def resize( image, height=128, width=128, interpolate_mode=cv2.INTER_LANCZOS4 ):
return F.resize_image(image,
height=height, width=width,
resize_mode='square',
padding_mode=cv2.BORDER_CONSTANT,
interpolate_mode=interpolate_mode,
)
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 __getitem__(self, idx):
# read image
image, label = self.data[(idx) % len(self.data)]
#A,A_inv = F.compute_norm_mat( image.shape[1], image.shape[0] )
#image = F.equalization(image,A,A_inv)
image = utility.to_channels(image, self.num_channels)
# read background
if self.bbackimage:
idxk = random.randint(1, len(self.databack) - 1)
back = self.databack[idxk]
back = F.resize_image(back,
640,
1024,
resize_mode='crop',
interpolate_mode=cv2.INTER_LINEAR)
back = utility.to_channels(back, self.num_channels)
else:
back = np.ones((640, 1024, 3), dtype=np.uint8) * 255
if self.generate == 'image':
obj = ObjectImageTransform(image)
elif self.generate == 'image_and_mask':
image_org, image_ilu, mask, h = self.ren.generate(image, back)
image_org = utility.to_gray(image_org.astype(np.uint8))
image_org = utility.to_channels(image_org, self.num_channels)
image_org = image_org.astype(np.uint8)
image_ilu = utility.to_gray(image_ilu.astype(np.uint8))
image_ilu = utility.to_channels(image_ilu, self.num_channels)
image_ilu = image_ilu.astype(np.uint8)
mask = mask[:, :, 0]
mask_t = np.zeros((mask.shape[0], mask.shape[1], 2))
mask_t[:, :, 0] = (mask == 0).astype(np.uint8) # 0-backgraund
mask_t[:, :, 1] = (mask == 1).astype(np.uint8)
obj_image = ObjectImageTransform(image_org.copy())
obj_data = ObjectImageAndMaskMetadataTransform(
image_ilu.copy(), mask_t, np.concatenate(
([label], h), axis=0)) #np.array([label])
else:
assert (False)
if self.transform_image:
obj_image = self.transform_image(obj_image)
if self.transform_data:
obj_data = self.transform_data(obj_data)
x_img, y_mask, y_lab = obj_data.to_value()
x_org = obj_image.to_value()
return x_org, x_img, y_mask, y_lab
def __getitem__(self, idx):
# read image
image, label = self.data[(idx) % len(self.data)]
image = utility.to_channels(image, self.num_channels)
# read background
if self.bbackimage:
idxk = random.randint(1, len(self.databack) - 1)
back = self.databack[idxk] #(idx)%len(self.databack)
back = F.resize_image(back,
640,
1024,
resize_mode='crop',
interpolate_mode=cv2.INTER_LINEAR)
back = utility.to_channels(back, self.num_channels)
else:
back = np.ones((640, 1024, 3), dtype=np.uint8) * 255
if self.generate == 'image':
obj = ObjectImageTransform(image)
elif self.generate == 'image_and_label':
_, image, _ = self.ren.generate(image, back)
image = utility.to_gray(image.astype(np.uint8))
image_t = utility.to_channels(image, self.num_channels)
image_t = image_t.astype(np.uint8)
label = utility.to_one_hot(int(label), self.data.numclass)
obj = ObjectImageAndLabelTransform(image_t, label)
elif self.generate == 'image_and_mask':
_, image, mask = self.ren.generate(image, back)
image = utility.to_gray(image.astype(np.uint8))
image_t = utility.to_channels(image, self.num_channels)
image_t = image_t.astype(np.uint8)
#print( image_t.shape, image_t.min(), image_t.max(), flush=True )
#assert(False)
mask = mask[:, :, 0]
mask_t = np.zeros((mask.shape[0], mask.shape[1], 2))
mask_t[:, :, 0] = (mask == 0).astype(np.uint8) # backgraund
mask_t[:, :, 1] = (mask == 1).astype(np.uint8)
obj = ObjectImageAndMaskMetadataTransform(image_t, mask_t,
np.array([label]))
else:
assert (False)
if self.transform:
obj = self.transform(obj)
return obj.to_dict()
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()