def __data_generator(self, batch_samples):
# initialize images and labels tensors for faster processing
X = np.empty((len(batch_samples), *self.img_crop_dims, 3))
y = np.empty((len(batch_samples), self.n_classes))
for i, sample in enumerate(batch_samples):
# load and randomly augment image
img_file = os.path.join(
self.img_dir, '{}.{}'.format(sample['image_id'],
self.img_format))
img = utils.load_image(img_file, self.img_load_dims)
if img is not None:
img = utils.random_crop(img, self.img_crop_dims)
img = utils.random_horizontal_flip(img)
X[i, ] = img
# normalize labels
y[i, ] = utils.normalize_labels(sample['label'])
# apply basenet specific preprocessing
# input is 4D numpy array of RGB values within [0, 255]
X = self.basenet_preprocess(X)
return X, y
def __data_generator(self, batch_samples):
# initialize images and labels tensors for faster processing
X = np.empty((len(batch_samples), *self.img_load_dims, 3))
y = np.empty((len(batch_samples), self.n_classes))
for i, sample in enumerate(batch_samples):
# load and randomly augment image
img_file = os.path.join(self.img_dir, '{}.{}'.format(sample['image_id'], self.img_format))
img = utils.load_image(img_file, self.img_load_dims)
if img is not None:
X[i, ] = img
# normalize labels
if sample.get('label') is not None:
y[i, ] = utils.normalize_labels(sample['label'])
# apply basenet specific preprocessing
# input is 4D numpy array of RGB values within [0, 255]
X = self.basenet_preprocess(X)
return X, y
def test_normalize_label(self):
labels = np.array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1])
normed_label = utils.normalize_labels(labels)
np.testing.assert_array_equal(np.array([.1, .1, .1, .1, .1, .1, .1, .1, .1, .1]), normed_label)
def test_normalize_label(self):
labels = np.array([1, 1, 1, 1, 1, 1, 1, 1, 1, 1])
normed_label = utils.normalize_labels(labels)
np.testing.assert_array_equal(
np.array([.1, .1, .1, .1, .1, .1, .1, .1, .1, .1]), normed_label)