极智AI | 多模态大模型中的动态高分辨率

极智视界分享了多模态大模型中的动态高分辨率技术，该技术允许模型根据图像复杂度实时调整处理分辨率，以优化计算量。介绍了LLava-Next中的实现，包括切图和缩放两个分支，并展示了动态高分辨率的代码实现，涉及寻找最接近的宽高比和动态预处理。

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