VisualPRM-8B-v1_1

import torch
import torchvision.transforms as T

from PIL import Image
from transformers import AutoModel, AutoTokenizer
from torchvision.transforms.functional import InterpolationMode

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, input_size=448, max_num=12):
    image = Image.open(image).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

def main():
    path = 'OpenGVLab/VisualPRM-8B-v1.1'
    tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
    model = AutoModel.from_pretrained(
        path,
        trust_remote_code=True,
        low_cpu_mem_usage=True,
        torch_dtype=torch.bfloat16,
    ).eval().cuda()

    question = 'Find m \\angle 3.'

    response_a = """
To find the measure of \\angle 3, we need to use the properties of the angles in the given geometric figure.

1. \\angle EDC is a right angle, and it is split into \\angle EDF and \\angle 3.

2. We know that \\angle EDF = 39^\\circ because it is labeled in the diagram.

3. Since \\angle EDC is 90^\\circ, we can set up the equation for \\angle 3: \\angle EDC = \\angle EDF + \\angle 3

4. Substituting the known values, we get: 90^\\circ = 39^\\circ + \\angle 3

5. Solving for \\angle 3: \\angle 3 = 90^\\circ - 39^\\circ

6. Simplifying the equation: \\angle 3 = 51^\\circ

Final answer: 51^\\circ
""".strip()

    response_b = """
To find \\( m \\angle 3 \\), we need to analyze the given geometric figure carefully.

1. Recognize that \\( \\angle 3 \\) is part of triangle \\( BCE \\). Since \\( \\angle 1 \\) is given as 48° and \\( \\angle 2 \\) is a right angle (90°), we can use the properties of a right triangle to find \\( \\angle 3 \\).

2. The sum of the angles in any triangle is 180°. Therefore, in triangle \\( BCE \\): \[ \\angle 1 + \\angle 2 + \\angle 3 = 180° \]

3. Substitute the known values: \[ 48° + 90° + \\angle 3 = 180° \]

4. Solve for \\( \\angle 3 \\): \[ \\angle 3 = 180° - 48° - 90° = 42° \]

Thus, the measure of \\( \\angle 3 \\) is 42°.

Final answer: 42
""".strip()

    response_list = [
        response_a,
        response_b,
    ]
    image = 'examples/image.png'
    pixel_values = load_image(image).to(torch.bfloat16).cuda()

    sorted_response_list = model.select_best_response(
        tokenizer=tokenizer,
        question=question,
        response_list=response_list,
        pixel_values=pixel_values,
        return_scores=True,
    )

    print('Best response:', sorted_response_list[0][0])
    print('Highest score:', sorted_response_list[0][1])

if __name__ == '__main__':
    main()

import torch
import torchvision.transforms as T

from PIL import Image
from transformers import AutoModel, AutoTokenizer
from torchvision.transforms.functional import InterpolationMode

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, input_size=448, max_num=12):
    image = Image.open(image).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

def main():
    path = 'OpenGVLab/VisualPRM-8B-v1.1'
    tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
    model = AutoModel.from_pretrained(
        path,
        trust_remote_code=True,
        low_cpu_mem_usage=True,
        torch_dtype=torch.bfloat16,
    ).eval().cuda()

    question = 'Find m \\angle 3.'

    response_a = """
To find the measure of \\angle 3, we need to use the properties of the angles in the given geometric figure.

1. \\angle EDC is a right angle, and it is split into \\angle EDF and \\angle 3.

2. We know that \\angle EDF = 39^\\circ because it is labeled in the diagram.

3. Since \\angle EDC is 90^\\circ, we can set up the equation for \\angle 3: \\angle EDC = \\angle EDF + \\angle 3

4. Substituting the known values, we get: 90^\\circ = 39^\\circ + \\angle 3

5. Solving for \\angle 3: \\angle 3 = 90^\\circ - 39^\\circ

6. Simplifying the equation: \\angle 3 = 51^\\circ

Final answer: 51^\\circ
""".strip()

    response_b = """
To find \\( m \\angle 3 \\), we need to analyze the given geometric figure carefully.

1. Recognize that \\( \\angle 3 \\) is part of triangle \\( BCE \\). Since \\( \\angle 1 \\) is given as 48° and \\( \\angle 2 \\) is a right angle (90°), we can use the properties of a right triangle to find \\( \\angle 3 \\).

