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')
import mlcv.classification as classification
import mlcv.feature_extraction as feature_extraction
import mlcv.input_output as io
from scripts import SESSION1
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...')
D, L, _, _ = feature_extraction.parallel_sift(train_images_filenames,
train_labels)
print('Time spend: {:.2f} s'.format(time.time() - start))
temp = time.time()
# Train Linear SVM classifier
print('Training the SVM classifier...')
svm, std_scaler, pca = classification.train_rbf_svm(
D,
L,
model_name=SESSION1['model'],
save_scaler=SESSION1['scaler'],
save_pca=SESSION1['pca'])
print('Time spend: {:.2f} s'.format(time.time() - temp))
temp = time.time()
print('\nTOTAL TRAINING TIME: {:.2f} s'.format(time.time() - start))
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_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=settings.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('Elapsed time: {:.2f} s'.format(time.time() - start))
temp = time.time()
print('Creating GMM model with {} Gaussians'.format(settings.codebook_size))
gmm = bovw.create_gmm(D, codebook_name='gmm_{}'.format(settings.codebook_size))
print('Elapsed time: {:.2f} s'.format(time.time() - temp))
temp = time.time()
print('Getting Fisher vectors from training set...')
fisher, labels = bovw.fisher_vectors(D, L, I, gmm)
print('Elapsed time: {:.2f} s'.format(time.time() - temp))
import mlcv.classification as classification
import mlcv.feature_extraction as feature_extraction
import mlcv.input_output as io
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...')
D, L, _, _ = feature_extraction.parallel_sift(train_images_filenames,
train_labels,
num_samples_class=30)
print('Time spend: {:.2f} s'.format(time.time() - start))
temp = time.time()
# Read the test set
test_images_filenames, test_labels = io.load_test_set()
print('Loaded {} test images.'.format(len(test_images_filenames)))
# Feature extraction with sift
print('Obtaining sift features...')
D_t, L_t, I_t, _ = feature_extraction.parallel_sift(
test_images_filenames, test_labels)
print('Time spend: {:.2f} s'.format(time.time() - temp))
svm = time.time()
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 = 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, Kp = 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('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='default_codebook')
print('Elapsed time: {:.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)
