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 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, 'gmm_{}_dense_{}'.format(
k,
ds,
))
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,
L,
I,
gmm,
normalization='power',
spatial_pyramid=True)
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.pyramid_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, ds): {
'cv_results':
results,
'sift_time':
sift_time,
'gmm_time':
gmm_time,
'fisher_time':
fisher_time,
'scaler_time':
scaler_time,
'crossvalidation_time':
crossvalidation_time,
'total_time':
sift_time + gmm_time + fisher_time + scaler_time +
crossvalidation_time
}
})
io.save_object(
cv_results,
'pyramid_svm_optimization_fisher_vectors_power_no_pca',
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, 'ds': ds})
io.log('-------------------------------\n')
io.log('\nSaving best parameters...')
io.save_object(
best_params,
'best_params_pyramid_svm_optimization_fisher_vectors_power_no_pca',
ignore=True)
best_params_file = os.path.abspath(
'./ignore/best_params_pyramid_svm_optimization_fisher_vectors_power_no_pca.pickle'
)
io.log('Saved at {}'.format(best_params_file))
io.log('\nSaving all cross-validation values...')
io.save_object(cv_results,
'pyramid_svm_optimization_fisher_vectors_power_no_pca',
ignore=True)
cv_results_file = os.path.abspath(
'./ignore/pyramid_svm_optimization_fisher_vectors_power_no_pca.pickle')
io.log('Saved at {}'.format(cv_results_file))
io.log('\nBEST PARAMS')
io.log('k={}, C={}, dense_grid={} --> accuracy: {:.3f}'.format(
best_params['k'], best_params['C'], best_params['ds'], best_accuracy))
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, Kp_pos = io.load_object('train_sift_descriptors', ignore=True), \
io.load_object('train_sift_labels', ignore=True), \
io.load_object('train_sift_indices', ignore=True), \
io.load_object('train_sift_keypoints', 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)
Kp_pos = np.array([Kp[i].pt for i in range(0, len(Kp))],
dtype=np.float64)
io.save_object(Kp_pos, 'train_sift_keypoints', ignore=True)
print('Elapsed time: {:.2f} s'.format(time.time() - start))
# Start hyperparameters optimization
print('\nSTARTING HYPERPARAMETER OPTIMIZATION FOR PYRAMID SVM')
codebook_k_values = [2**i for i in range(7, 14)]
params_distribution = {'C': np.logspace(-4, 3, 10**6)}
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('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,
spatial_pyramid=True,
normalization='l1')
print('Elapsed time: {:.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('Elapsed time: {:.2f} s'.format(time.time() - temp))
temp = time.time()
print('Optimizing SVM hyperparameters...')
svm = SVC(kernel='precomputed')
random_search = RandomizedSearchCV(svm,
params_distribution,
n_iter=n_iter,
scoring='accuracy',
n_jobs=N_JOBS,
refit=False,
verbose=1,
cv=4)
# Precompute Gram matrix
gram = kernels.pyramid_kernel(vis_words, vis_words)
random_search.fit(gram, labels)
print('Elapsed time: {:.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
# Appending all parameter-scores combinations
cv_results.update({k: results})
io.save_object(cv_results, 'pyramid_svm_optimization_l1')
# 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={} --> accuracy: {:.3f}'.format(best_params['k'],
best_params['C'],
best_accuracy))
print('Saving all cross-validation values...')
io.save_object(cv_results, 'pyramid_svm_optimization_l1')
print('Done')