2. The sum of the angles in any triangle is 180°. Therefore, in triangle \\( BCE \\): \[ \\angle 1 + \\angle 2 + \\angle 3 = 180° \]

3. Substitute the known values: \[ 48° + 90° + \\angle 3 = 180° \]

4. Solve for \\( \\angle 3 \\): \[ \\angle 3 = 180° - 48° - 90° = 42° \]

Thus, the measure of \\( \\angle 3 \\) is 42°.

Final answer: 42
""".strip()

    response_list = [
        response_a,
        response_b,
    ]
    image = 'examples/image.png'
    pixel_values = load_image(image).to(torch.bfloat16).cuda()

    sorted_response_list = model.select_best_response(
        tokenizer=tokenizer,
        question=question,
        response_list=response_list,
        pixel_values=pixel_values,
        return_scores=True,
    )

    print('Best response:', sorted_response_list[0][0])
    print('Highest score:', sorted_response_list[0][1])

if __name__ == '__main__':
    main()

import torch
import torchvision.transforms as T

from PIL import Image
from transformers import AutoModel, AutoTokenizer
from torchvision.transforms.functional import InterpolationMode

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, input_size=448, max_num=12):
    image = Image.open(image).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

def main():
    path = 'OpenGVLab/VisualPRM-8B-v1.1'
    tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
    model = AutoModel.from_pretrained(
        path,
        trust_remote_code=True,
        low_cpu_mem_usage=True,
        torch_dtype=torch.bfloat16,
    ).eval().cuda()

    question = 'Find m \\angle 3.'

    response_a = """
To find the measure of \\angle 3, we need to use the properties of the angles in the given geometric figure.

1. \\angle EDC is a right angle, and it is split into \\angle EDF and \\angle 3.

2. We know that \\angle EDF = 39^\\circ because it is labeled in the diagram.

3. Since \\angle EDC is 90^\\circ, we can set up the equation for \\angle 3: \\angle EDC = \\angle EDF + \\angle 3

4. Substituting the known values, we get: 90^\\circ = 39^\\circ + \\angle 3

5. Solving for \\angle 3: \\angle 3 = 90^\\circ - 39^\\circ

6. Simplifying the equation: \\angle 3 = 51^\\circ

Final answer: 51^\\circ
""".strip()

    response_b = """
To find \\( m \\angle 3 \\), we need to analyze the given geometric figure carefully.

1. Recognize that \\( \\angle 3 \\) is part of triangle \\( BCE \\). Since \\( \\angle 1 \\) is given as 48° and \\( \\angle 2 \\) is a right angle (90°), we can use the properties of a right triangle to find \\( \\angle 3 \\).

2. The sum of the angles in any triangle is 180°. Therefore, in triangle \\( BCE \\): \[ \\angle 1 + \\angle 2 + \\angle 3 = 180° \]

3. Substitute the known values: \[ 48° + 90° + \\angle 3 = 180° \]

4. Solve for \\( \\angle 3 \\): \[ \\angle 3 = 180° - 48° - 90° = 42° \]

Thus, the measure of \\( \\angle 3 \\) is 42°.

Final answer: 42
""".strip()

    response_list = [
        response_a,
        response_b,
    ]
    image = 'examples/image.png'
    pixel_values = load_image(image).to(torch.bfloat16).cuda()

    sorted_response_list = model.select_best_response(
        tokenizer=tokenizer,
        question=question,
        response_list=response_list,
        pixel_values=pixel_values,
        return_scores=True,
    )

    print('Best response:', sorted_response_list[0][0])
    print('Highest score:', sorted_response_list[0][1])

if __name__ == '__main__':
    main()

import torch
import torchvision.transforms as T

from PIL import Image
from transformers import AutoModel, AutoTokenizer
from torchvision.transforms.functional import InterpolationMode

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, input_size=448, max_num=12):
    image = Image.open(image).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

def main():
    path = 'OpenGVLab/VisualPRM-8B-v1.1'
    tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
    model = AutoModel.from_pretrained(
        path,
        trust_remote_code=True,
        low_cpu_mem_usage=True,
        torch_dtype=torch.bfloat16,
    ).eval().cuda()

    question = 'Find m \\angle 3.'

    response_a = """
To find the measure of \\angle 3, we need to use the properties of the angles in the given geometric figure.

1. \\angle EDC is a right angle, and it is split into \\angle EDF and \\angle 3.

