flash_vstream/eval_video/model_msvd_qa.py

# Based on https://github.com/haotian-liu/LLaVA.

import os
import json
import math
import torch
import argparse
from tqdm import tqdm
from decord import VideoReader, cpu

from llama_vstream.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN
from llama_vstream.conversation import conv_templates, SeparatorStyle
from llama_vstream.model.builder import load_pretrained_model
from llama_vstream.utils import disable_torch_init
from llama_vstream.mm_utils import tokenizer_image_token, get_model_name_from_path, KeywordsStoppingCriteria


def split_list(lst, n):
    """Split a list into n (roughly) equal-sized chunks"""
    chunk_size = math.ceil(len(lst) / n)  # integer division
    return [lst[i:i+chunk_size] for i in range(0, len(lst), chunk_size)]


def get_chunk(lst, n, k):
    chunks = split_list(lst, n)
    return chunks[k]


def parse_args():
    """
    Parse command-line arguments.
    """
    parser = argparse.ArgumentParser()

    # Define the command-line arguments
    parser.add_argument('--video_dir', help='Directory containing video files.', required=True)
    parser.add_argument('--gt_file', help='Path to the ground truth file containing question.', required=True)
    parser.add_argument('--output_dir', help='Directory to save the model results JSON.', required=True)
    parser.add_argument('--output_name', help='Name of the file for storing results JSON.', required=True)
    parser.add_argument("--model-path", type=str, default="facebook/opt-350m")
    parser.add_argument("--model-base", type=str, default=None)
    parser.add_argument("--conv-mode", type=str, default=None)
    parser.add_argument("--num-chunks", type=int, default=1)
    parser.add_argument("--chunk-idx", type=int, default=0)
    parser.add_argument("--model-max-length", type=int, default=None)

    return parser.parse_args()


def load_video(video_path):
    vr = VideoReader(video_path, ctx=cpu(0))
    total_frame_num = len(vr)
    fps = round(vr.get_avg_fps())
    frame_idx = [i for i in range(0, len(vr), fps)]
    spare_frames = vr.get_batch(frame_idx).asnumpy()
    return spare_frames

    
def run_inference(args):
    """
    Run inference on ActivityNet QA DataSet using the Video-ChatGPT model.

    Args:
        args: Command-line arguments.
    """
    # Initialize the model
    model_name = get_model_name_from_path(args.model_path)
    tokenizer, model, image_processor, context_len = load_pretrained_model(args.model_path, args.model_base, model_name, args.model_max_length)

    # Load both ground truth file containing questions and answers
    with open(args.gt_file) as file:
        gt_questions = json.load(file)
    gt_questions = get_chunk(gt_questions, args.num_chunks, args.chunk_idx)

    # Create the output directory if it doesn't exist
    if not os.path.exists(args.output_dir):
        try:
            os.makedirs(args.output_dir)
        except Exception as e:
            print(f'mkdir Except: {e}')

    video_formats = ['.mp4', '.avi', '.mov', '.mkv']
    if args.num_chunks > 1:
        output_name = f"{args.num_chunks}_{args.chunk_idx}"
    else:
        output_name = args.output_name
    answers_file = os.path.join(args.output_dir, f"{output_name}.json")
    ans_file = open(answers_file, "w")

    for sample in tqdm(gt_questions, desc=f"cuda:{args.chunk_idx} "):
        video_name = sample['video_id']
        question = sample['question']
        id = sample['id']
        answer = sample['answer']

        sample_set = {'id': id, 'question': question, 'answer': answer}

        # Load the video file
        for fmt in video_formats:  # Added this line
            temp_path = os.path.join(args.video_dir, f"{video_name}{fmt}")
            if os.path.exists(temp_path):
                video_path = temp_path
                break

        # Check if the video exists
        if os.path.exists(video_path):
            video = load_video(video_path)
            video = image_processor.preprocess(video, return_tensors='pt')['pixel_values'].half().cuda()
            video = [video]
            
        qs = question
        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[args.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,
                do_sample=True,
                temperature=0.002,
                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()

        sample_set['pred'] = outputs
        ans_file.write(json.dumps(sample_set) + "\n")
        ans_file.flush()

    ans_file.close()


if __name__ == "__main__":
    args = parse_args()
    run_inference(args)