-400:] * np.sqrt(eigval[-400:])
logging.info("Dump oriol")
mpi.root_pickle((eigval, eigvec), 'cifar_dump_oriol.pickle')
Xtrain = np.dot(Xtrain, U)
Xtest = np.dot(Xtest, U)
"""
w, b = classifier.l2svm_onevsall(Xtrain, Ytrain, 0.002,
fminargs={'maxfun': 4000})
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_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)
