def transform(x,y,crop_range,rot_range,shear_range,zoom_range,t):
if t == False: # If t is set to false the input is only cropped
crop_type = np.random.randint(0,5,1)[0] # Randomly crop image from either center or a corner.
x_new = SpecialCrop((crop_range),crop_type=crop_type)(x)
y_new = SpecialCrop((crop_range),crop_type=crop_type)(y)
else:
rot = RandomRotate(rot_range,lazy=True)(x)
shear = RandomShear(shear_range,lazy=True)(x)
zoom = RandomZoom(zoom_range,lazy=True)(x)
flip = RandomFlip(v=True,p = np.random.randint(0,2,1)[0])# Images and label is flipped with 0.5 prob.
crop_type = np.random.randint(0,5,1)[0]
x_new = SpecialCrop((crop_range),crop_type=crop_type)(x)
y_new = SpecialCrop((crop_range),crop_type=crop_type)(y)
x_new = th_affine2d(x_new,rot)
y_new = th_affine2d(y_new,rot)
x_new = th_affine2d(x_new,shear)
y_new = th_affine2d(y_new,shear)
x_new = th_affine2d(x_new,zoom)
y_new = th_affine2d(y_new,zoom)
x_new = flip(x_new)
y_new = flip(y_new)
return AddChannel()(x_new), AddChannel()(y_new) # Add channel for concatenating batch.
def cropBox(img, ul, br, resH, resW):
ul = ul.int()
br = br.int()
lenH = max(br[1] - ul[1], (br[0] - ul[0]) * resH / resW)
lenW = lenH * resW / resH
if img.dim() == 2:
img = img[np.newaxis, :]
newDim = torch.IntTensor((img.size(0), int(lenH), int(lenW)))
newImg = img[:, ul[1]:, ul[0]:].clone()
# Crop and Padding
size = torch.IntTensor((int(br[1] - ul[1]), int(br[0] - ul[0])))
newImg = SpecialCrop(size, 1)(newImg)
newImg = Pad(newDim)(newImg)
# Resize to output
v_Img = torch.autograd.Variable(newImg)
v_Img = torch.unsqueeze(v_Img, 0)
# newImg = F.upsample_bilinear(v_Img, size=(int(resH), int(resW))).data[0]
if torch.__version__ == '0.4.0a0+32f3bf7' or torch.__version__ == '0.4.0':
newImg = F.upsample(v_Img,
size=(int(resH), int(resW)),
mode='bilinear',
align_corners=True).data[0]
else:
newImg = F.interpolate(v_Img,
size=(int(resH), int(resW)),
mode='bilinear',
align_corners=True).data[0]
return newImg
def cropBox(img, up_left, bottom_right, target_height, target_width):
up_left = up_left.int()
bottom_right = bottom_right.int()
curr_height = max(bottom_right[1] - up_left[1],
(bottom_right[0] - up_left[0]) * target_height /
target_width)
curr_width = curr_height * target_width / target_height
if img.dim() == 2:
img = img[np.newaxis, :]
new_dim = torch.IntTensor((img.size(0), int(curr_height), int(curr_width)))
new_img = img[:, up_left[1]:, up_left[0]:]
# crop and padding
size = torch.IntTensor(
(bottom_right[1] - up_left[1], bottom_right[0] - up_left[0]))
new_img = SpecialCrop(size, 1)(new_img)
new_img = Pad(new_dim)(new_img)
# resize to output
v_img = torch.unsqueeze(new_img, 0)
# newImg = F.upsample_bilinear(v_Img, size=(int(resH), int(resW))).data[0]
new_img = F.upsample(v_img,
size=(int(target_height), int(target_width)),
mode='bilinear',
align_corners=True).data[0]
return new_img
def cropBox(img, ul, br, resH, resW):
ul = ul.int() # xmin, ymin
br = br.int() # xmax, ymax
lenH = max(br[1] - ul[1], (br[0] - ul[0]) * resH / resW)
lenW = lenH * resW / resH
if img.dim() == 2:
img = img[np.newaxis, :]
newDim = torch.IntTensor((img.size(0), int(lenH), int(lenW)))
newImg = img[:, ul[1]:, ul[0]:]
# Crop and Padding
size = torch.IntTensor((br[1] - ul[1], br[0] - ul[0]))
newImg = SpecialCrop(size, 1)(newImg)
newImg = Pad(newDim)(newImg)
# Resize to output
# batch = 0, channel = img.size(0), h = int(lenH), w = int(lenW)
v_Img = torch.unsqueeze(newImg, 0)
# newImg = F.upsample_bilinear(v_Img, size=(int(resH), int(resW))).data[0]
newImg = F.upsample(v_Img, size=(int(resH), int(resW)),
mode='bilinear', align_corners=True).data[0]
return newImg
def SpecialCrop_setup():
tforms = {}
tforms['specialcrop_0_1010'] = SpecialCrop((10, 10), 0)
tforms['specialcrop_0_510'] = SpecialCrop((5, 10), 0)
tforms['specialcrop_0_105'] = SpecialCrop((10, 5), 0)
tforms['specialcrop_0_99'] = SpecialCrop((9, 9), 0)
tforms['specialcrop_0_79'] = SpecialCrop((7, 9), 0)
tforms['specialcrop_0_97'] = SpecialCrop((9, 7), 0)
tforms['specialcrop_1_1010'] = SpecialCrop((10, 10), 1)
tforms['specialcrop_1_510'] = SpecialCrop((5, 10), 1)
tforms['specialcrop_1_105'] = SpecialCrop((10, 5), 1)
tforms['specialcrop_1_99'] = SpecialCrop((9, 9), 1)
tforms['specialcrop_1_79'] = SpecialCrop((7, 9), 1)
tforms['specialcrop_1_97'] = SpecialCrop((9, 7), 1)
tforms['specialcrop_2_1010'] = SpecialCrop((10, 10), 2)
tforms['specialcrop_2_510'] = SpecialCrop((5, 10), 2)
tforms['specialcrop_2_105'] = SpecialCrop((10, 5), 2)
tforms['specialcrop_2_99'] = SpecialCrop((9, 9), 2)
tforms['specialcrop_2_79'] = SpecialCrop((7, 9), 2)
tforms['specialcrop_2_97'] = SpecialCrop((9, 7), 2)
tforms['specialcrop_3_1010'] = SpecialCrop((10, 10), 3)
tforms['specialcrop_3_510'] = SpecialCrop((5, 10), 3)
tforms['specialcrop_3_105'] = SpecialCrop((10, 5), 3)
tforms['specialcrop_3_99'] = SpecialCrop((9, 9), 3)
tforms['specialcrop_3_79'] = SpecialCrop((7, 9), 3)
tforms['specialcrop_3_97'] = SpecialCrop((9, 7), 3)
tforms['specialcrop_4_1010'] = SpecialCrop((10, 10), 4)
tforms['specialcrop_4_510'] = SpecialCrop((5, 10), 4)
tforms['specialcrop_4_105'] = SpecialCrop((10, 5), 4)
tforms['specialcrop_4_99'] = SpecialCrop((9, 9), 4)
tforms['specialcrop_4_79'] = SpecialCrop((7, 9), 4)
tforms['specialcrop_4_97'] = SpecialCrop((9, 7), 4)
return tforms
