def plot_curve():
print('Loading results object...')
res = io.load_object('rbf_svm_optimization_dense_norml1', ignore=True)
print('Plotting...')
colors = itertools.cycle([
'blue', 'green', 'red', 'cyan', 'magenta', 'yellow', 'darkolivegreen',
'darkviolet', 'black'
])
fig = plt.figure(figsize=(40, 20), facecolor='white')
# Compute subplot parameters
num_subplots = len(res)
num_rows = np.ceil(num_subplots / 2)
# All subplots
for ind, k in enumerate(sorted(res.keys())):
results = res[k]
x = results['param_C']
y = results['param_gamma']
z = results['mean_test_score']
print('For codebook with visual words {} '.format(k))
print('Accuracy {}'.format(max(z)))
print('C {}'.format(x[np.argmax(z)]))
print('gamma {}'.format(y[np.argmax(z)]))
color = colors.next()
ax = fig.add_subplot(num_rows, 2, ind + 1, projection='3d')
ax.scatter(x, y, z, c=color, lw=2)
ax.set_title('{} visual words'.format(k))
ax.set_xlabel('C')
ax.set_ylabel('gamma')
ax.set_zlabel('Accuracy')
plt.tight_layout()
plt.show()
plt.close()
def train_poly_svm(X,
y,
C=1,
degree=3,
gamma='auto',
coef0=0.0,
standardize=True,
dim_reduction=None,
save_scaler=False,
save_pca=False,
model_name=None):
# PCA for dimensionality reduction if necessary
pca = None
if dim_reduction is not None and dim_reduction > 0:
pca = decomposition.PCA(n_components=dim_reduction)
pca.fit(X)
X = pca.transform(X)
# Standardize the data before classification if necessary
std_scaler = None
if standardize:
std_scaler = preprocessing.StandardScaler()
std_scaler.fit(X)
X_std = std_scaler.transform(X)
else:
X_std = X
# Instance of SVM classifier
clf = svm.SVC(kernel='poly',
C=C,
degree=degree,
gamma=gamma,
coef0=coef0,
probability=True)
if model_name is not None:
# Try to load a previously trained model
try:
clf = io.load_object(model_name)
except (IOError, EOFError):
clf.fit(X_std, y)
# Store the model with the provided name
io.save_object(clf, model_name)
else:
clf.fit(X_std, y)
if save_scaler:
io.save_object(std_scaler, save_scaler)
if save_pca:
io.save_object(pca, save_pca)
return clf, std_scaler, pca
def plot_curve():
print('Loading results object...')
res = io.load_object('intersection_dense_none_svm_optimization',
ignore=True)
print('Plotting...')
colors = itertools.cycle([
'blue', 'green', 'red', 'cyan', 'magenta', 'yellow', 'darkolivegreen',
'darkviolet', 'black'
])
plt.figure(figsize=(20, 10), dpi=200, facecolor='white')
# Compute subplot parameters
num_subplots = len(res)
num_rows = np.ceil(num_subplots / 2)
# All subplots
for ind, k in enumerate(sorted(res.keys())):
# Plot
results = res[k]
x = results['param_C']
y = results['mean_test_score']
e = results['std_test_score']
sorted_indices = x.argsort()
x_sorted = np.asarray(x[sorted_indices], dtype=np.float64)
y_sorted = np.asarray(y[sorted_indices], dtype=np.float64)
e_sorted = np.asarray(e[sorted_indices], dtype=np.float64)
color = colors.next()
ax = plt.subplot(num_rows, 2, ind + 1)
ax.set_xscale("log")
ax.errorbar(x_sorted,
y_sorted,
e_sorted,
linestyle='--',
lw=2,
marker='x',
color=color)
ax.set_title('{} visual words'.format(k))
ax.set_xlabel('C')
ax.set_ylabel('Accuracy')
# Print information
print('CODEBOOK {} '.format(k))
print('-------------')
print('Mean accuracy: {}'.format(y.max()))
print('Std accuracy: {}'.format(e[np.argmax(y)]))
print('C: {}'.format(x[np.argmax(y)]))
print()
plt.tight_layout()
plt.show()
plt.close()
def train_linear_svm(X,
y,
C=1,
standardize=True,
dim_reduction=23,
