def prepare(filepath, mean_image, h, w):
width = w
height = h
img_array = cv2.imread(filepath) # read in the image
img_array = imgproc.toUINT8(img_array)
img_array = imgproc.process_image(img_array, (height, width))
img_array = np.float32(img_array)
new_array = cv2.resize(img_array, (width, height)) # resize image to match model's expected sizing
res = new_array.reshape(-1, height, width, 3)
res = res - mean_image
return res # return the image with shaping that TF wants.
def read_image(filename, number_of_channels):
""" read_image using skimage
The output is a 3-dim image [H, W, C]
"""
if number_of_channels == 1:
image = io.imread(filename, as_gray=True)
image = imgproc.toUINT8(image)
assert (len(image.shape) == 2)
image = np.expand_dims(image, axis=2) #H,W,C
assert (len(image.shape) == 3 and image.shape[2] == 1)
elif number_of_channels == 3:
image = io.imread(filename)
if (len(image.shape) == 2):
image = color.gray2rgb(image)
image = imgproc.toUINT8(image)
assert (len(image.shape) == 3)
else:
raise ValueError("number_of_channels must be 1 or 3")
if not os.path.exists(filename):
raise ValueError(filename + " does not exist!")
return image
def draw_result(self, filenames):
w = 1000
h = 1000
w_i = np.int(w / 10)
h_i = np.int(h / 10)
image_r = np.zeros((w, h, 3), dtype=np.uint8) + 255
x = 0
y = 0
for i, filename in enumerate(filenames):
pos = (i * w_i)
x = pos % w
y = np.int(np.floor(pos / w)) * h_i
image = self.read_image(filename)
image = imgproc.toUINT8(trans.resize(image, (h_i, w_i)))
image_r[y:y + h_i, x:x + w_i, :] = image
return image_r
def prepare(filepath, mean_image, h, w):
width = w
height = h
img_array = cv2.imread(
filepath,
cv2.IMREAD_UNCHANGED,
) # read in the image, convert to grayscale
img_array = imgproc.toUINT8(img_array)
img_array = imgproc.process_image(img_array, (height, width))
#cv2.imshow("window", img_array)
#cv2.waitKey()
img_array = np.float32(img_array)
new_array = cv2.resize(
img_array,
(width, height)) # resize image to match model's expected sizing
res = new_array.reshape(-1, height, width, 3)
res = res - mean_image
return res # return the image with shaping that TF wants.