def main(C=1):
dataset = NYUSegmentation()
# load training data
data_train = load_nyu(n_sp=500, sp='rgbd')
data_train = add_edges(data_train)
data_train = add_edge_features(dataset,
data_train,
depth_diff=True,
normal_angles=True)
data_train = discard_void(dataset, data_train)
n_states = 4.
print("number of samples: %s" % len(data_train.X))
class_weights = 1. / np.bincount(np.hstack(data_train.Y))
class_weights *= n_states / 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(inference_method='qpbo',
class_weight=class_weights,
n_edge_features=5,
symmetric_edge_features=[0, 1])
experiment_name = "rgbd_test%f" % C
ssvm = learners.OneSlackSSVM(model,
verbose=2,
C=C,
max_iter=100000,
n_jobs=-1,
tol=0.001,
show_loss_every=100,
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", {
'branch_and_bound': True
}))
ssvm.fit(data_train.X, data_train.Y)
print("fit finished!")
return
def main():
ds = PascalSegmentation()
# load training data
edge_type = "pairwise"
which = "kTrain"
data_train = load_pascal(which=which, sp_type="cpmc")
data_train = add_edges(data_train, edge_type)
data_train = add_edge_features(ds, data_train)
data_train = discard_void(ds, data_train, ds.void_label)
X, Y = data_train.X, data_train.Y
class_weights = 1. / np.bincount(np.hstack(Y))
class_weights *= 21. / np.sum(class_weights)
model = crfs.EdgeFeatureGraphCRF(class_weight=class_weights,
symmetric_edge_features=[0, 1],
antisymmetric_edge_features=[2],
inference_method='qpbo')
ssvm = learners.NSlackSSVM(model, C=0.01, n_jobs=-1)
ssvm.fit(X, Y)
def main(C=1, test=False):
ds = PascalSegmentation()
# load training data
edge_type = "pairwise"
if test:
which = "train"
else:
which = "kTrain"
data_train = load_pascal(which=which, sp_type="cpmc")
data_train = add_edges(data_train, edge_type)
data_train = add_edge_features(ds, data_train)
data_train = discard_void(ds, data_train, ds.void_label)
print("number of samples: %s" % len(data_train.X))
class_weights = 1. / np.bincount(np.hstack(data_train.Y))
class_weights *= 21. / np.sum(class_weights)
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(inference_method='qpbo',
class_weight=class_weights,
symmetric_edge_features=[0, 1],
antisymmetric_edge_features=[2])
experiment_name = "cpmc_edge_features_trainval_new_%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=None)
#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=0.1, decay_exponent=1, decay_t0=100)
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 = 'ad3bb'
#ssvm.n_jobs = 1
ssvm.fit(data_train.X, data_train.Y, warm_start=warm_start)
return
print("fit finished!")
if test:
data_val = load_pascal('val')
else:
data_val = load_pascal('kVal')
data_val = add_edges(data_val, edge_type)
data_val = add_edge_features(ds, data_val, more_colors=True)
eval_on_sp(ds, data_val, ssvm.predict(data_val.X), print_results=True)
from pystruct import learners
import pystruct.models as crfs
from pystruct.utils import SaveLogger
data_train = cPickle.load(open("data_train_dict.pickle"))
C = 0.01
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. / np.sum(class_weights)
print(class_weights)
model = crfs.EdgeFeatureGraphCRF(inference_method='qpbo',
class_weight=class_weights,
symmetric_edge_features=[0, 1],
antisymmetric_edge_features=[2])
experiment_name = "edge_features_one_slack_trainval_%f" % C
ssvm = learners.NSlackSSVM(model,
verbose=2,
C=C,
max_iter=100000,
n_jobs=-1,
tol=0.0001,
show_loss_every=5,
logger=SaveLogger(experiment_name + ".pickle",
save_every=100),
inactive_threshold=1e-3,
inactive_window=10,
import pickle
import pdb, time, os
from pystruct import learners
import pystruct.models as crfs
from pystruct.utils import SaveLogger
output_folder = 'out'
method = 'max-product'
evaluate_val = True
import cv2