save_scaler=False,
save_pca=False,
model_name=None,
liblinear=False):
# PCA for dimensionality reduction if necessary
pca = None
if dim_reduction is not None and dim_reduction > 0:
pca = decomposition.PCA(n_components=dim_reduction)
pca.fit(X)
X = pca.transform(X)
# Standardize the data before classification if necessary
std_scaler = None
if standardize:
std_scaler = preprocessing.StandardScaler()
std_scaler.fit(X)
X_std = std_scaler.transform(X)
else:
X_std = X
# Instance of SVM classifier
clf = svm.LinearSVC(C=C, max_iter=5000,
tol=1e-4) if liblinear else svm.SVC(
kernel='linear', C=C, probability=True)
if model_name is not None:
# Try to load a previously trained model
try:
clf = io.load_object(model_name)
except (IOError, EOFError):
clf.fit(X_std, y)
# Store the model with the provided name
io.save_object(clf, model_name)
else:
clf.fit(X_std, y)
if save_scaler:
io.save_object(std_scaler, save_scaler)
if save_pca:
io.save_object(pca, save_pca)
return clf, std_scaler, pca
def plot_svm_param(filename, mode='2d', name='default'):
results = io.load_object(filename)
print(results)
fig = plt.figure()
fig.suptitle(name, fontsize=14, fontweight='bold')
if mode == '3d':
ax = fig.add_subplot(111, projection='3d')
ax.scatter(results[0], results[1], results[2], c='r', marker='o')
if name == 'poly':
ax.set_xlabel('d')
ax.set_ylabel('r')
ax.set_zlabel('Accuracy')
elif name == 'sigmoid':
ax.set_xlabel('r')
ax.set_ylabel('gamma')
ax.set_zlabel('Accuracy')
D = results[0]
G = results[1]
A = results[2]
ind = np.argmax(results[2])
print(name + ' 2D: Best parameters are: Degree ' + str(D[ind]) + ' Gamma ' + str(
G[ind]) + ' with Accuracy ' + str(
A[ind]))
elif mode == '2d':
ax = fig.add_subplot(111)
ax.plot(results[0], results[2])
ax.set_xlabel('Gamma')
ax.set_ylabel('Accuracy')
G = results[0]
A = results[2]
ind = np.argmax(results[2])
print(name + ' : Best parameters are: Gamma ' + str(G[ind]) + ' with Accuracy ' + str(A[ind]))
elif mode == 'cost':
ax = fig.add_subplot(111)
ax.set_xlabel('Cost')
ax.set_ylabel('Accuracy')
ax.plot(results[0], results[1])
C = results[0]
A = results[1]
ind = np.argmax(results[1])
print(name + '-cost : Best parameters are: C ' + str(C[ind]) + ' with Accuracy ' + str(A[ind]))
plt.show()
def create_gmm(D, codebook_name=None):
from libraries.yael.yael import ynumpy
k = settings.codebook_size
if codebook_name is not None:
# Try to load a previously trained codebook
try:
gmm = io.load_object(codebook_name)
except (IOError, EOFError):
gmm = ynumpy.gmm_learn(np.float32(D), k)
# Store the model with the provided name
io.save_object(gmm, codebook_name)
else:
gmm = ynumpy.gmm_learn(np.float32(D), k)
return gmm
def create_codebook(X, codebook_name=None, k_means_init='random'):
k = settings.codebook_size
batch_size = 20 * k if X.shape[0] > 20 * k else X.shape[0] / 10
codebook = cluster.MiniBatchKMeans(n_clusters=k,
verbose=False,
batch_size=batch_size,
compute_labels=False,
reassignment_ratio=10**-4,
init=k_means_init)
if codebook_name is not None:
# Try to load a previously trained codebook
try:
codebook = io.load_object(codebook_name)
except (IOError, EOFError):
codebook.fit(X)
# Store the model with the provided name
io.save_object(codebook, codebook_name)
else:
codebook.fit(X)
return codebook
def train_pyramid_svm(X,
y,
C=1,
standardize=True,
dim_reduction=None,
save_scaler=False,
save_pca=False,
model_name=None):
# Standardize the data before classification if necessary
std_scaler = None
