def test_resize(self):
np_img = (np.zeros([28, 24, 3])).astype('uint8')
pil_img = Image.fromarray(np_img)
np_reseized_img = F.resize(np_img, 40)
pil_reseized_img = F.resize(pil_img, 40)
np.testing.assert_almost_equal(np_reseized_img,
np.array(pil_reseized_img))
gray_img = (np.zeros([28, 32])).astype('uint8')
gray_resize_img = F.resize(gray_img, 40)
def test_errors(self):
with self.assertRaises(TypeError):
F.to_tensor(1)
with self.assertRaises(ValueError):
fake_img = Image.fromarray(
(np.random.rand(28, 28, 3) * 255).astype('uint8'))
F.to_tensor(fake_img, data_format=1)
with self.assertRaises(TypeError):
fake_img = Image.fromarray(
(np.random.rand(28, 28, 3) * 255).astype('uint8'))
F.resize(fake_img, '1')
with self.assertRaises(TypeError):
F.resize(1, 1)
with self.assertRaises(TypeError):
F.pad(1, 1)
with self.assertRaises(TypeError):
F.crop(1, 1, 1, 1, 1)
with self.assertRaises(TypeError):
F.hflip(1)
with self.assertRaises(TypeError):
F.vflip(1)
with self.assertRaises(TypeError):
F.adjust_brightness(1, 0.1)
with self.assertRaises(TypeError):
F.adjust_contrast(1, 0.1)
with self.assertRaises(TypeError):
F.adjust_hue(1, 0.1)
with self.assertRaises(TypeError):
F.adjust_saturation(1, 0.1)
with self.assertRaises(TypeError):
F.rotate(1, 0.1)
with self.assertRaises(TypeError):
F.to_grayscale(1)
with self.assertRaises(ValueError):
set_image_backend(1)
with self.assertRaises(ValueError):
image_load('tmp.jpg', backend=1)
def _apply_image(self, img):
if self.param is None:
self.param = self._get_param(img)
i, j, h, w = self.param
cropped_img = F.crop(img, i, j, h, w)
return F.resize(cropped_img, self.size, self.interpolation)
def __call__(self, inputs):
"""inputs must be (lq_img, gt_img)"""
scale = self.scale
lq_patch_size = self.gt_patch_size // scale
lq = inputs[0]
gt = inputs[1]
h_lq, w_lq, _ = lq.shape
h_gt, w_gt, _ = gt.shape
if h_gt != h_lq * scale or w_gt != w_lq * scale:
raise ValueError('scale size not match')
if h_lq < lq_patch_size or w_lq < lq_patch_size:
raise ValueError('lq size error')
# randomly choose top and left coordinates for lq patch
top = random.randint(0, h_lq - lq_patch_size)
left = random.randint(0, w_lq - lq_patch_size)
# crop lq patch
lq = lq[top:top + lq_patch_size, left:left + lq_patch_size, ...]
# crop corresponding gt patch
top_gt, left_gt = int(top * scale), int(left * scale)
gt = gt[top_gt:top_gt + self.gt_patch_size,
left_gt:left_gt + self.gt_patch_size, ...]
if self.scale_list and self.scale == 4:
lqx2 = F.resize(gt, (lq_patch_size * 2, lq_patch_size * 2),
'bicubic')
outputs = (lq, lqx2, gt)
return outputs
outputs = (lq, gt)
return outputs
def get_cluster_label(uint8_img, segments):
# get features from the first layers.
fextractor = FeatureExtractor()
paddle.enable_static()
feature = fextractor.forward(uint8_img).transpose((1, 2, 0))
paddle.disable_static()
img_size = (uint8_img.shape[1], uint8_img.shape[2])
feature = F.resize(feature, img_size)
X = extract_superpixel_features(feature, segments)
_, h_pre_models_kmeans = get_pre_models()
try:
kmeans_model = load_pickle_file(h_pre_models_kmeans)
except:
raise ValueError("NormLIME needs the KMeans model, where we provided a default one in "
"pre_models/kmeans_model.pkl.")
try:
cluster_labels = kmeans_model.predict(X)
except AttributeError:
from sklearn.metrics import pairwise_distances_argmin_min
cluster_labels, _ = pairwise_distances_argmin_min(X, kmeans_model.cluster_centers_)
return cluster_labels
def data_labels(file_path_list, predict_fn, batch_size):
print("Initialization for fast NormLIME: Computing each sample in the test list.")