2. We know that \\angle EDF = 39^\\circ because it is labeled in the diagram.

3. Since \\angle EDC is 90^\\circ, we can set up the equation for \\angle 3: \\angle EDC = \\angle EDF + \\angle 3

4. Substituting the known values, we get: 90^\\circ = 39^\\circ + \\angle 3

5. Solving for \\angle 3: \\angle 3 = 90^\\circ - 39^\\circ

6. Simplifying the equation: \\angle 3 = 51^\\circ

Final answer: 51^\\circ
""".strip()

    response_b = """
To find \\( m \\angle 3 \\), we need to analyze the given geometric figure carefully.

1. Recognize that \\( \\angle 3 \\) is part of triangle \\( BCE \\). Since \\( \\angle 1 \\) is given as 48° and \\( \\angle 2 \\) is a right angle (90°), we can use the properties of a right triangle to find \\( \\angle 3 \\).

2. The sum of the angles in any triangle is 180°. Therefore, in triangle \\( BCE \\): \[ \\angle 1 + \\angle 2 + \\angle 3 = 180° \]

3. Substitute the known values: \[ 48° + 90° + \\angle 3 = 180° \]

4. Solve for \\( \\angle 3 \\): \[ \\angle 3 = 180° - 48° - 90° = 42° \]

Thus, the measure of \\( \\angle 3 \\) is 42°.

Final answer: 42
""".strip()

    response_list = [
        response_a,
        response_b,
    ]
    image = 'examples/image.png'
    pixel_values = load_image(image).to(torch.bfloat16).cuda()

    sorted_response_list = model.select_best_response(
        tokenizer=tokenizer,
        question=question,
        response_list=response_list,
        pixel_values=pixel_values,
        return_scores=True,
    )

    print('Best response:', sorted_response_list[0][0])
    print('Highest score:', sorted_response_list[0][1])

if __name__ == '__main__':
    main()

import torch
import torchvision.transforms as T

from PIL import Image
from transformers import AutoModel, AutoTokenizer
from torchvision.transforms.functional import InterpolationMode

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, input_size=448, max_num=12):
    image = Image.open(image).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

def main():
    path = 'OpenGVLab/VisualPRM-8B-v1.1'
    tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
    model = AutoModel.from_pretrained(
        path,
        trust_remote_code=True,
        low_cpu_mem_usage=True,
        torch_dtype=torch.bfloat16,
    ).eval().cuda()

    question = 'Find m \\angle 3.'

    response_a = """
To find the measure of \\angle 3, we need to use the properties of the angles in the given geometric figure.

1. \\angle EDC is a right angle, and it is split into \\angle EDF and \\angle 3.

2. We know that \\angle EDF = 39^\\circ because it is labeled in the diagram.

3. Since \\angle EDC is 90^\\circ, we can set up the equation for \\angle 3: \\angle EDC = \\angle EDF + \\angle 3

4. Substituting the known values, we get: 90^\\circ = 39^\\circ + \\angle 3

5. Solving for \\angle 3: \\angle 3 = 90^\\circ - 39^\\circ

6. Simplifying the equation: \\angle 3 = 51^\\circ

Final answer: 51^\\circ
""".strip()

    response_b = """
To find \\( m \\angle 3 \\), we need to analyze the given geometric figure carefully.

1. Recognize that \\( \\angle 3 \\) is part of triangle \\( BCE \\). Since \\( \\angle 1 \\) is given as 48° and \\( \\angle 2 \\) is a right angle (90°), we can use the properties of a right triangle to find \\( \\angle 3 \\).

2. The sum of the angles in any triangle is 180°. Therefore, in triangle \\( BCE \\): \[ \\angle 1 + \\angle 2 + \\angle 3 = 180° \]

3. Substitute the known values: \[ 48° + 90° + \\angle 3 = 180° \]

4. Solve for \\( \\angle 3 \\): \[ \\angle 3 = 180° - 48° - 90° = 42° \]

Thus, the measure of \\( \\angle 3 \\) is 42°.

