def load_data_global_probs(dataset="train", latent=False):
def padded_vstack(blub):
a, b = blub
if a.shape[0] > b.shape[0]:
b = np.hstack([b, np.zeros((b.shape[0], a.shape[1] - b.shape[1]))])
return np.vstack([a, b])
data = load_data(dataset=dataset, which="piecewise")
data = add_kraehenbuehl_features(data, which="train_30px")
data = add_kraehenbuehl_features(data, which="train")
data = add_edges(data)
if latent:
data = add_top_node(data)
descs = np.load("/home/user/amueller/checkout/superpixel_crf/"
"global_probs_%s.npy" % dataset)
X = []
for x, glob_desc in zip(data.X, descs):
if latent:
x_ = padded_vstack([x[0],
np.repeat(sigm(glob_desc)[np.newaxis, 1:],
x[2], axis=0)])
else:
x_ = np.hstack([x[0], np.repeat(sigm(glob_desc)[np.newaxis, :],
x[0].shape[0], axis=0)])
# add features for latent node
if len(x) == 3:
X.append((x_, x[1], x[2]))
else:
X.append((x_, x[1]))
return DataBunch(X, data.Y, data.file_names, data.superpixels)
def load_data_global_probs(dataset="train", latent=False):
def padded_vstack(blub):
a, b = blub
if a.shape[0] > b.shape[0]:
b = np.hstack([b, np.zeros((b.shape[0], a.shape[1] - b.shape[1]))])
return np.vstack([a, b])
data = load_data(dataset=dataset, which="piecewise")
data = add_kraehenbuehl_features(data, which="train_30px")
data = add_kraehenbuehl_features(data, which="train")
data = add_edges(data)
if latent:
data = add_top_node(data)
descs = np.load("/home/user/amueller/checkout/superpixel_crf/"
"global_probs_%s.npy" % dataset)
X = []
for x, glob_desc in zip(data.X, descs):
if latent:
x_ = padded_vstack([
x[0],
np.repeat(sigm(glob_desc)[np.newaxis, 1:], x[2], axis=0)
])
else:
x_ = np.hstack([
x[0],
np.repeat(sigm(glob_desc)[np.newaxis, :],
x[0].shape[0],
axis=0)
])
# add features for latent node
if len(x) == 3:
X.append((x_, x[1], x[2]))
else:
X.append((x_, x[1]))
return DataBunch(X, data.Y, data.file_names, data.superpixels)
def main(C=1, test=False):
# load training data
#independent = True
independent = False
data_train = load_data(which="piecewise")
data_train = add_edges(data_train,
independent=independent,
fully_connected=True)
data_train = add_kraehenbuehl_features(data_train, which="train_30px")
data_train = add_kraehenbuehl_features(data_train, which="train")
#data_train = load_data_global_probs()
if not independent:
data_train = add_edge_features(data_train)
data_train = discard_void(data_train, 21)
if test:
data_val = load_data("val", which="piecewise_train")
data_val = add_edges(data_val, independent=independent)
data_val = add_kraehenbuehl_features(data_val, which="train_30px")
data_val = add_kraehenbuehl_features(data_val, which="train")
data_val = add_edge_features(data_val)
data_val = discard_void(data_val, 21)
data_train = concatenate_datasets(data_train, data_val)
#X_.extend(data_val.X)
#Y_.extend(data_val.Y)
n_states = 21
print("number of samples: %s" % len(data_train.X))
class_weights = 1. / np.bincount(np.hstack(data_train.Y))
#class_weights[21] = 0
class_weights *= 21. / np.sum(class_weights)
#class_weights = np.ones(n_states)
print(class_weights)
#model = crfs.GraphCRF(n_states=n_states,
#n_features=data_train.X[0][0].shape[1],
#inference_method='qpbo', class_weight=class_weights)
model = crfs.EdgeFeatureGraphCRF(n_states=n_states,
n_features=data_train.X[0][0].shape[1],
inference_method='qpbo',
class_weight=class_weights,
n_edge_features=3,
symmetric_edge_features=[0, 1],
antisymmetric_edge_features=[2])
experiment_name = "fully_connected_%f" % C
#warm_start = True
warm_start = False
ssvm = learners.OneSlackSSVM(model,
verbose=2,
C=C,
max_iter=100000,
n_jobs=-1,
tol=0.0001,
show_loss_every=50,
inference_cache=50,
cache_tol='auto',
logger=SaveLogger(experiment_name + ".pickle",
save_every=100),
inactive_threshold=1e-5,
break_on_bad=False,
inactive_window=50,
switch_to_ad3=False)
#ssvm = learners.SubgradientSSVM(
#model, verbose=3, C=C, max_iter=10000, n_jobs=-1, show_loss_every=10,
#logger=SaveLogger(experiment_name + ".pickle", save_every=10),
#momentum=0, learning_rate=0.001, decay_exponent=1)
if warm_start:
ssvm = SaveLogger(experiment_name + ".pickle").load()
ssvm.logger = SaveLogger(file_name=experiment_name + "_refit.pickle",
save_every=10)
ssvm.learning_rate = 0.000001
#ssvm.model.inference_method = 'ad3'
#ssvm.n_jobs = 1
ssvm.fit(data_train.X, data_train.Y, warm_start=warm_start)
print("fit finished!")