if standardize:
std_scaler = preprocessing.StandardScaler()
std_scaler.fit(X)
X_std = std_scaler.transform(X)
else:
X_std = X
clf = svm.SVC(kernel=kernels.pyramid_kernel, C=C, probability=True)
if model_name is not None:
# Instance of SVM classifier
# Try to load a previously trained model
try:
clf = io.load_object(model_name)
except (IOError, EOFError):
clf.fit(X_std, y)
# Store the model with the provided name
io.save_object(clf, model_name)
else:
clf.fit(X_std, y)
if save_scaler:
io.save_object(std_scaler, save_scaler)
return clf, std_scaler, None
def train():
start = time.time()
# Read the training set
train_images_filenames, train_labels = io.load_training_set()
print('Loaded {} train images.'.format(len(train_images_filenames)))
# Feature extraction with sift
print('Obtaining sift features...')
try:
D, L, I = io.load_object('train_sift_descriptors', ignore=True), \
io.load_object('train_sift_labels', ignore=True), \
io.load_object('train_sift_indices', ignore=True)
except IOError:
D, L, I, _ = feature_extraction.parallel_sift(train_images_filenames,
train_labels,
num_samples_class=-1,
n_jobs=N_JOBS)
io.save_object(D, 'train_sift_descriptors', ignore=True)
io.save_object(L, 'train_sift_labels', ignore=True)
io.save_object(I, 'train_sift_indices', ignore=True)
print('Time spend: {:.2f} s'.format(time.time() - start))
# Start hyperparameters optimization
print('\nSTARTING HYPERPARAMETER OPTIMIZATION FOR RBF SVM')
codebook_k_values = [2**i for i in range(7, 16)]
params_distribution = {
'C': np.logspace(-4, 1, 10**3),
'gamma': np.logspace(-3, 1, 10**3)
}
n_iter = 100
best_accuracy = 0
best_params = {}
cv_results = {}
# Iterate codebook values
for k in codebook_k_values:
temp = time.time()
print('Creating codebook with {} visual words'.format(k))
D = D.astype(np.uint32)
codebook = bovw.create_codebook(D,
codebook_name='codebook_{}'.format(k))
print('Time spend: {:.2f} s'.format(time.time() - temp))
temp = time.time()
print('Getting visual words from training set...')
vis_words, labels = bovw.visual_words(D,
L,
I,
codebook,
normalization='l1')
print('Time spend: {:.2f} s'.format(time.time() - temp))
temp = time.time()
print('Scaling features...')
std_scaler = StandardScaler().fit(vis_words)
vis_words = std_scaler.transform(vis_words)
print('Time spend: {:.2f} s'.format(time.time() - temp))
temp = time.time()
print('Optimizing SVM hyperparameters...')
svm = SVC(kernel='rbf')
random_search = RandomizedSearchCV(svm,
params_distribution,
n_iter=n_iter,
scoring='accuracy',
n_jobs=N_JOBS,
refit=False,
verbose=1,
cv=4)
random_search.fit(vis_words, labels)
print('Time spend: {:.2f} s'.format(time.time() - temp))
# Convert MaskedArrays to ndarrays to avoid unpickling bugs
results = random_search.cv_results_
results['param_C'] = results['param_C'].data
results['param_gamma'] = results['param_gamma'].data
# Appending all parameter-scores combinations
cv_results.update({k: results})
io.save_object(cv_results, 'rbf_svm_optimization_norml1')
# Obtaining the parameters which yielded the best accuracy
if random_search.best_score_ > best_accuracy:
best_accuracy = random_search.best_score_
best_params = random_search.best_params_
best_params.update({'k': k})
print('-------------------------------\n')
print('\nBEST PARAMS')
print('k={}, C={} , gamma={} --> accuracy: {:.3f}'.format(
best_params['k'], best_params['C'], best_params['gamma'],
best_accuracy))
print('Saving all cross-validation values...')