Final answer: 42
""".strip()

    response_list = [
        response_a,
        response_b,
    ]
    image = 'examples/image.png'
    pixel_values = load_image(image).to(torch.bfloat16).cuda()

    sorted_response_list = model.select_best_response(
        tokenizer=tokenizer,
        question=question,
        response_list=response_list,
        pixel_values=pixel_values,
        return_scores=True,
    )

    print('Best response:', sorted_response_list[0][0])
    print('Highest score:', sorted_response_list[0][1])

if __name__ == '__main__':
    main()

import torch
import torchvision.transforms as T

from PIL import Image
from transformers import AutoModel, AutoTokenizer
from torchvision.transforms.functional import InterpolationMode

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, input_size=448, max_num=12):
    image = Image.open(image).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

def main():
    path = 'OpenGVLab/VisualPRM-8B-v1.1'
    tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
    model = AutoModel.from_pretrained(
        path,
        trust_remote_code=True,
        low_cpu_mem_usage=True,
        torch_dtype=torch.bfloat16,
    ).eval().cuda()

    question = 'Find m \\angle 3.'

    response_a = """
To find the measure of \\angle 3, we need to use the properties of the angles in the given geometric figure.

1. \\angle EDC is a right angle, and it is split into \\angle EDF and \\angle 3.

2. We know that \\angle EDF = 39^\\circ because it is labeled in the diagram.

3. Since \\angle EDC is 90^\\circ, we can set up the equation for \\angle 3: \\angle EDC = \\angle EDF + \\angle 3

4. Substituting the known values, we get: 90^\\circ = 39^\\circ + \\angle 3

5. Solving for \\angle 3: \\angle 3 = 90^\\circ - 39^\\circ

6. Simplifying the equation: \\angle 3 = 51^\\circ

Final answer: 51^\\circ
""".strip()

    response_b = """
To find \\( m \\angle 3 \\), we need to analyze the given geometric figure carefully.

1. Recognize that \\( \\angle 3 \\) is part of triangle \\( BCE \\). Since \\( \\angle 1 \\) is given as 48° and \\( \\angle 2 \\) is a right angle (90°), we can use the properties of a right triangle to find \\( \\angle 3 \\).

2. The sum of the angles in any triangle is 180°. Therefore, in triangle \\( BCE \\): \[ \\angle 1 + \\angle 2 + \\angle 3 = 180° \]

3. Substitute the known values: \[ 48° + 90° + \\angle 3 = 180° \]

4. Solve for \\( \\angle 3 \\): \[ \\angle 3 = 180° - 48° - 90° = 42° \]

Thus, the measure of \\( \\angle 3 \\) is 42°.

Final answer: 42
""".strip()

    response_list = [
        response_a,
        response_b,
    ]
    image = 'examples/image.png'
    pixel_values = load_image(image).to(torch.bfloat16).cuda()

    sorted_response_list = model.select_best_response(
        tokenizer=tokenizer,
        question=question,
        response_list=response_list,
        pixel_values=pixel_values,
        return_scores=True,
    )

    print('Best response:', sorted_response_list[0][0])
    print('Highest score:', sorted_response_list[0][1])

if __name__ == '__main__':
    main()

import torch
import torchvision.transforms as T

from PIL import Image
from transformers import AutoModel, AutoTokenizer
from torchvision.transforms.functional import InterpolationMode

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, input_size=448, max_num=12):
    image = Image.open(image).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

def main():
    path = 'OpenGVLab/VisualPRM-8B-v1.1'
    tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
    model = AutoModel.from_pretrained(
        path,
        trust_remote_code=True,
        low_cpu_mem_usage=True,
        torch_dtype=torch.bfloat16,
    ).eval().cuda()

    question = 'Find m \\angle 3.'

    response_a = """
To find the measure of \\angle 3, we need to use the properties of the angles in the given geometric figure.

1. \\angle EDC is a right angle, and it is split into \\angle EDF and \\angle 3.

2. We know that \\angle EDF = 39^\\circ because it is labeled in the diagram.

3. Since \\angle EDC is 90^\\circ, we can set up the equation for \\angle 3: \\angle EDC = \\angle EDF + \\angle 3

4. Substituting the known values, we get: 90^\\circ = 39^\\circ + \\angle 3

5. Solving for \\angle 3: \\angle 3 = 90^\\circ - 39^\\circ

6. Simplifying the equation: \\angle 3 = 51^\\circ

Final answer: 51^\\circ
""".strip()

    response_b = """
To find \\( m \\angle 3 \\), we need to analyze the given geometric figure carefully.

1. Recognize that \\( \\angle 3 \\) is part of triangle \\( BCE \\). Since \\( \\angle 1 \\) is given as 48° and \\( \\angle 2 \\) is a right angle (90°), we can use the properties of a right triangle to find \\( \\angle 3 \\).

