data_std = train_features_numpy.std()
train_features_numpy /= data_std
train_features_numpy = train_features_numpy[numpy.random.permutation(numtrain)]
train_features_theano = theano.shared(train_features_numpy)
test_features -= data_mean
test_features /= data_std
test_feature_beginnings = test_features[:,:frame_len*3]
print '... done'
print 'pretraining velocity model ...'
pretrainmodel_velocity = gatedAutoencoder.FactoredGatedAutoencoder(
numvisX=frame_len,
numvisY=frame_len,
numfac=200,
nummap=100,
output_type='real',
corruption_type='zeromask',
corruption_level=0.3,
numpy_rng=numpy_rng,
theano_rng=theano_rng)
pretrain_features_velocity_numpy = numpy.concatenate([train_features_numpy[i, 2*j*frame_len:2*(j+1)*frame_len][None,:] for j in range(seq_len/(frame_len*2)) for i in range(numtrain)],0)
pretrain_features_velocity_numpy = pretrain_features_velocity_numpy[numpy.random.permutation(pretrain_features_velocity_numpy.shape[0])]
pretrain_features_velocity_theano = theano.shared(pretrain_features_velocity_numpy)
pretrainer_velocity = GraddescentMinibatch(pretrainmodel_velocity, pretrain_features_velocity_theano, batchsize=100, learningrate=0.01)
for epoch in xrange(10):
pretrainer_velocity.step()
print '... done'
batchsize = 100
numvisX = train_features_x.shape[1]
numvisY = train_features_y.shape[1]
numbatches = train_features.get_value().shape[0] / batchsize
# INSTANTIATE MODEL
print '... instantiating model'
numpy_rng = numpy.random.RandomState(1)
theano_rng = RandomStreams(1)
model = gatedAutoencoder.FactoredGatedAutoencoder(numvisX=numvisX,
numvisY=numvisY,
numfac=numfac, nummap=nummap, numhid=numhid,
output_type='real',
weight_decay_vis=weight_decay_vis,
weight_decay_map=weight_decay_map,
corruption_type=corruption_type,
corruption_level=corruption_level,
init_topology = init_topology,
numpy_rng=numpy_rng,
theano_rng=theano_rng)
print '... done'
# TRAIN MODEL
numepochs = 100
learningrate = 0.01
#trainer = gatedAutoencoder.GraddescentMinibatch(model, train_features, batchsize, learningrate)
trainer = GraddescentMinibatch(model, train_features, batchsize, learningrate)
def main(args):
ifile = args.input
ofile = args.output
numfac = args.numfac
nummap = args.nummap
numepochs = args.numepochs
doNorm = args.donorm
verbose = args.verbose
learningrate = args.learnrate
print '... loading data'
mat = scipy.io.loadmat(ifile)
train_features_x = numpy.float64(mat['x'])
train_features_y = numpy.float64(mat['y'])
#NORMALIZE DATA:
if doNorm == 1:
eps = 0
train_features_x -= train_features_x.mean(0)[None, :]
train_features_y -= train_features_y.mean(0)[None, :]
train_features_x /= train_features_x.std(0)[None, :] + train_features_x.std() * 0.1 + eps
train_features_y /= train_features_y.std(0)[None, :] + train_features_y.std() * 0.1 + eps
#scipy.io.savemat('train_features_norm.mat',{'nx':train_features_x,'ny':train_features_y},oned_as='column')
#SHUFFLE TRAINING DATA TO MAKE SURE ITS NOT SORTED:
R = numpy.random.permutation(train_features_x.shape[0])
train_features_x = train_features_x[R, :]
train_features_y = train_features_y[R, :]
print train_features_x.shape
print train_features_y.shape
train_features_numpy = numpy.concatenate((train_features_x, train_features_y), 1)
train_features = T.cast(theano.shared(train_features_numpy),'float64')
print train_features.type
print '... done'
#numfac = 600
#nummap = 400
numhid = 0
weight_decay_vis = 0.0
weight_decay_map = 0.0
corruption_type = 'zeromask'
corruption_level = 0.5
init_topology = None
batchsize = 100
numvisX = train_features_x.shape[1]
numvisY = train_features_y.shape[1]
numbatches = train_features.get_value().shape[0] / batchsize
# INSTANTIATE MODEL
print '... instantiating model'
numpy_rng = numpy.random.RandomState(1)
theano_rng = RandomStreams(1)
model = gatedAutoencoder.FactoredGatedAutoencoder(numvisX=numvisX,
numvisY=numvisY,
numfac=numfac, nummap=nummap, numhid=numhid,
output_type='real',
weight_decay_vis=weight_decay_vis,
weight_decay_map=weight_decay_map,
corruption_type=corruption_type,
corruption_level=corruption_level,
init_topology = init_topology,
numpy_rng=numpy_rng,
theano_rng=theano_rng)
print '... done'
# TRAIN MODEL
#numepochs = 100
#learningrate = 0.01
#trainer = gatedAutoencoder.GraddescentMinibatch(model, train_features, batchsize, learningrate)
trainer = GraddescentMinibatch(model, train_features, batchsize, learningrate, 0.9, None, verbose)
for epoch in xrange(numepochs):
trainer.step()
scipy.io.savemat(ofile, {'wxf':model.layer.wxf.get_value(), 'wyf':model.layer.wyf.get_value(), 'whf':model.layer.whf_in.get_value(), 'z_bias':model.layer.bmap.get_value()},oned_as='column')