io.save_object(cv_results, 'rbf_svm_optimization_norml1')
print('Done')
def plot_curve():
io.log('Loading cross-validation values...')
cv_values = io.load_object('intersection_svm_CNNfeatures', ignore=True)
io.log('Loading best parameters...')
best_params = io.load_object('best_params_intersection_svm_CNNfeatures1',
ignore=True)
io.log('Plotting...')
colors = itertools.cycle([
'blue', 'green', 'red', 'cyan', 'magenta', 'yellow', 'darkolivegreen',
'darkviolet', 'black'
])
# Subplot parameters
plt.figure(facecolor='white')
num_subplots = len(codebook_size)
num_columns = 1
num_rows = np.ceil(num_subplots / num_columns)
# All subplots
for ind, k in enumerate(codebook_size):
# Search dictionary
val = cv_values[(k)]
results = val['cv_results']
feature_time = val['feature_time']
pca_time = val['pca_time']
gmm_time = val['gmm_time']
fisher_time = val['fisher_time']
scaler_time = val['scaler_time']
crossvalidation_time = val['crossvalidation_time']
total_time = val['total_time']
# Plot
x = results['param_C']
y = results['mean_test_score']
e = results['std_test_score']
sorted_indices = x.argsort()
x_sorted = np.asarray(x[sorted_indices], dtype=np.float64)
y_sorted = np.asarray(y[sorted_indices], dtype=np.float64)
e_sorted = np.asarray(e[sorted_indices], dtype=np.float64)
color = colors.next()
ax = plt.subplot(num_rows, num_columns, ind + 1)
ax.set_xscale("log")
ax.set_ylim((0.7, 0.9))
ax.errorbar(x_sorted,
y_sorted,
e_sorted,
linestyle='--',
lw=2,
marker='x',
color=color)
ax.set_title('{} Gaussians in GMM'.format(k))
ax.set_xlabel('C')
ax.set_ylabel('Accuracy')
# Print information
io.log('CODEBOOK {} '.format(k))
io.log('-------------')
io.log('Mean accuracy: {}'.format(y.max()))
io.log('Std accuracy: {}'.format(e[np.argmax(y)]))
io.log('C: {}'.format(x[np.argmax(y)]))
io.log()
io.log('Timing')
io.log('\tSIFT time: {:.2f} s'.format(feature_time))
io.log('\tPCA time: {:.2f} s'.format(pca_time))
io.log('\tGMM time: {:.2f} s'.format(gmm_time))
io.log('\tFisher time: {:.2f} s'.format(fisher_time))
io.log('\tScaler time: {:.2f} s'.format(scaler_time))
io.log('\tCV time: {:.2f} s'.format(crossvalidation_time))
io.log('\t_________________________')
io.log('\tTOTAL TIME: {:.2f} s'.format(total_time))
io.log()
plt.tight_layout()
plt.show()
plt.close()
def train():
best_accuracy = 0
best_params = {}
cv_results = {}
""" SETTINGS """
settings.n_jobs = 1
# Read the training set
train_images_filenames, train_labels = io.load_training_set()
io.log('Loaded {} train images.'.format(len(train_images_filenames)))
k = 64
io.log('Obtaining dense CNN features...')
