动态分辨率技术允许模型根据输入图像的复杂度和处理需求,实时调整其处理的分辨率。在处理简单或者信息量较少的图像时,模型可能会采用较低的分辨率以减少计算量;在处理复杂或者细节丰富的图像时,模型则会采用更高的分辨率以捕获更多细节。
下面是 LLava-Next 中动态高分辨率的实现示意图,其实就是两个分支,一个是 split 切图,一个是 resize 直接对大图进行缩放,这是为了保留全局的语义信息。对于视觉编码模型的输入来说,动态高分辨率的切图比如切 4 张图,完了还要再加上 resize 的那张图,这样其实是 5 张图的输入。
从代码实现来说,下面的动态高分辨率的代码实现来自 InternVL2 的图片预处理,主要就是对动态高分辨率的处理,
# 忽略导入
IMAGENET_MEAN = (0.485, 0.456, 0.406)
IMAGENET_STD = (0.229, 0.224, 0.225)
def build_transform(input_size):
MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
transform = T.Compose([
T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
T.ToTensor(),
T.Normalize(mean=MEAN, std=STD)
])
return transform
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=12, image_size=448, use_thumbnail=False):
orig_width, orig_height = image.size
aspect_ratio = orig_width / orig_height
# calculate the existing image aspect ratio
target_ratios = set(
(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])
# find the closest aspect ratio to the target
target_aspect_ratio = find_closest_aspect_ratio(
aspect_ratio, target_ratios, orig_width, orig_height, image_size)
# calculate the target width and height
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]
# resize the image
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 the image
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
def load_image(image_file, input_size=448, max_num=12):
image = Image.open(image_file).convert('RGB')
transform = build_transform(input_size=input_size)
images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num)
pixel_values = [transform(image) for image in images]
pixel_values = torch.stack(pixel_values)
return pixel_values
这段代码其实就是主要就是两个过程,首先是寻找最接近的宽高比,也就是 find_closest_aspect_ratio
函数在做的事情,然后就是动态预处理,包括了切割和缩放,最后进行拼接,结束,等待送入视觉编码模型。
好了,以上分享了 多模态大模型中的动态高分辨率,希望我的分享能对你的学习有一点帮助。
好文章,需要你的鼓励
后来广为人知的“云上奥运”这一说法,正是从这一刻起走上历史舞台。云计算这一概念,也随之被越来越多的人所熟知。乘云科技CEO郝凯对此深有感受,因为在2017年春节过后不久,他的公司开始成为阿里云的合作伙伴,加入了滚滚而来的云计算大潮中。同一年,郝凯带领团队也第一次参加了阿里云的“双11”活动,实现了800万元的销售业绩。
随着各行各业数字化变革的不断深入,人类社会正加速迈向智能化。作为智能世界和数字经济的坚实底座,数据中心也迎来了蓬勃发展。面