def __getitem__(self, idx):
idx1, idx2, idx3 = self.triplets[idx]
img1, lab1 = self.data[idx1]
img2, lab2 = self.data[idx2]
img3, lab3 = self.data[idx3]
img1 = np.array(img1)
img2 = np.array(img2)
img3 = np.array(img3)
img1 = utility.to_channels(img1, self.num_channels)
img2 = utility.to_channels(img2, self.num_channels)
img3 = utility.to_channels(img3, self.num_channels)
lab1 = utility.to_one_hot(lab1, self.numclass)
lab2 = utility.to_one_hot(lab2, self.numclass)
lab3 = utility.to_one_hot(lab3, self.numclass)
a = ObjectImageAndLabelTransform(img1, lab1)
b = ObjectImageAndLabelTransform(img2, lab2)
c = ObjectImageAndLabelTransform(img3, lab3)
if self.transform is not None:
a = self.transform(a)
b = self.transform(b)
c = self.transform(c)
return {'a': a.to_dict(), 'b': b.to_dict(), 'c': c.to_dict()}
def __getitem__(self, idx):
image, label = self.data[idx]
image = np.array(image)
image = utility.to_channels(image, self.num_channels)
label = utility.to_one_hot(label, self.numclass)
obj = ObjectImageAndLabelTransform( image, label )
if self.transform:
sample = self.transform( obj )
return obj.to_dict()
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 __getitem__(self, idx):
idx = idx % len(self.data)
image, label = self.data[idx]
image = np.array(image)
image = utility.to_channels(image, self.num_channels)
label = utility.to_one_hot(label,
self.numclass) #no one-hot haixuanguo
# parse image and label to tensor
obj = ObjectImageAndLabelTransform(image, label)
# transform data
if self.transform:
obj = self.transform(obj)
return obj.to_dict()
def __getitem__(self, idx):
idx = idx % self.numclass
class_index = self.labels_index[idx]
n = len(class_index)
idx = class_index[random.randint(0, n - 1)]
image, label = self.data[idx]
image = np.array(image)
image = utility.to_channels(image, self.num_channels)
label = utility.to_one_hot(label, self.numclass)
obj = ObjectImageAndLabelTransform(image, label)
if self.transform:
obj = self.transform(obj)
return obj.to_dict()
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_label':
_, image_ilu, _, _ = self.ren.generate( image, back )
#image_ilu, _, _, _ = self.ren.generate( image, back )
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)
label = utility.to_one_hot( int(label), self.data.numclass )
obj = ObjectImageAndLabelTransform( image_ilu, label )
if self.transform_image:
obj = self.transform_image( obj )
return obj.to_dict()
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