Chat UniVi

🚀 Chat-UniVi：統一視覺表徵賦能大語言模型實現圖像和視頻理解

Chat-UniVi 是一個統一視覺表徵模型，可賦能大語言模型實現圖像和視頻理解。它採用統一的視覺表徵框架，通過聯合訓練策略，使模型在圖像和視頻任務上均表現出色。

相關資源

• 論文
• 代碼

📄 許可證

Llama 2 遵循 LLAMA 2 社區許可證，版權歸 Meta Platforms, Inc. 所有。

✨ 主要特性

💡 圖像和視頻的統一視覺表徵

我們採用一組動態視覺令牌來統一表示圖像和視頻。這種表徵框架使模型能夠高效利用有限數量的視覺令牌，同時捕捉圖像所需的空間細節和視頻所需的綜合時間關係。

🔥 聯合訓練策略，讓大語言模型理解圖像和視頻

Chat-UniVi 在包含圖像和視頻的混合數據集上進行訓練，無需任何修改即可直接應用於涉及這兩種媒體的任務。

🤗 高性能，圖像和視頻互補學習

大量實驗結果表明，作為一個統一模型，Chat-UniVi 始終優於現有的專門針對圖像或視頻的方法。

💻 使用示例

視頻理解推理

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)

圖像理解推理

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)