2. The sum of the angles in any triangle is 180°. Therefore, in triangle \\( BCE \\): \[ \\angle 1 + \\angle 2 + \\angle 3 = 180° \]

3. Substitute the known values: \[ 48° + 90° + \\angle 3 = 180° \]

4. Solve for \\( \\angle 3 \\): \[ \\angle 3 = 180° - 48° - 90° = 42° \]

Thus, the measure of \\( \\angle 3 \\) is 42°.

Final answer: 42
""".strip()

    response_list = [
        response_a,
        response_b,
    ]
    image = 'examples/image.png'
    pixel_values = load_image(image).to(torch.bfloat16).cuda()

    sorted_response_list = model.select_best_response(
        tokenizer=tokenizer,
        question=question,
        response_list=response_list,
        pixel_values=pixel_values,
        return_scores=True,
    )

    print('Best response:', sorted_response_list[0][0])
    print('Highest score:', sorted_response_list[0][1])

if __name__ == '__main__':
    main()

import torch
import torchvision.transforms as T

from PIL import Image
from transformers import AutoModel, AutoTokenizer
from torchvision.transforms.functional import InterpolationMode

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, input_size=448, max_num=12):
    image = Image.open(image).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

def main():
    path = 'OpenGVLab/VisualPRM-8B-v1.1'
    tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
    model = AutoModel.from_pretrained(
        path,
        trust_remote_code=True,
        low_cpu_mem_usage=True,
        torch_dtype=torch.bfloat16,
    ).eval().cuda()

    question = 'Find m \\angle 3.'

    response_a = """
To find the measure of \\angle 3, we need to use the properties of the angles in the given geometric figure.

1. \\angle EDC is a right angle, and it is split into \\angle EDF and \\angle 3.

2. We know that \\angle EDF = 39^\\circ because it is labeled in the diagram.

3. Since \\angle EDC is 90^\\circ, we can set up the equation for \\angle 3: \\angle EDC = \\angle EDF + \\angle 3

4. Substituting the known values, we get: 90^\\circ = 39^\\circ + \\angle 3

5. Solving for \\angle 3: \\angle 3 = 90^\\circ - 39^\\circ

6. Simplifying the equation: \\angle 3 = 51^\\circ

Final answer: 51^\\circ
""".strip()

    response_b = """
To find \\( m \\angle 3 \\), we need to analyze the given geometric figure carefully.

1. Recognize that \\( \\angle 3 \\) is part of triangle \\( BCE \\). Since \\( \\angle 1 \\) is given as 48° and \\( \\angle 2 \\) is a right angle (90°), we can use the properties of a right triangle to find \\( \\angle 3 \\).

2. The sum of the angles in any triangle is 180°. Therefore, in triangle \\( BCE \\): \[ \\angle 1 + \\angle 2 + \\angle 3 = 180° \]

3. Substitute the known values: \[ 48° + 90° + \\angle 3 = 180° \]

4. Solve for \\( \\angle 3 \\): \[ \\angle 3 = 180° - 48° - 90° = 42° \]

Thus, the measure of \\( \\angle 3 \\) is 42°.

Final answer: 42
""".strip()

    response_list = [
        response_a,
        response_b,
    ]
    image = 'examples/image.png'
    pixel_values = load_image(image).to(torch.bfloat16).cuda()

    sorted_response_list = model.select_best_response(
        tokenizer=tokenizer,
        question=question,
        response_list=response_list,
        pixel_values=pixel_values,
        return_scores=True,
    )

    print('Best response:', sorted_response_list[0][0])
    print('Highest score:', sorted_response_list[0][1])

if __name__ == '__main__':
    main()

import torch
import torchvision.transforms as T

from PIL import Image
from transformers import AutoModel, AutoTokenizer
from torchvision.transforms.functional import InterpolationMode

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, input_size=448, max_num=12):
    image = Image.open(image).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

def main():
    path = 'OpenGVLab/VisualPRM-8B-v1.1'
    tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
    model = AutoModel.from_pretrained(
        path,
        trust_remote_code=True,
        low_cpu_mem_usage=True,
        torch_dtype=torch.bfloat16,
    ).eval().cuda()

    question = 'Find m \\angle 3.'

    response_a = """
To find the measure of \\angle 3, we need to use the properties of the angles in the given geometric figure.

1. \\angle EDC is a right angle, and it is split into \\angle EDF and \\angle 3.

