def __init__(self,
data,
pathnameback=None,
ext='jpg',
count=None,
num_channels=3,
generate='image_and_mask',
iluminate=True, angle=45, translation=0.3, warp=0.1, factor=0.2,
transform_image=None,
transform_data=None,
):
"""Initialization
"""
self.data = data
self.bbackimage = pathnameback != None
self.databack = None
if count is None:
count = len(data)
if self.bbackimage:
pathnameback = os.path.expanduser( pathnameback )
self.databack = imutl.imageProvide( pathnameback, ext=ext )
self.num_classes=data.numclass
self.labels = data.labels
self.num_channels = num_channels
self.generate = generate
self.ren = Generator( iluminate, angle, translation, warp, factor )
self.count=count
self.transform_image = transform_image
self.transform_data = transform_data
def test_dataset_generator():
data = FactoryDataset.factory(pathname=os.path.expanduser('~/.datasets/'),
name=FactoryDataset.ck,
subset=FactoryDataset.training,
download=True)
ren = Generator()
img, y = data[np.random.randint(len(data))]
img = np.stack((img, img, img), axis=2)
idx = 1
pathname = os.path.expanduser('~/.datasets/coco')
data_back = imutl.imageProvide(pathname, ext='jpg')
back = data_back[(idx) % len(data_back)]
back = F.resize_image(back,
640,
1024,
resize_mode='crop',
interpolate_mode=cv2.INTER_LINEAR)
#back = back[:,:,0]
#back = np.random.randint(255, size=(640, 1024) )
print(img.shape, img.max())
print(back.shape, back.max())
image, image_ilu, mask, h = ren.generate(img, back)
print(image.shape, image.max())
print(mask.shape, mask.max())
def __init__(
self,
data,
pathnameback=None,
ext='jpg',
count=None,
num_channels=3,
generate='image_and_mask',
iluminate=True,
angle=45,
translation=0.3,
warp=0.1,
factor=0.2,
transform_image=None,
transform_data=None,
):
"""Initialization
:params
pathnameback: when it is none, background is white
count: trainiteration/testiteration, to generate more images with different background
"""
# Assign all self variables for later.
self.data = data
self.bbackimage = pathnameback != None
self.databack = None
if count is None:
count = len(data)
# If the user gives us a place to save these images, do so.
if self.bbackimage:
pathnameback = os.path.expanduser(pathnameback)
self.databack = imutl.imageProvide(pathnameback, ext=ext)
self.num_classes = data.numclass
self.labels = data.labels
self.num_channels = num_channels
self.generate = generate
self.ren = Generator(iluminate, angle, translation, warp, factor)
self.count = count
self.transform_image = transform_image
self.transform_data = transform_data
def test_dataset_generator():
data = FactoryDataset.factory(pathname='~/.datasets/',
name=FactoryDataset.bu3dfe,
subset=FactoryDataset.training,
download=True)
ren = Generator()
img, y = data[np.random.randint(len(data))]
img = np.stack((img, img, img), axis=2)
idx = 1
pathname = os.path.expanduser('~/.datasets/photo')
data_back = imutl.imageProvide(pathname, ext='jpg')
back = data_back[(idx) % len(data_back)]
back = F.resize_image(back,
640,
1024,
resize_mode='crop',
interpolate_mode=cv2.INTER_LINEAR)
#back = back[:,:,0]
#back = np.random.randint(255, size=(640, 1024) )
print(img.shape, img.max())
print(back.shape, back.max())
image, mask = ren.generate(img, back)
print(image.shape, image.max())
print(mask.shape, mask.max())
plt.figure()
plt.subplot(121)
plt.imshow(image.mean(axis=2), cmap='gray')
plt.subplot(122)
plt.imshow(mask[:, :, 0])
plt.show()
def __init__(self, pathname, ext, num_channels=1, transform=None ):
self.data = imageProvide(pathname, ext )
self.transform = transform
self.num_channels = num_channels
