def extract_features(path, filenames):
hog_length = len(extract_hog(imread(join(path, filenames[0]))))
data = zeros((len(filenames), hog_length))
for i in range(0, len(filenames)):
filename = join(path, filenames[i])
data[i, :] = extract_hog(imread(filename))
return data
def extract_features(path, filenames):
hog_length = len(
extract_hog(imread(path + '/' + filenames[0], plugin='matplotlib')))
data = zeros((len(filenames), hog_length))
for i in range(0, len(filenames)):
filename = path + '/' + filenames[i]
data[i, :] = extract_hog(imread(filename, plugin='matplotlib'))
return data
def dump_features(path, filenames):
hog_length = len(extract_hog(imread(join(path, filenames[0]))))
data = zeros((len(filenames), hog_length))
with open(HOG_FILENAME, mode='w') as hog_file:
hog_writer = csv.writer(hog_file, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
hog_writer.writerow(['filename', 'hog_vector'])
for i in range(0, len(filenames)):
filename = join(path, filenames[i])
data[i, :] = extract_hog(imread(filename))
hog_writer.writerow([filename, ','.join(np.asarray(np.round(data[i], 3), dtype=str))])
if i % 100 == 0:
print('{} done'.format(i))
def extract_features(path, filenames):
hog_length = len(extract_hog(imread(join(path, filenames[0]))))
data = zeros((len(filenames), hog_length))
hog_data = pd.read_csv(HOG_FILENAME)
hog_data = hog_data.set_index('filename')
for i in range(0, len(filenames)):
filename = join(path, filenames[i])
data[i, :] = np.asarray(hog_data.loc[filename].hog_vector.split(','), dtype=float)
if i % 5000 == 0:
print('{} done'.format(i))
train_data, test_data = extract_data(seed)
train_data['filenames'] = 'public_tests/00_test_img_input/train/' + train_data['filenames']
test_data['filenames'] = 'public_tests/00_test_img_input/train/' + test_data['filenames']
train_data = train_data.merge(hog_data, how='inner', left_on='filenames', right_on='filename')
test_data = test_data.merge(hog_data, how='inner', left_on='filenames', right_on='filename')
return train_data, test_data