_, h_pre_models_kmeans = get_pre_models()
kmeans_model = load_pickle_file(h_pre_models_kmeans)
num_features = len(kmeans_model.cluster_centers_)
y_labels = []
fextractor = FeatureExtractor()
x_data = []
tmp_imgs = []
for each_data_ in tqdm.tqdm(file_path_list):
image_show = read_image(each_data_) # todo: whether add resize_to, crop_to?
tmp_imgs.append(image_show)
paddle.enable_static()
feature = fextractor.forward(image_show).transpose((1, 2, 0))
paddle.disable_static()
img_size = (image_show.shape[1], image_show.shape[2])
feature = F.resize(feature, img_size)
segments = np.zeros(img_size, np.int32)
num_blocks = 10
height_per_i = segments.shape[0] // num_blocks + 1
width_per_i = segments.shape[1] // num_blocks + 1
for i in range(segments.shape[0]):
for j in range(segments.shape[1]):
segments[i, j] = i // height_per_i * num_blocks + j // width_per_i
X = extract_superpixel_features(feature, segments)
try:
cluster_labels = kmeans_model.predict(X)
except AttributeError:
from sklearn.metrics import pairwise_distances_argmin_min
cluster_labels, _ = pairwise_distances_argmin_min(X, kmeans_model.cluster_centers_)
x_data_i = np.zeros((num_features))
for c in cluster_labels:
x_data_i[c] = 1
x_data.append(x_data_i)
if len(tmp_imgs) == batch_size:
outputs = predict_fn(np.concatenate(tmp_imgs, axis=0))
y_labels.extend(outputs)
tmp_imgs = []
if len(tmp_imgs) > 0:
outputs = predict_fn(np.concatenate(tmp_imgs, axis=0))
y_labels.extend(outputs)
return x_data, y_labels
def test_resize(self):
np_img = (np.zeros([28, 24, 3]) * 255).astype('uint8')
pil_img = Image.fromarray(np_img)
tensor_img = F.to_tensor(pil_img, 'CHW') * 255
np_reseized_img = F.resize(np_img, 40)
pil_reseized_img = F.resize(pil_img, 40)
tensor_reseized_img = F.resize(tensor_img, 40)
tensor_reseized_img2 = F.resize(tensor_img, (46, 40))
np.testing.assert_almost_equal(np_reseized_img,
np.array(pil_reseized_img))
np.testing.assert_almost_equal(np_reseized_img,
tensor_reseized_img.numpy().transpose(
(1, 2, 0)),
decimal=3)
np.testing.assert_almost_equal(np_reseized_img,
tensor_reseized_img2.numpy().transpose(
(1, 2, 0)),
decimal=3)
gray_img = (np.zeros([28, 32])).astype('uint8')
gray_resize_img = F.resize(gray_img, 40)
def test_errors(self):
with self.assertRaises(TypeError):
F.to_tensor(1)
with self.assertRaises(ValueError):
fake_img = Image.fromarray(
(np.random.rand(28, 28, 3) * 255).astype('uint8'))
F.to_tensor(fake_img, data_format=1)
with self.assertRaises(ValueError):
fake_img = paddle.rand((3, 100, 100))
F.pad(fake_img, 1, padding_mode='symmetric')
with self.assertRaises(TypeError):
fake_img = paddle.rand((3, 100, 100))
F.resize(fake_img, {1: 1})
with self.assertRaises(TypeError):
fake_img = Image.fromarray(
(np.random.rand(28, 28, 3) * 255).astype('uint8'))
F.resize(fake_img, '1')
with self.assertRaises(TypeError):
F.resize(1, 1)
with self.assertRaises(TypeError):
F.pad(1, 1)
with self.assertRaises(TypeError):
F.crop(1, 1, 1, 1, 1)
with self.assertRaises(TypeError):
F.hflip(1)
with self.assertRaises(TypeError):
F.vflip(1)
with self.assertRaises(TypeError):
F.adjust_brightness(1, 0.1)
with self.assertRaises(TypeError):
F.adjust_contrast(1, 0.1)
with self.assertRaises(TypeError):
F.adjust_hue(1, 0.1)
with self.assertRaises(TypeError):
F.adjust_saturation(1, 0.1)
with self.assertRaises(TypeError):
F.affine('45')
with self.assertRaises(TypeError):
F.affine(45, translate=0.3)
with self.assertRaises(TypeError):
F.affine(45, translate=[0.2, 0.2, 0.3])
with self.assertRaises(TypeError):
F.affine(45, translate=[0.2, 0.2], scale=-0.5)
with self.assertRaises(TypeError):
F.affine(45, translate=[0.2, 0.2], scale=0.5, shear=10)
with self.assertRaises(TypeError):
F.affine(45, translate=[0.2, 0.2], scale=0.5, shear=[-10, 0, 10])
with self.assertRaises(TypeError):
F.affine(45,
translate=[0.2, 0.2],
scale=0.5,
shear=[-10, 10],
interpolation=2)
with self.assertRaises(TypeError):
F.affine(45,
translate=[0.2, 0.2],
scale=0.5,
shear=[-10, 10],
center=0)
with self.assertRaises(TypeError):
F.rotate(1, 0.1)
with self.assertRaises(TypeError):
F.to_grayscale(1)
with self.assertRaises(ValueError):
set_image_backend(1)
with self.assertRaises(ValueError):
image_load('tmp.jpg', backend=1)
def _apply_image(self, image):
return F.resize(image, self.params['taget_size'], self.interpolation)
def apply_image(self, img):
return F.resize(img, self.size, self.interpolation)
