def feature_meanstd(mat, reg = None):
'''
Utility function that does distributed mean and std computation
Input:
mat: the local data matrix, each row is a feature vector and each
column is a feature dim
reg: if reg is not None, the returned std is computed as
std = np.sqrt(std**2 + reg)
Output:
m: the mean for each dimension
std: the standard deviation for each dimension
The implementation is actually moved to iceberk.mathutil now, we leave the
code here just for backward compatibility
'''
m, std = mathutil.mpi_meanstd(mat)
if reg is not None:
std = np.sqrt(std**2 + reg)
return m, std
{'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]:
logging.info('Training with dictionary size %d' % i)
})
])
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]:
logging.info('Training with dictionary size %d' % i)
