Chat UniVi

🚀 Chat-UniVi: 統一視覚表現による画像と動画理解を備えた大規模言語モデル

Chat-UniViは、画像と動画の統一視覚表現を用いて、大規模言語モデルに画像と動画の理解能力を付与するモデルです。このモデルは、画像と動画を含む混合データセットで学習されており、画像と動画の両方を扱うタスクに直接適用できます。

詳細情報の論文またはリソース: [論文] [コード]

📄 ライセンス

Llama 2は、LLAMA 2 Community Licenseの下でライセンスされています。 Copyright (c) Meta Platforms, Inc. All Rights Reserved.

✨ 主な機能

💡 画像と動画の統一視覚表現

一連の動的視覚トークンを用いて、画像と動画を統一的に表現します。この表現フレームワークにより、モデルは限られた数の視覚トークンを効率的に利用して、画像に必要な空間的詳細と動画に必要な包括的な時間的関係を同時に捉えることができます。

🔥 共同学習戦略による画像と動画の理解

Chat-UniViは、画像と動画の両方を含む混合データセットで学習されているため、何らの変更も必要とせずに、両方のメディアを扱うタスクに直接適用できます。

🤗 高い性能と画像と動画の相補的学習

広範な実験結果から、Chat-UniViは統一モデルとして、既存の画像または動画専用の手法を上回る性能を発揮することが示されています。

💻 使用例

基本的な使用法

動画理解の推論

import torch
import os
from ChatUniVi.constants import *
from ChatUniVi.conversation import conv_templates, SeparatorStyle
from ChatUniVi.model.builder import load_pretrained_model
from ChatUniVi.utils import disable_torch_init
from ChatUniVi.mm_utils import tokenizer_image_token, get_model_name_from_path, KeywordsStoppingCriteria
from PIL import Image
from decord import VideoReader, cpu
import numpy as np


def _get_rawvideo_dec(video_path, image_processor, max_frames=MAX_IMAGE_LENGTH, image_resolution=224, video_framerate=1, s=None, e=None):
    # speed up video decode via decord.

    if s is None:
        start_time, end_time = None, None
    else:
        start_time = int(s)
        end_time = int(e)
        start_time = start_time if start_time >= 0. else 0.
        end_time = end_time if end_time >= 0. else 0.
        if start_time > end_time:
            start_time, end_time = end_time, start_time
        elif start_time == end_time:
            end_time = start_time + 1

    if os.path.exists(video_path):
        vreader = VideoReader(video_path, ctx=cpu(0))
    else:
        print(video_path)
        raise FileNotFoundError

    fps = vreader.get_avg_fps()
    f_start = 0 if start_time is None else int(start_time * fps)
    f_end = int(min(1000000000 if end_time is None else end_time * fps, len(vreader) - 1))
    num_frames = f_end - f_start + 1
    if num_frames > 0:
        # T x 3 x H x W
        sample_fps = int(video_framerate)
        t_stride = int(round(float(fps) / sample_fps))

        all_pos = list(range(f_start, f_end + 1, t_stride))
        if len(all_pos) > max_frames:
            sample_pos = [all_pos[_] for _ in np.linspace(0, len(all_pos) - 1, num=max_frames, dtype=int)]
        else:
            sample_pos = all_pos

        patch_images = [Image.fromarray(f) for f in vreader.get_batch(sample_pos).asnumpy()]

        patch_images = torch.stack([image_processor.preprocess(img, return_tensors='pt')['pixel_values'][0] for img in patch_images])
        slice_len = patch_images.shape[0]

        return patch_images, slice_len
    else:
        print("video path: {} error.".format(video_path))


if __name__ == '__main__':
    # Model Parameter
    model_path = "Chat-UniVi/Chat-UniVi"  # or "Chat-UniVi/Chat-UniVi-13B"、"Chat-UniVi/Chat-UniVi-v1.5"
    video_path = ${video_path}

    # The number of visual tokens varies with the length of the video. "max_frames" is the maximum number of frames.
    # When the video is long, we will uniformly downsample the video to meet the frames when equal to the "max_frames".
    max_frames = 100

    # The number of frames retained per second in the video.
    video_framerate = 1

    # Input Text
    qs = "Describe the video."

    # Sampling Parameter
    conv_mode = "simple"
    temperature = 0.2
    top_p = None
    num_beams = 1

    disable_torch_init()
    model_path = os.path.expanduser(model_path)
    model_name = "ChatUniVi"
    tokenizer, model, image_processor, context_len = load_pretrained_model(model_path, None, model_name)

    mm_use_im_start_end = getattr(model.config, "mm_use_im_start_end", False)
    mm_use_im_patch_token = getattr(model.config, "mm_use_im_patch_token", True)
    if mm_use_im_patch_token:
        tokenizer.add_tokens([DEFAULT_IMAGE_PATCH_TOKEN], special_tokens=True)
    if mm_use_im_start_end:
        tokenizer.add_tokens([DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN], special_tokens=True)
    model.resize_token_embeddings(len(tokenizer))

    vision_tower = model.get_vision_tower()
    if not vision_tower.is_loaded:
        vision_tower.load_model()
    image_processor = vision_tower.image_processor

    if model.config.config["use_cluster"]:
        for n, m in model.named_modules():
            m = m.to(dtype=torch.bfloat16)

