Spaces:
Sleeping
Sleeping
File size: 3,111 Bytes
76d12f3 | 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 |
def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height,
image_size):
best_ratio_diff = float('inf')
best_ratio = (1, 1)
area = width * height
for ratio in target_ratios:
target_aspect_ratio = ratio[0] / ratio[1]
ratio_diff = abs(aspect_ratio - target_aspect_ratio)
if ratio_diff < best_ratio_diff:
best_ratio_diff = ratio_diff
best_ratio = ratio
elif ratio_diff == best_ratio_diff:
if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:
best_ratio = ratio
return best_ratio
def dynamic_preprocess(image,
min_num=1,
max_num=6,
image_size=448,
use_thumbnail=False):
orig_width, orig_height = image.size
aspect_ratio = orig_width / orig_height
target_ratios = {(i, j)
for n in range(min_num, max_num + 1)
for i in range(1, n + 1) for j in range(1, n + 1)
if i * j <= max_num and i * j >= min_num}
target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])
target_aspect_ratio = find_closest_aspect_ratio(aspect_ratio,
target_ratios, orig_width,
orig_height, image_size)
target_width = image_size * target_aspect_ratio[0]
target_height = image_size * target_aspect_ratio[1]
blocks = target_aspect_ratio[0] * target_aspect_ratio[1]
resized_img = image.resize((target_width, target_height))
processed_images = []
for i in range(blocks):
box = ((i % (target_width // image_size)) * image_size,
(i // (target_width // image_size)) * image_size,
((i % (target_width // image_size)) + 1) * image_size,
((i // (target_width // image_size)) + 1) * image_size)
split_img = resized_img.crop(box)
processed_images.append(split_img)
assert len(processed_images) == blocks
if use_thumbnail and len(processed_images) != 1:
thumbnail_img = image.resize((image_size, image_size))
processed_images.append(thumbnail_img)
return processed_images
import re
def find_seg_indices(text):
all_seg_indices = [m.start() for m in re.finditer(r'\[SEG\]', text)]
answer_spans = [(m.start(), m.end()) for m in re.finditer(r'<answer>.*?</answer>', text, re.DOTALL)]
if len(answer_spans) == 0:
return [], []
if len(answer_spans) > 1:
print(f"Warning: There should be only one <answer> tag in the text. {text}")
answer_span = answer_spans[0]
start, end = answer_span
seg_indices_in_reason = []
seg_indices_in_answer = []
for idx, seg_ind in enumerate(all_seg_indices):
if start <= seg_ind < end:
seg_indices_in_answer.append(idx)
elif seg_ind < start:
seg_indices_in_reason.append(idx)
else:
continue
return seg_indices_in_reason, seg_indices_in_answer |