def test_convsparsenet(lam_sparse=.1,N=16,perc_var=100.):
from hdl.models import SparseSlowModel
from hdl.learners import SGD
whitenpatches = 1000
#model = ConvWhitenInputModel(imshp=(10,1,32,32),convwhitenfiltershp=(7,7),perc_var=100.)
model = ConvSparseSlowModel(imshp=(10,1,28,28),convwhitenfiltershp=(7,7),N=N,kshp=(7,7),perc_var=perc_var,lam_sparse=lam_sparse)
l = SGD(model=model,datasource='vid075-chunks',display_every=1000,save_every=10000,batchsize=model.imshp[0])
print 'whitenpatches', whitenpatches
print 'model.imshp', model.imshp
print 'model.convwhitenfiltershp', model.convwhitenfiltershp
databatch = l.get_databatch(whitenpatches)
l.model.learn_whitening(databatch)
l.model.setup()
l.learn(iterations=20000)
l.change_target(.5)
l.learn(iterations=5000)
l.change_target(.5)
l.learn(iterations=5000)
#l.learn(iterations=160000)
#l.change_target(.5)
#l.learn(iterations=20000)
#l.change_target(.5)
#l.learn(iterations=20000)
from hdl.display import display_final
display_final(l.model)
def test_convsparsenet_subspace(lam_sparse=1.,lam_slow=1.,N=8,perc_var=100.,stride=(1,1)):
from hdl.models import ConvSparseSlowModel
from hdl.learners import SGD
whitenpatches = 1000
psz = 48
ksz = 16
convwhitenfiltershp=(15,15)
#model = ConvWhitenInputModel(imshp=(10,1,32,32),convwhitenfiltershp=(7,7),perc_var=100.)
model = ConvSparseSlowModel(imshp=(4,1,psz,psz),convwhitenfiltershp=convwhitenfiltershp,N=N,kshp=(ksz,ksz),stride=stride,
sparse_cost='subspacel1',
perc_var=perc_var,
lam_sparse=lam_sparse,
lam_slow=lam_slow,
mask=True,
force_subspace_orthogonal=True)
l = SGD(model=model,datasource='vid075-chunks',display_every=50,save_every=10000,
eta_target_maxupdate=0.5,
batchsize=model.imshp[0])
print 'whitenpatches', whitenpatches
print 'model.imshp', model.imshp
print 'model.convwhitenfiltershp', model.convwhitenfiltershp
databatch = l.get_databatch(whitenpatches)
l.model.learn_whitening(databatch)
l.model.setup()
l.learn(iterations=1000)
l.model.center_basis_functions=False
l.learn(iterations=9000)
l.change_target(.5)
l.learn(iterations=5000)
l.change_target(.5)
l.learn(iterations=5000)
#l.learn(iterations=160000)
#l.change_target(.5)
#l.learn(iterations=20000)
#l.change_target(.5)
#l.learn(iterations=20000)
from hdl.display import display_final
display_final(l.model)
def test_convsparsenet(lam_sparse=.1,N=16,perc_var=100.,stride=1,kshp=(7,7),batchsize=4):
from hdl.learners import SGD
whitenpatches = 1000
if isinstance(kshp,int): kshp = (kshp,kshp)
if isinstance(stride,int): stride = (stride,stride)
imszr = 5*stride[0] + kshp[0] - 1
imszc = 5*stride[1] + kshp[1] - 1
#model = ConvWhitenInputModel(imshp=(10,1,32,32),convwhitenfiltershp=(7,7),perc_var=100.)
model = ConvSparseSlowModel(imshp=(batchsize,1,imszr,imszc),convwhitenfiltershp=(7,7),N=N,kshp=kshp,stride=stride,
perc_var=perc_var,lam_sparse=lam_sparse)
l = SGD(model=model,datasource='vid075-chunks',display_every=50,save_every=10000,batchsize=model.imshp[0])
print 'whitenpatches', whitenpatches
print 'model.imshp', model.imshp
print 'model.convwhitenfiltershp', model.convwhitenfiltershp
databatch = l.get_databatch(whitenpatches)
l.model.learn_whitening(databatch)
l.model.setup()
l.learn(iterations=5000)
l.model.center_basis_functions = False
l.learn(iterations=15000)
l.change_target(.5)
l.learn(iterations=5000)
l.change_target(.5)
l.learn(iterations=5000)
#l.learn(iterations=160000)
#l.change_target(.5)
#l.learn(iterations=20000)
#l.change_target(.5)
#l.learn(iterations=20000)
from hdl.display import display_final
display_final(l.model)
def test_sparsenet_subspace(lam_sparse=1.,lam_slow=1.,N=8,perc_var=100.):
from hdl.models import SparseSlowModel
from hdl.learners import SGD
whitenpatches = 10000
psz = 16
#model = ConvWhitenInputModel(imshp=(10,1,32,32),convwhitenfiltershp=(7,7),perc_var=100.)
