def compute_caltech_features():
caltech = datasets.TwoLayerDataset(FLAGS.root, ['jpg'], max_size=300)
conv = pipeline.ConvLayer([
dsift.DsiftExtractor(FLAGS.sift_size, FLAGS.sift_stride),
pipeline.LLCEncoder({'k': FLAGS.llc_k},
trainer=pipeline.KmeansTrainer(
{'k': FLAGS.dict_size})),
pipeline.PyramidPooler({
'level': 3,
'method': 'max'
})
])
conv.train(caltech, 400000)
feat = conv.process_dataset(caltech, as_2d=True)
mpi.mkdir(FLAGS.feature_dir)
if mpi.is_root():
with (open(os.path.join(FLAGS.feature_dir, FLAGS.model_file),
'w')) as fid:
pickle.dump(conv, fid)
mpi.dump_matrix_multi(feat,
os.path.join(FLAGS.feature_dir, FLAGS.feature_file))
mpi.dump_matrix_multi(caltech.labels(),
os.path.join(FLAGS.feature_dir, FLAGS.label_file))
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 compute_caltech_features():
caltech = datasets.TwoLayerDataset(FLAGS.root, ["jpg"], max_size=300)
conv = pipeline.ConvLayer(
[
dsift.DsiftExtractor(FLAGS.sift_size, FLAGS.sift_stride),
pipeline.LLCEncoder({"k": FLAGS.llc_k}, trainer=pipeline.KmeansTrainer({"k": FLAGS.dict_size})),
pipeline.PyramidPooler({"level": 3, "method": "max"}),
]
)
conv.train(caltech, 400000)
feat = conv.process_dataset(caltech, as_2d=True)
mpi.mkdir(FLAGS.feature_dir)
if mpi.is_root():
with (open(os.path.join(FLAGS.feature_dir, FLAGS.model_file), "w")) as fid:
pickle.dump(conv, fid)
mpi.dump_matrix_multi(feat, os.path.join(FLAGS.feature_dir, FLAGS.feature_file))
mpi.dump_matrix_multi(caltech.labels(), os.path.join(FLAGS.feature_dir, FLAGS.label_file))
trainer = pipeline.ZcaTrainer({'reg': 0.1})),
#pipeline.SpatialMeanNormalizer({'channels': 3}),
pipeline.ThresholdEncoder({'alpha': 0.25, 'twoside': False},
trainer = pipeline.OMPTrainer(
{'k': 3200, 'max_iter':100})),
pipeline.KernelPooler(\
{'kernel': pipeline.KernelPooler.kernel_uniform(15),
'method': 'max',
'stride': 1})
],
fixed_size = True)
conv.train(regions_data, 400000)
mpi.root_pickle(conv, "conv.pickle")
# so let's get the regions' features after pooling.
regions_pooled = conv.process_dataset(regions_data)
mpi.dump_matrix_multi(regions_pooled,
'/tscratch/tmp/jiayq/pooled_lda/regions_pooled')
logging.info("Feature shape:" + str(regions_pooled.shape[1:]))
std = mathutil.mpi_std(regions_pooled.reshape(regions_pooled.shape[0], \
np.prod(regions_pooled.shape[1:])))
# compute the std mean
std.resize(np.prod(regions_pooled.shape[1:-1]), regions_pooled.shape[-1])
std = std.mean(axis=0)
std_order = np.argsort(std)
# now, compute the within-class std
regions_pooled_view = regions_pooled.reshape(regions_pooled.shape[0],
np.prod(regions_pooled.shape[1:-1]), regions_pooled.shape[-1])
within_std_local = regions_pooled_view.var(axis=1)
print within_std_local.shape
within_std = np.sqrt(mathutil.mpi_mean(within_std_local))
test_data = visiondata.CUBDataset(ROOT, False, crop = CROP,
target_size = TARGET_SIZE, prefetch = True)
if MIRRORED:
train_data = datasets.MirrorSet(train_data)
CONV.train(train_data, 400000, exhaustive = True)
mpi.root_pickle(CONV, __file__ + ".conv.pickle")
Xtrain = CONV.process_dataset(train_data, as_2d = True)
Xtest = CONV.process_dataset(test_data, as_2d = True)
Ytrain = train_data.labels()
Ytest = test_data.labels()
m, std = classifier.feature_meanstd(Xtrain)
Xtrain -= m
Xtrain /= std
Xtest -= m
Xtest /= std
mpi.dump_matrix_multi(Xtrain, os.path.join(FEATDIR,'Xtrain'))
mpi.dump_matrix_multi(Xtest, os.path.join(FEATDIR,'Xtest'))
mpi.dump_matrix_multi(Ytrain, os.path.join(FEATDIR,'Ytrain'))
mpi.dump_matrix_multi(Ytest, os.path.join(FEATDIR,'Ytest'))
else:
Xtrain = mpi.load_matrix_multi(os.path.join(FEATDIR,'Xtrain'))
Xtest = mpi.load_matrix_multi(os.path.join(FEATDIR,'Xtest'))
Ytrain = mpi.load_matrix_multi(os.path.join(FEATDIR,'Ytrain'))
Ytest = mpi.load_matrix_multi(os.path.join(FEATDIR,'Ytest'))
if FLAGS.flat:
logging.info("Performing flat classification")
solver = classifier.SolverMC(FLAGS.reg,
classifier.Loss.loss_multiclass_logistic,
classifier.Reg.reg_l2,
fminargs = {'maxfun': 1000})
trainer = pipeline.NormalizedKmeansTrainer(
{'k': 1600, 'max_iter':100})), # does encoding
pipeline.SpatialPooler({'grid': (2,2), 'method': 'ave'})
])
logging.info('Training the pipeline...')