start_feature = time.time()
try:
D, L, I = io.load_object('train_CNN_descriptors', ignore=True), \
io.load_object('train_CNN_labels', ignore=True), \
io.load_object('train_CNN_indices', ignore=True)
except IOError:
# load VGG model
base_model = VGG16(weights='imagenet')
# io.save_object(base_model, 'base_model', ignore=True)
# visualize topology in an image
plot(base_model,
to_file='modelVGG16.png',
show_shapes=True,
show_layer_names=True)
# crop the model up to a certain layer
model = Model(input=base_model.input,
output=base_model.get_layer('block5_conv2').output)
D, L, I = feature_extraction.parallel_CNN_features(
train_images_filenames,
train_labels,
model,
num_samples_class=-1,
n_jobs=settings.n_jobs)
io.save_object(D, 'train_CNN_descriptors', ignore=True)
io.save_object(L, 'train_CNN_labels', ignore=True)
io.save_object(I, 'train_CNN_indices', ignore=True)
feature_time = time.time() - start_feature
io.log('Elapsed time: {:.2f} s'.format(feature_time))
for dim_red in pca_reduction:
io.log('Applying PCA ... ')
start_pca = time.time()
settings.pca_reduction = D.shape[1] * dim_red
pca, D_pca = feature_extraction.pca(D)
pca_time = time.time() - start_pca
io.log('Elapsed time: {:.2f} s'.format(pca_time))
for k in codebook_size:
io.log('Creating GMM model (k = {})'.format(k))
start_gmm = time.time()
settings.codebook_size = k
gmm = bovw.create_gmm(
D_pca,
'gmm_{}_pca_{}_CNNfeature'.format(k, settings.pca_reduction))
gmm_time = time.time() - start_gmm
io.log('Elapsed time: {:.2f} s'.format(gmm_time))
io.log('Getting Fisher vectors from training set...')
start_fisher = time.time()
fisher, labels = bovw.fisher_vectors(D_pca,
L,
I,
gmm,
normalization='l2')
fisher_time = time.time() - start_fisher
io.log('Elapsed time: {:.2f} s'.format(fisher_time))
io.log('Scaling features...')
start_scaler = time.time()
std_scaler = StandardScaler().fit(fisher)
vis_words = std_scaler.transform(fisher)
scaler_time = time.time() - start_scaler
io.log('Elapsed time: {:.2f} s'.format(scaler_time))
io.log('Optimizing SVM hyperparameters...')
start_crossvalidation = time.time()
svm = SVC(kernel='precomputed')
random_search = RandomizedSearchCV(svm,
params_distribution,
n_iter=n_iter,
scoring='accuracy',
n_jobs=settings.n_jobs,
refit=False,
cv=3,
verbose=1)
# Precompute Gram matrix
gram = kernels.intersection_kernel(vis_words, vis_words)
random_search.fit(gram, labels)
crossvalidation_time = time.time() - start_crossvalidation
io.log('Elapsed time: {:.2f} s'.format(crossvalidation_time))
# Convert MaskedArrays to ndarrays to avoid unpickling bugs
results = random_search.cv_results_
results['param_C'] = results['param_C'].data
# Appending all parameter-scores combinations
cv_results.update({
(k): {
'cv_results':
results,
'feature_time':
feature_time,
'pca_time':
pca_time,
'gmm_time':
gmm_time,
'fisher_time':
fisher_time,
'scaler_time':
scaler_time,
'crossvalidation_time':
crossvalidation_time,
'total_time':
feature_time + pca_time + gmm_time + fisher_time +
scaler_time + crossvalidation_time
}
})
io.save_object(cv_results,
'intersection_svm_CNNfeatures',
ignore=True)
# Obtaining the parameters which yielded the best accuracy
if random_search.best_score_ > best_accuracy:
best_accuracy = random_search.best_score_
best_params = random_search.best_params_
best_params.update({'k': k, 'pca': dim_red})
io.log('-------------------------------\n')
io.log('\nSaving best parameters...')
io.save_object(best_params,
'best_params_intersection_svm_CNNfeatures',
ignore=True)
best_params_file = os.path.abspath(
'./ignore/best_params_intersection_svm_CNNfeatures.pickle')
io.log('Saved at {}'.format(best_params_file))
io.log('\nSaving all cross-validation values...')
