Spaces:
Runtime error
Runtime error
File size: 3,257 Bytes
c5801c1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
import random
from PIL import Image
import numpy as np
def center_crop_arr(pil_image, image_size):
"""
Center cropping implementation from ADM.
https://github.com/openai/guided-diffusion/blob/8fb3ad9197f16bbc40620447b2742e13458d2831/guided_diffusion/image_datasets.py#L126
"""
while min(*pil_image.size) >= 2 * image_size:
pil_image = pil_image.resize(tuple(x // 2 for x in pil_image.size), resample=Image.BOX)
scale = image_size / min(*pil_image.size)
pil_image = pil_image.resize(tuple(round(x * scale) for x in pil_image.size), resample=Image.BICUBIC)
arr = np.array(pil_image)
crop_y = (arr.shape[0] - image_size) // 2
crop_x = (arr.shape[1] - image_size) // 2
return Image.fromarray(arr[crop_y : crop_y + image_size, crop_x : crop_x + image_size])
def center_crop(pil_image, crop_size):
while pil_image.size[0] >= 2 * crop_size[0] and pil_image.size[1] >= 2 * crop_size[1]:
pil_image = pil_image.resize(tuple(x // 2 for x in pil_image.size), resample=Image.BOX)
scale = max(crop_size[0] / pil_image.size[0], crop_size[1] / pil_image.size[1])
pil_image = pil_image.resize(tuple(round(x * scale) for x in pil_image.size), resample=Image.BICUBIC)
# crop_left = random.randint(0, pil_image.size[0] - crop_size[0])
# crop_upper = random.randint(0, pil_image.size[1] - crop_size[1])
crop_left = (pil_image.size[0] - crop_size[0]) // 2
crop_upper = (pil_image.size[1] - crop_size[1]) // 2
crop_right = crop_left + crop_size[0]
crop_lower = crop_upper + crop_size[1]
return pil_image.crop(box=(crop_left, crop_upper, crop_right, crop_lower))
def var_center_crop(pil_image, crop_size_list, random_top_k=4):
w, h = pil_image.size
rem_percent = [min(cw / w, ch / h) / max(cw / w, ch / h) for cw, ch in crop_size_list]
crop_size = random.choice(
sorted(((x, y) for x, y in zip(rem_percent, crop_size_list)), reverse=True)[:random_top_k]
)[1]
return center_crop(pil_image, crop_size)
def var_center_crop_128(pil_image, crop_size_list, random_top_k=4):
w, h = pil_image.size
rem_percent = [min(cw / w, ch / h) / max(cw / w, ch / h) for cw, ch in crop_size_list]
crop_size = random.choice(
sorted(((x, y) for x, y in zip(rem_percent, crop_size_list)), reverse=True)[:random_top_k]
)[1]
breakpoint()
return center_crop(pil_image, (((w//128)*128), ((h//128)*128)))
def generate_crop_size_list(num_patches, patch_size, max_ratio=4.0):
assert max_ratio >= 1.0
crop_size_list = []
wp, hp = num_patches, 1
while wp > 0:
if max(wp, hp) / min(wp, hp) <= max_ratio:
if ((wp * patch_size)//32) % 2 == 0 and ((hp * patch_size)//32) % 2 == 0:
crop_size_list.append((wp * patch_size, hp * patch_size))
if (hp + 1) * wp <= num_patches:
hp += 1
else:
wp -= 1
return crop_size_list
def to_rgb_if_rgba(img: Image.Image):
if img.mode.upper() == "RGBA":
rgb_img = Image.new("RGB", img.size, (255, 255, 255))
rgb_img.paste(img, mask=img.split()[3]) # 3 is the alpha channel
return rgb_img
elif img.mode.upper() == "P":
return img.convert('RGB')
else:
return img
|