def train_svm(test=False, C=0.01, gamma=.1, grid=False):
which = "piecewise"
data_train = load_data(which=which)
data_train = add_kraehenbuehl_features(data_train, which="train_30px")
data_train = add_kraehenbuehl_features(data_train, which="train")
data_train_novoid = discard_void(data_train, 21)
if grid and test:
raise ValueError("Don't you dare grid-search on the test-set!")
svm = LinearSVC(C=C, class_weight='auto', multi_class='crammer_singer',
dual=False)
#svm = LogisticRegression(C=C, class_weight='auto')
data_val = load_data('val', which=which)
data_val = add_kraehenbuehl_features(data_val, which="train_30px")
data_val = add_kraehenbuehl_features(data_val, which="train")
data_val_novoid = discard_void(data_val, 21)
if grid:
n_samples_train = len(np.hstack(data_train_novoid.Y))
n_samples_val = len(np.hstack(data_val_novoid.Y))
cv = SimpleSplitCV(n_samples_train, n_samples_val)
data_trainval = concatenate_datasets(data_train_novoid,
data_val_novoid)
from sklearn.grid_search import GridSearchCV
#from sklearn.grid_search import RandomizedSearchCV
#from scipy.stats import expon, gamma
#param_grid = {'C': 10. ** np.arange(1, 4), 'gamma': 10. **
#np.arange(-3, 1)}
param_grid = {'C': 10. ** np.arange(-6, 2)}
scorer = PixelwiseScorer(data=data_val)
grid = GridSearchCV(svm, param_grid=param_grid, verbose=10, n_jobs=-1,
cv=cv, scoring=scorer, refit=False)
grid.fit(np.vstack(data_trainval.X),
np.hstack(data_trainval.Y))
print(grid.best_params_)
print(grid.best_score_)
else:
print(svm)
if test:
data_train_novoid = concatenate_datasets(data_train_novoid,
data_val_novoid)
print(np.vstack(data_train_novoid.X).shape)
svm.fit(np.vstack(data_train_novoid.X), np.hstack(data_train_novoid.Y))
if test:
data_test = load_data("test", which=which)
else:
data_test = load_data("val", which=which)
data_test = add_kraehenbuehl_features(data_test, which="train_30px")
data_test = add_kraehenbuehl_features(data_test, which="train")
scorer = PixelwiseScorer(data=data_test)
scorer(svm, None, None)
return svm
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