io.save_object(cv_results, 'intersection_svm_CNNfeatures', ignore=True)
cv_results_file = os.path.abspath(
'./ignore/intersection_svm_CNNfeatures.pickle')
io.log('Saved at {}'.format(cv_results_file))
io.log('\nBEST PARAMS')
io.log('k={}, dim_red={}, C={} --> accuracy: {:.3f}'.format(
best_params['k'], best_params['pca'], best_params['C'], best_accuracy))
def train():
best_accuracy = 0
best_params = {}
cv_results = {}
""" SETTINGS """
settings.n_jobs = 1
# Read the training set
train_images_filenames, train_labels = io.load_training_set()
io.log('Loaded {} train images.'.format(len(train_images_filenames)))
# Parameter sweep for dense SIFT
for ds in dense_sampling_density:
io.log('Obtaining dense features with sampling parameter {}...'.format(
ds))
start_sift = time.time()
settings.dense_sampling_density = ds
try:
D, L, I = io.load_object('train_dense_descriptors_{}'.format(settings.dense_sampling_density), ignore=True), \
io.load_object('train_dense_labels_{}'.format(settings.dense_sampling_density), ignore=True), \
io.load_object('train_dense_indices_{}'.format(settings.dense_sampling_density), ignore=True)
except IOError:
D, L, I, _ = feature_extraction.parallel_dense(
train_images_filenames,
train_labels,
num_samples_class=-1,
n_jobs=settings.n_jobs)
io.save_object(D,
'train_dense_descriptors_{}'.format(
settings.dense_sampling_density),
ignore=True)
io.save_object(L,
'train_dense_labels_{}'.format(
settings.dense_sampling_density),
ignore=True)
io.save_object(I,
'train_dense_indices_{}'.format(
settings.dense_sampling_density),
ignore=True)
sift_time = time.time() - start_sift
io.log('Elapsed time: {:.2f} s'.format(sift_time))
# Parameter sweep for PCA
for dim_red in pca_reduction:
io.log('Applying PCA (dim = {})...'.format(dim_red))
start_pca = time.time()
settings.pca_reduction = dim_red
pca, D_pca = feature_extraction.pca(D)
pca_time = time.time() - start_pca
io.log('Elapsed time: {:.2f} s'.format(pca_time))
# Parameter sweep for codebook size
for k in codebook_size:
io.log('Creating GMM model (k = {})'.format(k))
start_gmm = time.time()
settings.codebook_size = k
gmm = bovw.create_gmm(
D_pca, 'gmm_{}_dense_{}_pca_{}'.format(k, ds, dim_red))
gmm_time = time.time() - start_gmm
io.log('Elapsed time: {:.2f} s'.format(gmm_time))
io.log('Getting Fisher vectors from training set...')
start_fisher = time.time()
fisher, labels = bovw.fisher_vectors(D_pca,
L,
I,
gmm,
normalization='l2')
fisher_time = time.time() - start_fisher
io.log('Elapsed time: {:.2f} s'.format(fisher_time))
io.log('Scaling features...')
start_scaler = time.time()
std_scaler = StandardScaler().fit(fisher)
vis_words = std_scaler.transform(fisher)
scaler_time = time.time() - start_scaler
io.log('Elapsed time: {:.2f} s'.format(scaler_time))
io.log('Optimizing SVM hyperparameters...')