conv.train(cifar, 400000, exhaustive=True)
mpi.root_pickle(conv, 'cifar_conv.pickle')
# do pruning
try:
selected_idx = pickle.load(open('cifar_selected_idx.pickle'))
logging.info('Skipping first layer pruning')
except Exception, e:
features = conv.sample(cifar, 200000, True)
mpi.dump_matrix_multi(features, '/u/vis/ttmp/jiayq/cifar/cifar_feature_pooled_sample')
m, std = mathutil.mpi_meanstd(features)
features -= m
features /= std
covmat = mathutil.mpi_cov(features, reg = 0.01)
if mpi.is_root():
selected_idx = pcfs.max_variance_feature_selection(covmat, 800)
else:
selected_idx = None
selected_idx = mpi.COMM.bcast(selected_idx)
mpi.root_pickle((m, std, covmat), 'cifar_squared_correlation.pickle')
mpi.root_pickle(selected_idx, 'cifar_selected_idx.pickle')
dictionary_all = conv[-2].dictionary
for i in [25,50,100,200,400,800,1600]:
train_data = visiondata.CUBDataset(ROOT, True, crop=CROP, target_size=TARGET_SIZE, prefetch=True)
test_data = visiondata.CUBDataset(ROOT, False, crop=CROP, target_size=TARGET_SIZE, prefetch=True)
if MIRRORED:
train_data = datasets.MirrorSet(train_data)
CONV.train(train_data, 400000, exhaustive=True)
mpi.root_pickle(CONV, __file__ + ".conv.pickle")
Xtrain = CONV.process_dataset(train_data, as_2d=True)
Xtest = CONV.process_dataset(test_data, as_2d=True)
Ytrain = train_data.labels()
Ytest = test_data.labels()
m, std = classifier.feature_meanstd(Xtrain)
Xtrain -= m
Xtrain /= std
Xtest -= m
Xtest /= std
mpi.dump_matrix_multi(Xtrain, os.path.join(FEATDIR, "Xtrain"))
mpi.dump_matrix_multi(Xtest, os.path.join(FEATDIR, "Xtest"))
mpi.dump_matrix_multi(Ytrain, os.path.join(FEATDIR, "Ytrain"))
mpi.dump_matrix_multi(Ytest, os.path.join(FEATDIR, "Ytest"))
else:
Xtrain = mpi.load_matrix_multi(os.path.join(FEATDIR, "Xtrain"))
Xtest = mpi.load_matrix_multi(os.path.join(FEATDIR, "Xtest"))
Ytrain = mpi.load_matrix_multi(os.path.join(FEATDIR, "Ytrain"))
Ytest = mpi.load_matrix_multi(os.path.join(FEATDIR, "Ytest"))
if FLAGS.flat:
logging.info("Performing flat classification")
solver = classifier.SolverMC(
FLAGS.reg, classifier.Loss.loss_multiclass_logistic, classifier.Reg.reg_l2, fminargs={"maxfun": 1000}
)
w, b = solver.solve(Xtrain, classifier.to_one_of_k_coding(Ytrain, fill=0))
'grid': (2, 2),
'method': 'ave'
})
])
logging.info('Training the pipeline...')
conv.train(cifar, 400000, exhaustive=True)
mpi.root_pickle(conv, 'cifar_conv.pickle')
# do pruning
try:
selected_idx = pickle.load(open('cifar_selected_idx.pickle'))
logging.info('Skipping first layer pruning')
except Exception, e:
features = conv.sample(cifar, 200000, True)
mpi.dump_matrix_multi(
features, '/u/vis/ttmp/jiayq/cifar/cifar_feature_pooled_sample')
m, std = mathutil.mpi_meanstd(features)
features -= m
features /= std
covmat = mathutil.mpi_cov(features, reg=0.01)
if mpi.is_root():
selected_idx = pcfs.max_variance_feature_selection(covmat, 800)
else:
selected_idx = None
selected_idx = mpi.COMM.bcast(selected_idx)
mpi.root_pickle((m, std, covmat), 'cifar_squared_correlation.pickle')
mpi.root_pickle(selected_idx, 'cifar_selected_idx.pickle')
dictionary_all = conv[-2].dictionary
for i in [25, 50, 100, 200, 400, 800, 1600]:
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)
trainer = pipeline.ZcaTrainer({'reg': 0.1})),
#pipeline.SpatialMeanNormalizer({'channels': 3}),
pipeline.ThresholdEncoder({'alpha': 0.25, 'twoside': False},
trainer = pipeline.OMPTrainer(
{'k': 3200, 'max_iter':100})),
pipeline.KernelPooler(\
{'kernel': pipeline.KernelPooler.kernel_uniform(15),
'method': 'max',
'stride': 1})
],
fixed_size = True)
conv.train(regions_data, 400000)
mpi.root_pickle(conv, "conv.pickle")
# so let's get the regions' features after pooling.
regions_pooled = conv.process_dataset(regions_data)
mpi.dump_matrix_multi(regions_pooled,
'/tscratch/tmp/jiayq/pooled_lda/regions_pooled')
logging.info("Feature shape:" + str(regions_pooled.shape[1:]))
std = mathutil.mpi_std(regions_pooled.reshape(regions_pooled.shape[0], \
np.prod(regions_pooled.shape[1:])))
# compute the std mean
std.resize(np.prod(regions_pooled.shape[1:-1]), regions_pooled.shape[-1])
std = std.mean(axis=0)
std_order = np.argsort(std)
# now, compute the within-class std
regions_pooled_view = regions_pooled.reshape(
regions_pooled.shape[0], np.prod(regions_pooled.shape[1:-1]),
regions_pooled.shape[-1])
within_std_local = regions_pooled_view.var(axis=1)
print within_std_local.shape