def augument(data_path, label, image_name, save_path, size=224, training = True):
image_path = os.path.join(data_path, image_name)
(name, extension) = splitfilename(image_name)
extension = extension.lower()
if extension not in IMG_EXTS:
print('filered image: %s' % image_name)
return
try:
img = image.imdecode(open(image_path, 'rb').read()).astype('float32')
except Exception as ex:
print("error: ", ex)
return
if label is not None:
label_path = os.path.join(save_path, label)
else:
label_path = save_path
mkdir(label_path)
if training:
aug1 = image.HorizontalFlipAug(0.5)
aug2 = image.HorizontalFlipAug(.5)
img = image.resize_short(img, size=384, interp=2)
center_crop, _ = image.center_crop(img, size=(size, size))
new_name = "%s_%s%s" % (name, "0", extension)
cv.imwrite(os.path.join(label_path, new_name), center_crop.asnumpy())
random_crop, _ = image.random_crop(img, size=(size, size))
new_name = "%s_%s%s" % (name, "1", extension)
cv.imwrite(os.path.join(label_path, new_name), random_crop.asnumpy())
random_crop, _ = image.random_crop(img, size=(size, size))
new_name = "%s_%s%s" % (name, "2", extension)
cv.imwrite(os.path.join(label_path, new_name), random_crop.asnumpy())
random_crop, _ = image.random_crop(img, size=(size, size))
new_name = "%s_%s%s" % (name, "3", extension)
cv.imwrite(os.path.join(label_path, new_name), random_crop.asnumpy())
img_aug1 = aug1(random_crop).clip(0,255)
new_name = "%s_%s%s" % (name, "4", extension)
cv.imwrite(os.path.join(label_path, new_name), img_aug1.asnumpy())
img_aug2 = aug2(center_crop).clip(0, 255)
new_name = "%s_%s%s" % (name, "5", extension)
cv.imwrite(os.path.join(label_path, new_name), img_aug2.asnumpy())
img_resize = image.imresize(img, w=size, h=size, interp=2)
new_name = "%s_%s%s" % (name, "6", extension)
cv.imwrite(os.path.join(label_path, new_name), img_resize.asnumpy())
else:
img = image.resize_short(img, size=size)
img, _ = image.center_crop(img, size=(size, size))
new_name = "%s%s" % (name, extension)
cv.imwrite(os.path.join(label_path, new_name), img.asnumpy())
def pre_processing(self, img_path):
"""
对图片进行处理，先按照高度进行resize，resize之后如果宽度不足指定宽度，就补黑色像素，否则就强行缩放到指定宽度
:param img_path: 图片地址
:return:
"""
data_augment = False
if self.phase == 'train' and np.random.rand() > 0.5:
data_augment = True
if data_augment:
img_h = 40
img_w = 340
else:
img_h = self.img_h
img_w = self.img_w
img = image.imdecode(
open(img_path, 'rb').read(), 1 if self.img_channel == 3 else 0)
h, w = img.shape[:2]
ratio_h = float(img_h) / h
new_w = int(w * ratio_h)
if new_w < img_w:
img = image.imresize(img, w=new_w, h=img_h)
step = nd.zeros((img_h, img_w - new_w, self.img_channel),
dtype=img.dtype)
img = nd.concat(img, step, dim=1)
else:
img = image.imresize(img, w=img_w, h=img_h)
if data_augment:
img, _ = image.random_crop(img, (self.img_w, self.img_h))
return img
def __call__(self, img: np.ndarray):
"""
对图片进行处理，先按照高度进行resize，resize之后如果宽度不足指定宽度，就补黑色像素，否则就强行缩放到指定宽度
:param img_path: 图片地址
:return:
"""
data_augment = False
if self.phase == 'train' and np.random.rand() > 0.5:
data_augment = True
if data_augment:
img_h = 40
img_w = 340
else:
img_h = self.img_h
img_w = self.img_w
h, w = img.shape[:2]
ratio_h = float(img_h) / h
new_w = int(w * ratio_h)
if new_w < img_w and self.pad:
img = cv2.resize(img, (new_w, img_h))
if len(img.shape) == 2:
img = np.expand_dims(img, 3)
step = np.zeros((img_h, img_w - new_w, img.shape[-1]), dtype=img.dtype)
img = np.column_stack((img, step))
else:
img = cv2.resize(img, (img_w, img_h))
if data_augment:
img = nd.array(img)
img, _ = image.random_crop(img, (self.img_w, self.img_h))
img = img.asnumpy()
return img
def forward(self, x):
if self.pad:
x_pad = np.pad(x.asnumpy(),
self.pad,
mode='constant',
constant_values=0)
return image.random_crop(nd.array(x_pad), *self._args)[0]
def forward(self, x):
if not isinstance(self.size, (numbers.Number, tuple)):
raise TypeError('Got inappropriate size arg')
if isinstance(self.size, numbers.Number):
size = (self.size, self.size)
else:
size = self.size
return image.random_crop(x, size)[0]
def load_and_crop_image(root, files, crop_size):
imgs = []
for file in files:
fp = os.path.join(root, file)
img = image.imread(fp)
h, w = img.shape[:2]
ratio = h / w
if crop_size[0] / crop_size[1] < ratio:
w = crop_size[1]
h = w * ratio
else:
h = crop_size[0]
w = h / ratio
image.imresize(img, int(w), int(h))
img, rect = image.random_crop(img, crop_size)
imgs.append(img)
return imgs
def forward(self, x):
return image.random_crop(x, *self._args)[0]
def rand_crop(data, label, shape):
data, rect = image.random_crop(data, shape)
label = image.fixed_crop(label, *rect)
return data, label
def __voc_rand_crop(self, feature, label, height, width):
feature, rect = image.random_crop(feature, (width, height))
label = image.fixed_crop(label, *rect)
return feature, label
def voc_rand_crop(feature, label, height, width):
"""Random cropping for images of the Pascal VOC2012 Dataset."""
feature, rect = image.random_crop(feature, (width, height))
label = image.fixed_crop(label, *rect)
return feature, label
def forward(self, x):
if self.pad:
x_pad = np.pad(x.asnumpy(), self.pad,
mode='constant', constant_values=0)
return image.random_crop(nd.array(x_pad), *self._args)[0]
def rand_crop(data, label, height, width):
data, rect = random_crop(data, (width, height))
label = fixed_crop(label, *rect)
return data, label
def voc_rand_crop(img, label, height, width):
img, rect = image.random_crop(img, (width, height))
label = image.fixed_crop(label, *rect)
return img, label
def RandomCrop(data, label, height, width):
data, rect = image.random_crop(data,(height, width))
label = image.fixed_crop(label,*rect)
return data, label
def voc_rand_crop(data, label, height, width):
"""Random cropping for images of the Pascal VOC2012 Dataset."""
data, rect = image.random_crop(data, (width, height))
label = image.fixed_crop(label, *rect)
return data, label
def rand_crop(self, data, label, height, width):
data, rect = image.random_crop(data, (width, height))
label = image.fixed_crop(label, *rect)
return data, label
def voc_rand_crop(feature, label, height, width):
"""Randomly crop for both feature and label images."""
feature, rect = image.random_crop(feature, (width, height))
label = image.fixed_crop(label, *rect)
return feature, label