start_crossvalidation = time.time()
svm = SVC(kernel='precomputed')
random_search = RandomizedSearchCV(svm,
params_distribution,
n_iter=n_iter,
scoring='accuracy',
n_jobs=settings.n_jobs,
refit=False,
cv=3,
verbose=1)
# Precompute Gram matrix
gram = kernels.intersection_kernel(vis_words, vis_words)
random_search.fit(gram, labels)
crossvalidation_time = time.time() - start_crossvalidation
io.log('Elapsed time: {:.2f} s'.format(crossvalidation_time))
# Convert MaskedArrays to ndarrays to avoid unpickling bugs
results = random_search.cv_results_
results['param_C'] = results['param_C'].data
# Appending all parameter-scores combinations
cv_results.update({
(k, dim_red, ds): {
'cv_results':
results,
'sift_time':
sift_time,
'pca_time':
pca_time,
'gmm_time':
gmm_time,
'fisher_time':
fisher_time,
'scaler_time':
scaler_time,
'crossvalidation_time':
crossvalidation_time,
'total_time':
sift_time + pca_time + gmm_time + fisher_time +
scaler_time + crossvalidation_time
}
})
io.save_object(
cv_results,
'intersection_svm_optimization_fisher_vectors_l2',
ignore=True)
# Obtaining the parameters which yielded the best accuracy
if random_search.best_score_ > best_accuracy:
best_accuracy = random_search.best_score_
best_params = random_search.best_params_
best_params.update({'k': k, 'pca': dim_red, 'ds': ds})
io.log('-------------------------------\n')
io.log('\nSaving best parameters...')
io.save_object(
best_params,
'best_params_intersection_svm_optimization_fisher_vectors_l2',
ignore=True)
best_params_file = os.path.abspath(
'./ignore/best_params_intersection_svm_optimization_fisher_vectors_l2.pickle'
)
io.log('Saved at {}'.format(best_params_file))
io.log('\nSaving all cross-validation values...')
io.save_object(cv_results,
'intersection_svm_optimization_fisher_vectors_l2',
ignore=True)
cv_results_file = os.path.abspath(
'./ignore/intersection_svm_optimization_fisher_vectors_l2.pickle')
io.log('Saved at {}'.format(cv_results_file))
io.log('\nBEST PARAMS')
io.log('k={}, C={}, dim_red={}, dense_grid={} --> accuracy: {:.3f}'.format(
best_params['k'], best_params['C'], best_params['pca'],
best_params['ds'], best_accuracy))
predicted_class = lin_svm.classes_[np.argmax(prediction_prob)]
return predicted_class == test_label, predicted_class, np.ravel(prediction_prob)
""" MAIN SCRIPT"""
if __name__ == '__main__':
start = time.time()
if calculate_results==1:
# Read the training set
train_images_filenames, train_labels = io.load_training_set()
print('Loaded {} train images.'.format(len(train_images_filenames)))
# Feature extraction with sift
print('Obtaining dense sift features...')
try:
D, L, I = io.load_object('train_dense_descriptors', ignore=True), \
io.load_object('train_dense_labels', ignore=True), \
io.load_object('train_dense_indices', ignore=True)
except IOError:
D, L, I, _ = feature_extraction.parallel_dense(train_images_filenames, train_labels, num_samples_class=-1,
n_jobs=N_JOBS)
io.save_object(D, 'train_dense_descriptors', ignore=True)
io.save_object(L, 'train_dense_labels', ignore=True)
io.save_object(I, 'train_dense_indices', ignore=True)
print('Elapsed time: {:.2f} s'.format(time.time() - start))
temp = time.time()
print('Creating codebook with {} visual words'.format(K))
codebook = bovw.create_codebook(D, codebook_name='dense_codebook')
print('Elapsed time: {:.2f} s'.format(time.time() - temp))
predicted_class = svm.classes_[np.argmax(prediction_prob)]
return predicted_class == test_label, predicted_class, np.ravel(prediction_prob)
""" MAIN SCRIPT"""
if __name__ == '__main__':
start = time.time()
# Read the training set
train_images_filenames, train_labels = io.load_training_set()
print('Loaded {} train images.'.format(len(train_images_filenames)))
# Feature extraction with sift
print('Obtaining sift features...')