data_train = pickle.load(open("train_data_davis_sub.p", "rb"))
C = 0.01
n_states = 2
print("number of samples: %s" % len(data_train['X']))
model = crfs.EdgeFeatureGraphCRF(inference_method=method)
experiment_name = "edge_features_one_slack_trainval_%f" % C
ssvm = learners.NSlackSSVM(
model, verbose=2, C=C, max_iter=25, n_jobs=-1,
tol=0.0001, show_loss_every=5,
logger=SaveLogger(experiment_name + ".pickle", save_every=5),
inactive_threshold=1e-3, inactive_window=10, batch_size=100)
start = time.time()
ssvm.fit(data_train['X'], data_train['Y'])
print('average training time: %f s/iter'%((time.time()-start)/25.0))
data_val = pickle.load(open("val_data_davis_sub.p", "rb"))
start = time.time()
if evaluate_val:
y_pred = ssvm.predict(data_val['X'])
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
# split train and test data
test_ratio = 0.2
X_train, X_test, y_train, y_test = crosval.train_test_split(
X, y, test_size=test_ratio, random_state=0)
# setup parameter
n_states = np.unique(np.hstack(y)).shape[0]
class_weight = 1. / np.bincount(np.hstack(y))
class_weight *= float(n_states) / np.sum(class_weight)
n_jobs = 6
C = 0.01
# init CRF model
# model = models.EdgeFeatureGraphCRF(inference_method='qpbo', class_weight=class_weight, symmetric_edge_features=[0, 1], antisymmetric_edge_features=[2, 3])
model = models.EdgeFeatureGraphCRF(inference_method='qpbo',
class_weight=class_weight,
symmetric_edge_features=[0, 1, 2],
antisymmetric_edge_features=[3, 4])
# model = models.EdgeFeatureGraphCRF(class_weight=class_weight, symmetric_edge_features=[0, 1], antisymmetric_edge_features=[2, 3])
# init learner
ssvm = learners.NSlackSSVM(model,
verbose=2,
n_jobs=n_jobs,
C=C,
logger=SaveLogger(args.model_filename,
save_every=50))
# ssvm = learners.NSlackSSVM(model, verbose=2, C=C, max_iter=100000, n_jobs=n_jobs, tol=0.0001, show_loss_every=5, logger=SaveLogger(args.model_filename, save_every=50), inactive_threshold=1e-3, inactive_window=10, batch_size=100)
# train model
ssvm.fit(X_train, y_train)
dtype=np.int), edgesFeatures))
test_count = 0
test_Y = []
for i in range(0, len(test_edges)):
labels = np.zeros([1, test_edges[i][0].shape[0]], dtype=int)
for j in range(0, test_edges[i][0].shape[0]):
labels[0][j] = test_labels[test_count + j].astype(int)
test_count = test_count + test_edges[i][0].shape[0]
test_Y.append(labels[0])
C = 0.01
n_states = 2
class_weights = 1. / np.bincount(np.hstack(valid_Y))
class_weights *= 2. / np.sum(class_weights)
print(class_weights)
model = crfs.EdgeFeatureGraphCRF(class_weight=class_weights)
experiment_name = "edge_features_one_slack_trainval_%f" % C
ssvm = learners.NSlackSSVM(model,
verbose=2,
C=1,
max_iter=1000,
n_jobs=-1,
tol=0.0001,
show_loss_every=5,
inactive_threshold=1e-3,
inactive_window=10,
batch_size=100)
ssvm.fit(X_valid, valid_Y)
print "Saving Data"
(X_train,Y_train) = cPickle.load(open("/home/prassanna/Development/workspace/CamVid_scripts/FrameworkDump3/model/crf_data_200.pkl","r"))
#Do Some Data modifying operations
#Energy * -1 perhaps?
print "Initializing CRF"
nr_states= 12;
class_counts = np.bincount(np.hstack(Y_train))
class_frequency = 1./ class_counts;
class_weights = class_frequency*(nr_states/np.sum(class_frequency))
C = 0.01
experiment_name = "edge_features_one_slack_trainval_%f" % C
model = crfs.EdgeFeatureGraphCRF( n_states = nr_states, inference_method='max-product',
class_weight=class_weights,
symmetric_edge_features=[0])
ssvm = learners.OneSlackSSVM(
model, verbose=2, C=C, max_iter=100000, n_jobs=-1,
tol=0.0001, show_loss_every=5,
logger=SaveLogger(experiment_name + ".pickle", save_every=100),
inactive_threshold=1e-3, inactive_window=10)
#Fit CRF
ssvm.fit(X_train, Y_train)
cPickle.dump(ssvm, open("/home/prassanna/Development/workspace/CamVid_scripts/FrameworkDump3/model/trained_crf_fromdata.pkl", "w"))