def train_svm(C=0.1, grid=False):
ds = PascalSegmentation()
svm = LinearSVC(C=C, dual=False, class_weight='auto')
if grid:
data_train = load_pascal("kTrain")
X, y = shuffle(data_train.X, data_train.Y)
# prepare leave-one-label-out by assigning labels to images
image_indicators = np.hstack([np.repeat(i, len(x)) for i, x in
enumerate(X)])
# go down to only 5 "folds"
labels = image_indicators % 5
X, y = np.vstack(X), np.hstack(y)
cv = LeavePLabelOut(labels=labels, p=1)
param_grid = {'C': 10. ** np.arange(-3, 3)}
scorer = Scorer(recall_score, average="macro")
grid_search = GridSearchCV(svm, param_grid=param_grid, cv=cv,
verbose=10, scoring=scorer, n_jobs=-1)
grid_search.fit(X, y)
else:
data_train = load_pascal("train")
X, y = np.vstack(data_train.X), np.hstack(data_train.Y)
svm.fit(X, y)
print(svm.score(X, y))
eval_on_sp(ds, data_train, [svm.predict(x) for x in data_train.X],
print_results=True)
data_val = load_pascal("val")
eval_on_sp(ds, data_val, [svm.predict(x) for x in data_val.X],
print_results=True)
def visualize_pascal(plot_probabilities=False):
data = load_pascal('val')
ds = PascalSegmentation()
for x, y, f, sps in zip(data.X, data.Y, data.file_names, data.superpixels):
fig, ax = plt.subplots(2, 3)
ax = ax.ravel()
image = ds.get_image(f)
y_pixel = ds.get_ground_truth(f)
x_raw = load_kraehenbuehl(f)
boundary_image = mark_boundaries(image, sps)
ax[0].imshow(image)
ax[1].imshow(y_pixel, cmap=ds.cmap)
ax[2].imshow(boundary_image)
ax[3].imshow(np.argmax(x_raw, axis=-1), cmap=ds.cmap, vmin=0, vmax=256)
ax[4].imshow(y[sps], cmap=ds.cmap, vmin=0, vmax=256)
ax[5].imshow(np.argmax(x, axis=-1)[sps], cmap=ds.cmap, vmin=0,
vmax=256)
for a in ax:
a.set_xticks(())
a.set_yticks(())
plt.savefig("figures_pascal_val/%s.png" % f, bbox_inches='tight')
plt.close()
if plot_probabilities:
fig, ax = plt.subplots(3, 7)
for k in range(21):
ax.ravel()[k].matshow(x[:, :, k], vmin=0, vmax=1)
for a in ax.ravel():
a.set_xticks(())
a.set_yticks(())
plt.savefig("figures_pascal_val/%s_prob.png" % f,
bbox_inches='tight')
plt.close()
tracer()
def eval_segment_best_possible():
ds = PascalSegmentation()
print("loading")
data = load_pascal('train')
print("getting edges")
data = add_edges(data)
print("computing segments")
segments = [get_km_segments(x, ds.get_image(image_name), sps,
n_segments=25) for x, image_name, sps in
zip(data.X, data.file_names, data.superpixels)]
print("combining superpixels")
segments = [seg[sp] for seg, sp in zip(segments, data.superpixels)]
predictions = [gt_in_sp(ds, f, seg)[seg]
for seg, f in zip(segments, data.file_names)]
Y_true = [ds.get_ground_truth(f) for f in data.file_names]
hamming, jaccard = eval_on_pixels(ds, Y_true, predictions,
print_results=True)
tracer()
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)
def svm_on_segments(C=.1, learning_rate=.001, subgradient=False):
data_file = "data_train_XY.pickle"
ds = PascalSegmentation()
if os.path.exists(data_file):
X_, Y_ = cPickle.load(open(data_file))
else:
# load and prepare data
data_train = load_pascal("train", sp_type="cpmc")
data_train = make_cpmc_hierarchy(ds, data_train)
data_train = discard_void(ds, data_train)
X_, Y_ = data_train.X, data_train.Y
cPickle.dump((X_, Y_), open(data_file, 'wb'), -1)
class_weights = 1. / np.bincount(np.hstack(Y_))
class_weights *= 21. / np.sum(class_weights)
experiment_name = ("latent_25_cpmc_%f_qpbo_n_slack_blub3" % C)
logger = SaveLogger(experiment_name + ".pickle", save_every=10)
model = LatentNodeCRF(n_hidden_states=25,
inference_method='qpbo',
class_weight=class_weights,
latent_node_features=False)
if subgradient:
ssvm = learners.LatentSubgradientSSVM(
model, C=C, verbose=1, show_loss_every=10, logger=logger,
n_jobs=-1, learning_rate=learning_rate, decay_exponent=1,