try:
D, L, I, Kp_pos = io.load_object('train_dense_descriptors', ignore=True), \
io.load_object('train_dense_labels', ignore=True), \
io.load_object('train_dense_indices', ignore=True), \
io.load_object('train_dense_keypoints', ignore=True)
except IOError:
print('error')
D, L, I, Kp = feature_extraction.parallel_dense(train_images_filenames, train_labels, num_samples_class=-1,
n_jobs=N_JOBS)
io.save_object(D, 'train_dense_descriptors', ignore=True)
io.save_object(L, 'train_dense_labels', ignore=True)
io.save_object(I, 'train_dense_indices', ignore=True)
Kp_pos = np.array([Kp[i].pt for i in range(0, len(Kp))], dtype=np.float64)
io.save_object(Kp_pos, 'train_dense_keypoints', ignore=True)
print('Elapsed time: {:.2f} s'.format(time.time() - start))
temp = time.time()
import mlcv.input_output as io
import argparse
import matplotlib.pyplot as plt
if __name__ == '__main__':
arguments_parser = argparse.ArgumentParser()
arguments_parser.add_argument('file')
arguments_parser.add_argument('--dpi', type=int, default=50)
arguments = arguments_parser.parse_args()
filename = arguments.file
dpi = arguments.dpi
print(filename.upper())
# Load file
history = io.load_object(filename, ignore=True)
# Plot
plt.figure(dpi=dpi, facecolor='white')
plt.plot(history['acc'])
plt.plot(history['val_acc'])
plt.title('Accuracy')
plt.ylabel('Accuracy')
plt.xlabel('Epoch')
plt.ylim((0, 1))
plt.legend(['train', 'validation'], loc='lower right')
plt.show()
plt.close()
plt.figure(dpi=dpi, facecolor='white')
plt.plot(history['loss'])
""" SETTINGS """
settings.n_jobs = 1
settings.codebook_size = 32
settings.dense_sampling_density = 16
settings.pca_reduction = 64
start = time.time()
# Read the training set
train_images_filenames, train_labels = io.load_training_set()
print('Loaded {} train images.'.format(len(train_images_filenames)))
# Feature extraction with sift
print('Obtaining dense features...')
try:
D, L, I = io.load_object('train_dense_descriptors', ignore=True), \
io.load_object('train_dense_labels', ignore=True), \
io.load_object('train_dense_indices', ignore=True)
except IOError:
D, L, I, _ = feature_extraction.parallel_dense(train_images_filenames, train_labels,
num_samples_class=-1,
n_jobs=settings.n_jobs)
io.save_object(D, 'train_dense_descriptors', ignore=True)
io.save_object(L, 'train_dense_labels', ignore=True)
io.save_object(I, 'train_dense_indices', ignore=True)
print('Elapsed time: {:.2f} s'.format(time.time() - start))
temp = time.time()
print('Applying PCA...')
pca, D = feature_extraction.pca(D)
print('Elapsed time: {:.2f} s'.format(time.time() - temp))
probability=True)
probabilities = np.sum(predictions, axis=0)
predicted_class = svm.classes_[np.argmax(probabilities)]
return predicted_class == test_label, predicted_class, test_label
if __name__ == '__main__':
start = time.time()
# Read the test set
test_images_filenames, test_labels = io.load_test_set()
print('Loaded {} test images.'.format(len(test_images_filenames)))
# Load the trained model, scaler and PCA
svm = io.load_object(SESSION1['model'])
std_scaler = io.load_object(SESSION1['scaler'])
pca = io.load_object(SESSION1['pca'])
# Feature extraction with sift, prediction with SVM and aggregation to obtain final class
print('Predicting test data...')
result = joblib.Parallel(n_jobs=SESSION1['n_jobs'], backend='threading')(
joblib.delayed(parallel_testing)(test_image, test_label, svm,
std_scaler, pca)
for test_image, test_label in zip(test_images_filenames, test_labels))
correct_class = [i[0] for i in result]
predicted = [i[1] for i in result]
expected = [i[2] for i in result]
num_correct = np.count_nonzero(correct_class)