model = SparseSlowModel(patch_sz=psz,N=N,
sparse_cost='subspacel1',
perc_var=perc_var,
lam_sparse=lam_sparse,
lam_slow=lam_slow,T=48)
l = SGD(model=model,datasource='vid075-chunks',display_every=100,save_every=10000,batchsize=model.T)
print 'whitenpatches', whitenpatches
databatch = l.get_databatch(whitenpatches)
l.model.learn_whitening(databatch)
l.model.setup()
l.learn(iterations=5000)
l.change_target(.5)
l.learn(iterations=5000)
l.change_target(.5)
l.learn(iterations=5000)
#l.learn(iterations=160000)
#l.change_target(.5)
#l.learn(iterations=20000)
#l.change_target(.5)
#l.learn(iterations=20000)
from hdl.display import display_final
display_final(l.model)
whitenpatches = 200
patch_sz = 48
kshp = (16,16)
N = 256
model = ConvSparseSlowModel(imshp=(2,1,patch_sz,patch_sz),convwhitenfiltershp=(7,7),N=N,kshp=kshp,
perc_var=99.5,lam_sparse=1.0)
l = SGD(model=model,datasource='YouTubeFaces_aligned',display_every=1000,batchsize=model.imshp[0])
databatch = l.get_databatch(whitenpatches)
l.model.learn_whitening(databatch)
l.model.setup()
l.learn(iterations=100000)
#l.batchsize *= 2
#l.learn(iterations=100000)
l.change_target(.5)
#l.batchsize *= 2
l.learn(iterations=100000)
l.change_target(.5)
#l.batchsize *= 2
l.learn(iterations=100000)
l.change_target(.5)
#l.batchsize *= 2
l.learn(iterations=100000)
from hdl.display import display_final
display_final(l.model)
fname = os.path.join(savepath,'KAnalysis_AUC_progress.png')
plt.savefig(fname)
k_results = []
k_results.append(plot_kanalysis(l,X,Y))
plot_k_results(k_results)
epochs = 20
for epoch in range(epochs):
l.learn(iterations=10000)
k_results.append(plot_kanalysis(l,X,Y))
plot_k_results(k_results)
l.change_target(.1)
epochs = 10
for epoch in range(epochs):
l.learn(iterations=10000)
k_results.append(plot_kanalysis(l,X,Y))
plot_k_results(k_results)
l.change_target(.1)
epochs = 10
for epoch in range(epochs):
l.learn(iterations=10000)
k_results.append(plot_kanalysis(l,X,Y))
plot_k_results(k_results)
from hdl.display import display_final
display_final(l.model)
loss = compute_loss(ldefault.model,preXdefault)
print ldefault.iter, 'Default method loss:', loss
tic = now() - t0
lossdefault['loss'].append(loss)
lossdefault['time'].append(tic)
lossdefault['iter'].append(ldefault.iter)
for epoch in range(int(.8*epochs)):
ldefault.learn(iterations=iterations)
loss = compute_loss(ldefault.model,preXdefault)
print ldefault.iter, 'Default method loss:', loss, 'learner.eta', ldefault.eta
tic = now() - t0
lossdefault['loss'].append(loss)
lossdefault['time'].append(tic)
lossdefault['iter'].append(ldefault.iter)
ldefault.change_target(.5)
for epoch in range(int(.1*epochs)):
ldefault.learn(iterations=iterations)
loss = compute_loss(ldefault.model,preXdefault)
print ldefault.iter, 'Default method loss:', loss, 'learner.eta', ldefault.eta
tic = now() - t0
lossdefault['loss'].append(loss)
lossdefault['time'].append(tic)
lossdefault['iter'].append(ldefault.iter)
ldefault.change_target(.5)
for epoch in range(int(.1*epochs)):
ldefault.learn(iterations=iterations)
loss = compute_loss(ldefault.model,preXdefault)
print ldefault.iter, 'Default method loss:', loss, 'learner.eta', ldefault.eta
tic = now() - t0