return
def main(C=1, test=False):
# load training data
#independent = True
independent = False
data_train = load_data(which="piecewise")
data_train = add_edges(data_train, independent=independent,
fully_connected=True)
data_train = add_kraehenbuehl_features(data_train, which="train_30px")
data_train = add_kraehenbuehl_features(data_train, which="train")
#data_train = load_data_global_probs()
if not independent:
data_train = add_edge_features(data_train)
data_train = discard_void(data_train, 21)
if test:
data_val = load_data("val", which="piecewise_train")
data_val = add_edges(data_val, independent=independent)
data_val = add_kraehenbuehl_features(data_val, which="train_30px")
data_val = add_kraehenbuehl_features(data_val, which="train")
data_val = add_edge_features(data_val)
data_val = discard_void(data_val, 21)
data_train = concatenate_datasets(data_train, data_val)
#X_.extend(data_val.X)
#Y_.extend(data_val.Y)
n_states = 21
print("number of samples: %s" % len(data_train.X))
class_weights = 1. / np.bincount(np.hstack(data_train.Y))
#class_weights[21] = 0
class_weights *= 21. / np.sum(class_weights)
#class_weights = np.ones(n_states)
print(class_weights)
#model = crfs.GraphCRF(n_states=n_states,
#n_features=data_train.X[0][0].shape[1],
#inference_method='qpbo', class_weight=class_weights)
model = crfs.EdgeFeatureGraphCRF(n_states=n_states,
n_features=data_train.X[0][0].shape[1],
inference_method='qpbo',
class_weight=class_weights,
n_edge_features=3,
symmetric_edge_features=[0, 1],
antisymmetric_edge_features=[2])
experiment_name = "fully_connected_%f" % C
#warm_start = True
warm_start = False
ssvm = learners.OneSlackSSVM(
model, verbose=2, C=C, max_iter=100000, n_jobs=-1,
tol=0.0001, show_loss_every=50, inference_cache=50, cache_tol='auto',
logger=SaveLogger(experiment_name + ".pickle", save_every=100),
inactive_threshold=1e-5, break_on_bad=False, inactive_window=50,
switch_to_ad3=False)
#ssvm = learners.SubgradientSSVM(
#model, verbose=3, C=C, max_iter=10000, n_jobs=-1, show_loss_every=10,
#logger=SaveLogger(experiment_name + ".pickle", save_every=10),
#momentum=0, learning_rate=0.001, decay_exponent=1)
if warm_start:
ssvm = SaveLogger(experiment_name + ".pickle").load()
ssvm.logger = SaveLogger(
file_name=experiment_name + "_refit.pickle",
save_every=10)
ssvm.learning_rate = 0.000001
#ssvm.model.inference_method = 'ad3'
#ssvm.n_jobs = 1
ssvm.fit(data_train.X, data_train.Y, warm_start=warm_start)
print("fit finished!")
return