2. We know that \\angle EDF = 39^\\circ because it is labeled in the diagram.

3. Since \\angle EDC is 90^\\circ, we can set up the equation for \\angle 3: \\angle EDC = \\angle EDF + \\angle 3

4. Substituting the known values, we get: 90^\\circ = 39^\\circ + \\angle 3

5. Solving for \\angle 3: \\angle 3 = 90^\\circ - 39^\\circ

6. Simplifying the equation: \\angle 3 = 51^\\circ

Final answer: 51^\\circ
""".strip()

    response_b = """
To find \\( m \\angle 3 \\), we need to analyze the given geometric figure carefully.

1. Recognize that \\( \\angle 3 \\) is part of triangle \\( BCE \\). Since \\( \\angle 1 \\) is given as 48° and \\( \\angle 2 \\) is a right angle (90°), we can use the properties of a right triangle to find \\( \\angle 3 \\).

2. The sum of the angles in any triangle is 180°. Therefore, in triangle \\( BCE \\): \[ \\angle 1 + \\angle 2 + \\angle 3 = 180° \]

3. Substitute the known values: \[ 48° + 90° + \\angle 3 = 180° \]

4. Solve for \\( \\angle 3 \\): \[ \\angle 3 = 180° - 48° - 90° = 42° \]

Thus, the measure of \\( \\angle 3 \\) is 42°.

Final answer: 42
""".strip()

    response_list = [
        response_a,
        response_b,
    ]
    image = 'examples/image.png'
    pixel_values = load_image(image).to(torch.bfloat16).cuda()

    sorted_response_list = model.select_best_response(
        tokenizer=tokenizer,
        question=question,
        response_list=response_list,
        pixel_values=pixel_values,
        return_scores=True,
    )

    print('Best response:', sorted_response_list[0][0])
    print('Highest score:', sorted_response_list[0][1])

if __name__ == '__main__':
    main()

import torch
import torchvision.transforms as T

from PIL import Image
from transformers import AutoModel, AutoTokenizer
from torchvision.transforms.functional import InterpolationMode

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, input_size=448, max_num=12):
    image = Image.open(image).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

def main():
    path = 'OpenGVLab/VisualPRM-8B-v1.1'
    tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast=False)
    model = AutoModel.from_pretrained(
        path,
        trust_remote_code=True,
        low_cpu_mem_usage=True,
        torch_dtype=torch.bfloat16,
    ).eval().cuda()

    question = 'Find m \\angle 3.'

    response_a = """
To find the measure of \\angle 3, we need to use the properties of the angles in the given geometric figure.

1. \\angle EDC is a right angle, and it is split into \\angle EDF and \\angle 3.

2. We know that \\angle EDF = 39^\\circ because it is labeled in the diagram.

3. Since \\angle EDC is 90^\\circ, we can set up the equation for \\angle 3: \\angle EDC = \\angle EDF + \\angle 3

4. Substituting the known values, we get: 90^\\circ = 39^\\circ + \\angle 3

5. Solving for \\angle 3: \\angle 3 = 90^\\circ - 39^\\circ

6. Simplifying the equation: \\angle 3 = 51^\\circ

Final answer: 51^\\circ
""".strip()

    response_b = """
To find \\( m \\angle 3 \\), we need to analyze the given geometric figure carefully.

1. Recognize that \\( \\angle 3 \\) is part of triangle \\( BCE \\). Since \\( \\angle 1 \\) is given as 48° and \\( \\angle 2 \\) is a right angle (90°), we can use the properties of a right triangle to find \\( \\angle 3 \\).

2. The sum of the angles in any triangle is 180°. Therefore, in triangle \\( BCE \\): \[ \\angle 1 + \\angle 2 + \\angle 3 = 180° \]

3. Substitute the known values: \[ 48° + 90° + \\angle 3 = 180° \]

4. Solve for \\( \\angle 3 \\): \[ \\angle 3 = 180° - 48° - 90° = 42° \]

Thus, the measure of \\( \\angle 3 \\) is 42°.

Final answer: 42
""".strip()

    response_list = [
        response_a,
        response_b,
    ]
    image = 'examples/image.png'
    pixel_values = load_image(image).to(torch.bfloat16).cuda()

    sorted_response_list = model.select_best_response(
        tokenizer=tokenizer,
        question=question,
        response_list=response_list,
        pixel_values=pixel_values,
        return_scores=True,
    )

    print('Best response:', sorted_response_list[0][0])
    print('Highest score:', sorted_response_list[0][1])

if __name__ == '__main__':
    main()