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.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 data_prepare(data_root):
'''
Make a vector of weights for each image in the dataset, based
on class frequency. The returned vector of weights can be used
to create a WeightedRandomSampler for a DataLoader to have
class balancing when sampling for a training batch.
images - torchvisionDataset.imgs
nclasses - len(torchvisionDataset.classes)
https://discuss.pytorch.org/t/balanced-sampling-between-classes-with-torchvision-dataloader/2703/3
'''
count = []
images_data = []
images_label = []
class_file_list = os.listdir(data_root)
for i in tqdm.tqdm(range(len(class_file_list))):
images_path = os.listdir(os.path.join(data_root, class_file_list[i]))
count_value = 0
for image_path in images_path:
images_data.append(
vision.image_load(data_root + '/' + class_file_list[i] + '/' +
image_path,
backend='cv2'))
images_label.append(i)
count_value += 1
count.append(count_value)
num_classes = len(class_file_list)
num_sample = len(images_label)
weight_per_class = [0.] * num_classes
for i in tqdm.tqdm(range(num_classes)):
weight_per_class[i] = 1 / (num_classes * count[i])
weight = [0] * num_sample
for idx, val in enumerate(images_label):
weight[idx] = weight_per_class[images_label[idx]]
return weight, images_data, images_label, num_classes
def data_reader():
# 数据读取器，这里要单独写个
data_root = 'data/Casia_maxpy_clean'
images_data = []
images_label = []
batch_size = 128
count_value = 0
class_file_list = os.listdir(data_root)
for i in tqdm.tqdm(range(len(class_file_list)),ncols=80):
images_path = os.listdir(os.path.join(data_root, class_file_list[i]))
for image_path in images_path:
images_data.append(
vision.image_load(data_root + '/' + class_file_list[i] + '/' + image_path, backend='cv2'))
images_label.append(i)
count_value += 1
print(count_value)
assert len(images_data) == len(images_label)
def reader():
for i in range(int(len(images_data)/batch_size)-1):
data = images_data[i*batch_size:(i+1)*batch_size]
data = np.array(data)
data = np.transpose(data,(0,3, 1, 2))
data = (data - 127.5) / 127.5
yield data
return reader
def test_image_load(self):
fake_img = Image.fromarray((np.random.random(
(32, 32, 3)) * 255).astype('uint8'))
path = 'temp.jpg'
fake_img.save(path)
set_image_backend('pil')
pil_img = image_load(path).convert('RGB')
print(type(pil_img))
set_image_backend('cv2')
np_img = image_load(path)
os.remove(path)
def data_prepare(self):
data_root = self.data_root
images_data = []
images_label = []
count_value = 0
class_file_list = os.listdir(self.data_root)
for i in tqdm.tqdm(range(len(class_file_list)), ncols=80):
images_path = os.listdir(
os.path.join(self.data_root, class_file_list[i]))
for image_path in images_path:
images_data.append(
vision.image_load(data_root + '/' + class_file_list[i] +
'/' + image_path,
backend='cv2'))
images_label.append(i)
count_value += 1
print(count_value)
assert len(images_data) == len(images_label)
return images_data, images_label
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)