File size: 6,065 Bytes
a824a18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
import argparse
import torch
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, get_model_name_from_path, KeywordsStoppingCriteria

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(args):
    # 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)

    questions = json.load(open(os.path.expanduser(args.question_file), "r"))
    questions = get_chunk(questions, args.num_chunks, args.chunk_idx)
    answers_file = os.path.expanduser(args.answers_file)
    os.makedirs(os.path.dirname(answers_file), exist_ok=True)
    ans_file = open(answers_file, "w")
    for i, line in enumerate(tqdm(questions)):
        idx = line["id"]
        question = line['conversations'][0]
        qs = question['value'].replace('<image>', '').strip()
        cur_prompt = qs

        if 'image' in line:
            image_file = line["image"]
            image = Image.open(os.path.join(args.image_folder, image_file))
            image_tensor = image_processor.preprocess(image, return_tensors='pt')['pixel_values'][0]
            images = image_tensor.unsqueeze(0).half().cuda()
            if getattr(model.config, 'mm_use_im_start_end', False):
                qs = DEFAULT_IM_START_TOKEN + DEFAULT_IMAGE_TOKEN + DEFAULT_IM_END_TOKEN + '\n' + qs
            else:
                qs = DEFAULT_IMAGE_TOKEN + '\n' + qs
            cur_prompt = '<image>' + '\n' + cur_prompt
        else:
            images = None

        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)] if conv.version == "v0" else None

        with torch.inference_mode():
            output_ids = model.generate(
                input_ids,
                images=images,
                do_sample=True,
                temperature=0.2,
                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()

        # prompt for answer
        if args.answer_prompter:
            outputs_reasoning = outputs
            input_ids = tokenizer_image_token(prompt + outputs_reasoning + ' ###\nANSWER:', tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).cuda()

            with torch.inference_mode():
                output_ids = model.generate(
                    input_ids,
                    images=images,
                    do_sample=True,
                    temperature=0.2,
                    max_new_tokens=64,
                    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()
            outputs = outputs_reasoning + '\n The answer is ' + outputs

        ans_id = shortuuid.uuid()
        ans_file.write(json.dumps({"question_id": idx,
                                   "prompt": cur_prompt,
                                   "text": outputs,
                                   "answer_id": ans_id,
                                   "model_id": model_name,
                                   "metadata": {}}) + "\n")
        ans_file.flush()
    ans_file.close()

if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--model-path", type=str, default="facebook/opt-350m")
    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.json")
    parser.add_argument("--answers-file", type=str, default="answer.jsonl")
    parser.add_argument("--conv-mode", type=str, default="llava_v0")
    parser.add_argument("--num-chunks", type=int, default=1)
    parser.add_argument("--chunk-idx", type=int, default=0)
    parser.add_argument("--answer-prompter", action="store_true")
    args = parser.parse_args()

    eval_model(args)