def _hogs(data, load=True, save=False, verbose=False):
# initialize config
config = _config()
# initialize variables
datapath = config['hogs_data_path']
data_hog = []
# load hog data if exists
if load and os.path.isfile(datapath):
if verbose: print('loading descriptors............ ', end = '')
data_hog = np.load(datapath)
if verbose: print('done')
# calculate hog data otherwise
else:
# initialize variables
ix = config['shape_x']
iy = config['shape_y']
bn = config['bins_n']
cx = config['cell_x']
cy = config['cell_y']
bw = config['blok_w']
bh = config['blok_h']
# perform hog
t_beg = time.time()
size = data.shape[0]
loop = 0
for image in data:
if verbose: print('\rextracting descriptors......... %d%%'
%(loop*100//size), end = '')
desc = skim.hog(image.reshape(ix, iy), orientations=bn,
pixels_per_cell=(cx, cy), cells_per_block=(bw, bh))
data_hog.append(desc)
loop = loop + 1
data_hog = np.array(data_hog, dtype='float64')
t_end = time.time()
if verbose: print('\rextracting descriptors......... done @ %8.2f sec'
%(t_end - t_beg))
# save data
if save:
if verbose: print('saving descriptors............. ', end = '')
np.save(datapath, data_hog)
if verbose: print('done')
# return hog
return data_hog
def _plot(classifier, train, valid, step=None, save=False, verbose=False):
# initialize config
config = _config()
# initialize variables
if step is None: step = config['steps_d']
plot_figs_head = config['classifier'] + '-' + config['preprocess']
plot_data_path = config['plot_data_path']
plot_figs_path = config['plot_figs_path']
m_train = train.shape[0]
m_valid = valid.shape[0]
X_valid = valid[:, 1:]
y_valid = valid[:, 0]
error_train = []
error_valid = []
sizes_train = []
# calculate data for plot
for i in range(0, m_train, step):
if verbose: print('\rgenerating plot................ %d%%'
%(i*100//m_train), end = '')
# randomly shuffle training data
np.random.shuffle(train)
# select subset of randomized training data
X_train = train[:i+step, 1:]
y_train = train[:i+step, 0]
# train classifier with selected data
classifier.fit(X_train, y_train)
# cross-validate classifier
p_train = classifier.predict(X_train)
p_valid = classifier.predict(X_valid)
# estimate errors
error_train.append(sum(y_train != p_train) / len(y_train))
error_valid.append(sum(y_valid != p_valid) / m_valid)
sizes_train.append(i+step)
error_train = np.array(error_train, dtype='float64')
error_valid = np.array(error_valid, dtype='float64')
sizes_train = np.array(sizes_train, dtype='uint32')
if verbose: print('\rgenerating plot................ done')
# plot data
pplt.plot(sizes_train, error_train, 'rs-', label='training error')
pplt.plot(sizes_train, error_valid, 'gs-', label='cross-validation error')
pplt.title(plot_figs_head.upper()+' Learning Curve')
pplt.xlabel('number of training instances')
pplt.ylabel('classification error')
pplt.legend()
xmin,xmax = pplt.xlim()
ymin,ymax = pplt.ylim()
pplt.axis([xmin, xmax+step, ymin, ymax+0.01])
pplt.grid(True)
# save data
if save:
if verbose: print('saving plot.................... ', end = '')
data = pd.DataFrame({'x1_TrainSizes':sizes_train,
'y1_TrainError':error_train,
'y2_ValidError':error_valid})
data.to_csv(plot_data_path, index=False)
pplt.savefig(plot_figs_path)
if verbose: print('done')
# display plot
pplt.show()
