import argparse
import torch
torch.backends.cuda.enable_mem_efficient_sdp(False)
torch.backends.cuda.enable_flash_sdp(False)
import os
import json
from tqdm import tqdm
import shortuuid

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

from PIL import Image
import math


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 eval_model(image, prompt, args):

    args.model_base = 'teowu/llava_v1.5_7b_qinstruct_preview_v0.1'
    args.image = image
    args.prompt = prompt
    args.conv_mode = "llava_v1"
    args.num_chunks = 1
    args.chunk_idx = 0
    args.temperature = 0.2
    args.top_p = None
    args.num_beams = 1
    # Model
    disable_torch_init()
    model_path = os.path.expanduser(args.model_path)
    model_name = get_model_name_from_path(model_path)
    tokenizer, model, image_processor, context_len = load_pretrained_model(model_path, args.model_base, model_name)
    model.to(dtype=torch.bfloat16)

    idx = 'test'
    image_file = args.image
    qs = args.prompt
    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[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()

    image = Image.open(image_file).convert('RGB')
    image_tensor = process_images([image], image_processor, model.config)[0]
    image_tensor = image_tensor.to(model.device, dtype=torch.bfloat16)
    print(qs)
    print(torch.version.cuda)

    with torch.inference_mode():
        output_ids = model.generate(
            input_ids,
            images=image_tensor.unsqueeze(0).cuda(),
            image_sizes=[image.size],
            do_sample=True if args.temperature > 0 else False,
            temperature=args.temperature,
            top_p=args.top_p,
            num_beams=args.num_beams,
            # no_repeat_ngram_size=3,
            max_new_tokens=1024,
            use_cache=True)

    outputs = tokenizer.batch_decode(output_ids, skip_special_tokens=True)[0].strip()
    print(outputs)
    return outputs


if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    args = parser.parse_args()
    parser.add_argument("--model-path", type=str, default="./checkpoints/VLC_llava_v1.5_cot_lora_v0")
    parser.add_argument("--model-base", type=str, default=None)
    parser.add_argument("--image-folder", type=str, default="")
    parser.add_argument("--question-file", type=str, default="tables/question.jsonl")
    image = '/mnt/disk1/zian/LLaVA/my_test_image/blur_image1.jpg'
    prompt = 'Please describe this image.'
    args.model_path = '/mnt/disk1/zian/LLaVA/checkpoints/qinstruct_llava_v1.5_cot_lora_v5'

    outputs = eval_model(image, prompt, args)
    print(outputs)