    # Check if the video exists
    if video_path is not None:
        video_frames, slice_len = _get_rawvideo_dec(video_path, image_processor, max_frames=max_frames, video_framerate=video_framerate)

        cur_prompt = qs
        if model.config.mm_use_im_start_end:
            qs = DEFAULT_IM_START_TOKEN + DEFAULT_IMAGE_TOKEN * slice_len + DEFAULT_IM_END_TOKEN + '\n' + qs
        else:
            qs = DEFAULT_IMAGE_TOKEN * slice_len + '\n' + qs

        conv = conv_templates[conv_mode].copy()
        conv.append_message(conv.roles[0], qs)
        conv.append_message(conv.roles[1], None)
        prompt = conv.get_prompt()

        input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(
            0).cuda()

        stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
        keywords = [stop_str]
        stopping_criteria = KeywordsStoppingCriteria(keywords, tokenizer, input_ids)

        with torch.inference_mode():
            output_ids = model.generate(
                input_ids,
                images=video_frames.half().cuda(),
                do_sample=True,
                temperature=temperature,
                top_p=top_p,
                num_beams=num_beams,
                output_scores=True,
                return_dict_in_generate=True,
                max_new_tokens=1024,
                use_cache=True,
                stopping_criteria=[stopping_criteria])

        output_ids = output_ids.sequences
        input_token_len = input_ids.shape[1]
        n_diff_input_output = (input_ids != output_ids[:, :input_token_len]).sum().item()
        if n_diff_input_output > 0:
            print(f'[Warning] {n_diff_input_output} output_ids are not the same as the input_ids')
        outputs = tokenizer.batch_decode(output_ids[:, input_token_len:], skip_special_tokens=True)[0]
        outputs = outputs.strip()
        if outputs.endswith(stop_str):
            outputs = outputs[:-len(stop_str)]
        outputs = outputs.strip()
        print(outputs)

画像理解の推論

import torch
import os
from ChatUniVi.constants import *
from ChatUniVi.conversation import conv_templates, SeparatorStyle
from ChatUniVi.model.builder import load_pretrained_model
from ChatUniVi.utils import disable_torch_init
from ChatUniVi.mm_utils import tokenizer_image_token, get_model_name_from_path, KeywordsStoppingCriteria
from PIL import Image


if __name__ == '__main__':
    # Model Parameter
    model_path = "Chat-UniVi/Chat-UniVi"  # or "Chat-UniVi/Chat-UniVi-13B"、"Chat-UniVi/Chat-UniVi-v1.5"
    image_path = ${image_path}

    # Input Text
    qs = "Describe the image."

    # Sampling Parameter
    conv_mode = "simple"
    temperature = 0.2
    top_p = None
    num_beams = 1

    disable_torch_init()
    model_path = os.path.expanduser(model_path)
    model_name = "ChatUniVi"
    tokenizer, model, image_processor, context_len = load_pretrained_model(model_path, None, model_name)

    mm_use_im_start_end = getattr(model.config, "mm_use_im_start_end", False)
    mm_use_im_patch_token = getattr(model.config, "mm_use_im_patch_token", True)
    if mm_use_im_patch_token:
        tokenizer.add_tokens([DEFAULT_IMAGE_PATCH_TOKEN], special_tokens=True)
    if mm_use_im_start_end:
        tokenizer.add_tokens([DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN], special_tokens=True)
    model.resize_token_embeddings(len(tokenizer))

    vision_tower = model.get_vision_tower()
    if not vision_tower.is_loaded:
        vision_tower.load_model()
    image_processor = vision_tower.image_processor

    # Check if the video exists
    if image_path is not None:
        cur_prompt = qs
        if model.config.mm_use_im_start_end:
            qs = DEFAULT_IM_START_TOKEN + DEFAULT_IMAGE_TOKEN + DEFAULT_IM_END_TOKEN + '\n' + qs
        else:
            qs = DEFAULT_IMAGE_TOKEN + '\n' + qs

        conv = conv_templates[conv_mode].copy()
        conv.append_message(conv.roles[0], qs)
        conv.append_message(conv.roles[1], None)
        prompt = conv.get_prompt()

        input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).cuda()

        image = Image.open(image_path)
        image_tensor = image_processor.preprocess(image, return_tensors='pt')['pixel_values'][0]

        stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
        keywords = [stop_str]
        stopping_criteria = KeywordsStoppingCriteria(keywords, tokenizer, input_ids)

        with torch.inference_mode():
            output_ids = model.generate(
                input_ids,
                images=image_tensor.unsqueeze(0).half().cuda(),
                do_sample=True,
                temperature=temperature,
                top_p=top_p,
                num_beams=num_beams,
                max_new_tokens=1024,
                use_cache=True,
                stopping_criteria=[stopping_criteria])

        input_token_len = input_ids.shape[1]
        n_diff_input_output = (input_ids != output_ids[:, :input_token_len]).sum().item()
        if n_diff_input_output > 0:
            print(f'[Warning] {n_diff_input_output} output_ids are not the same as the input_ids')
        outputs = tokenizer.batch_decode(output_ids[:, input_token_len:], skip_special_tokens=True)[0]
        outputs = outputs.strip()
        if outputs.endswith(stop_str):
            outputs = outputs[:-len(stop_str)]
        outputs = outputs.strip()
        print(outputs)