momentum=0., max_iter=100000, decay_t0=100)
else:
latent_logger = SaveLogger("lssvm_" + experiment_name +
"_%d.pickle", save_every=1)
#base_ssvm = learners.OneSlackSSVM(
#model, verbose=2, C=C, max_iter=100, n_jobs=-1, tol=0.001,
#show_loss_every=200, inference_cache=50, logger=logger,
#cache_tol='auto', inactive_threshold=1e-5, break_on_bad=False,
#switch_to=('ogm', {'alg': 'dd'}))
base_ssvm = learners.NSlackSSVM(
model, verbose=4, C=C, n_jobs=-1, tol=0.1,
show_loss_every=20, logger=logger, inactive_threshold=1e-8,
break_on_bad=False, batch_size=36, inactive_window=10,
switch_to=('ad3', {'branch_and_bound': True}))
ssvm = learners.LatentSSVM(base_ssvm, logger=latent_logger,
latent_iter=3)
#warm_start = True
warm_start = False
if warm_start:
ssvm = logger.load()
ssvm.logger = SaveLogger(experiment_name + "_retrain.pickle",
save_every=10)
ssvm.max_iter = 10000
ssvm.decay_exponent = 1
#ssvm.decay_t0 = 1000
#ssvm.learning_rate = 0.00001
#ssvm.momentum = 0
X_, Y_ = shuffle(X_, Y_)
#ssvm.fit(data_train.X, data_train.Y)
ssvm.fit(X_, Y_)
#H_init = [np.hstack([y, np.random.randint(21, 26)]) for y in Y_]
#ssvm.fit(X_, Y_, H_init=H_init)
print("fit finished!")
def eval_spixel_best_possible():
data = load_pascal('kTrain', sp_type='cpmc')
pascal = PascalSegmentation()
hamming, jaccard = eval_on_sp(pascal, data, data.Y, print_results=True)
def eval_sp_prediction():
data = load_pascal('val')
predictions = [np.argmax(x, axis=-1) for x in data.X]
hamming, jaccard = eval_on_sp(data, predictions, print_results=True)
tracer()
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)
def svm_on_segments(C=.1, learning_rate=.001, subgradient=False):
data_file = "data_train_XY.pickle"
ds = PascalSegmentation()
if os.path.exists(data_file):
X_, Y_ = cPickle.load(open(data_file))
else:
# load and prepare data
data_train = load_pascal("train", sp_type="cpmc")
data_train = make_cpmc_hierarchy(ds, data_train)
data_train = discard_void(ds, data_train)
X_, Y_ = data_train.X, data_train.Y
cPickle.dump((X_, Y_), open(data_file, 'wb'), -1)
class_weights = 1. / np.bincount(np.hstack(Y_))
class_weights *= 21. / np.sum(class_weights)
experiment_name = ("latent_25_cpmc_%f_qpbo_n_slack_blub3" % C)
logger = SaveLogger(experiment_name + ".pickle", save_every=10)
model = LatentNodeCRF(n_hidden_states=25,
inference_method='qpbo',
class_weight=class_weights,
latent_node_features=False)
if subgradient:
ssvm = learners.LatentSubgradientSSVM(model,
C=C,
verbose=1,
show_loss_every=10,
logger=logger,
n_jobs=-1,
learning_rate=learning_rate,
decay_exponent=1,
momentum=0.,
max_iter=100000,
decay_t0=100)
else:
latent_logger = SaveLogger("lssvm_" + experiment_name + "_%d.pickle",
save_every=1)
#base_ssvm = learners.OneSlackSSVM(
#model, verbose=2, C=C, max_iter=100, n_jobs=-1, tol=0.001,
#show_loss_every=200, inference_cache=50, logger=logger,
#cache_tol='auto', inactive_threshold=1e-5, break_on_bad=False,
#switch_to=('ogm', {'alg': 'dd'}))
base_ssvm = learners.NSlackSSVM(model,
verbose=4,
C=C,
n_jobs=-1,
tol=0.1,
show_loss_every=20,
logger=logger,
inactive_threshold=1e-8,
break_on_bad=False,
batch_size=36,
inactive_window=10,
switch_to=('ad3', {
'branch_and_bound': True
}))
ssvm = learners.LatentSSVM(base_ssvm,
logger=latent_logger,
latent_iter=3)
#warm_start = True
warm_start = False
if warm_start:
ssvm = logger.load()
ssvm.logger = SaveLogger(experiment_name + "_retrain.pickle",
save_every=10)
ssvm.max_iter = 10000
ssvm.decay_exponent = 1
#ssvm.decay_t0 = 1000
#ssvm.learning_rate = 0.00001
#ssvm.momentum = 0
X_, Y_ = shuffle(X_, Y_)
#ssvm.fit(data_train.X, data_train.Y)
ssvm.fit(X_, Y_)
#H_init = [np.hstack([y, np.random.randint(21, 26)]) for y in Y_]
#ssvm.fit(X_, Y_, H_init=H_init)
print("fit finished!")