ml-fastvlm/predict.py at main · zenlm/ml-fastvlm · GitHub

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
#
# Modified from LLaVA/predict.py
# Please see ACKNOWLEDGEMENTS for details about LICENSE
#
import os
import argparse

import torch
from PIL import Image

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


def predict(args):
    # Remove generation config from model folder
    # to read generation parameters from args
    model_path = os.path.expanduser(args.model_path)
    generation_config = None
    if os.path.exists(os.path.join(model_path, 'generation_config.json')):
        generation_config = os.path.join(model_path, '.generation_config.json')
        os.rename(os.path.join(model_path, 'generation_config.json'),
                  generation_config)

    # Load model
    disable_torch_init()
    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, device="mps")

    # Construct prompt
    qs = args.prompt
    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()

    # Set the pad token id for generation
    model.generation_config.pad_token_id = tokenizer.pad_token_id

    # Tokenize prompt
    input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).to(torch.device("mps"))

    # Load and preprocess image
    image = Image.open(args.image_file).convert('RGB')
    image_tensor = process_images([image], image_processor, model.config)[0]

    # Run inference
    with torch.inference_mode():
        output_ids = model.generate(
            input_ids,
            images=image_tensor.unsqueeze(0).half(),
            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,
            max_new_tokens=256,
            use_cache=True)

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

    # Restore generation config
    if generation_config is not None:
        os.rename(generation_config, os.path.join(model_path, 'generation_config.json'))


if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--model-path", type=str, default="./llava-v1.5-13b")
    parser.add_argument("--model-base", type=str, default=None)
    parser.add_argument("--image-file", type=str, default=None, help="location of image file")
    parser.add_argument("--prompt", type=str, default="Describe the image.", help="Prompt for VLM.")
    parser.add_argument("--conv-mode", type=str, default="qwen_2")
    parser.add_argument("--temperature", type=float, default=0.2)
    parser.add_argument("--top_p", type=float, default=None)
    parser.add_argument("--num_beams", type=int, default=1)
    args = parser.parse_args()

    predict(args)