File size: 3,503 Bytes
4c609ee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import argparse
import os
import random
from flask import Flask, redirect, url_for, request

import numpy as np
import torch
import torch.backends.cudnn as cudnn
import gradio as gr

from minigpt4.common.config import Config
from minigpt4.common.dist_utils import get_rank
from minigpt4.common.registry import registry
from minigpt4.conversation.conversation import Chat, CONV_VISION

# imports modules for registration
from minigpt4.datasets.builders import *
from minigpt4.models import *
from minigpt4.processors import *
from minigpt4.runners import *
from minigpt4.tasks import *
from PIL import Image
import requests


from huggingface_hub import login
login("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")

def parse_args():
    parser = argparse.ArgumentParser(description="Demo")
    parser.add_argument("--cfg-path", required=True, help="path to configuration file.")
    parser.add_argument("--gpu-id", type=int, default=0, help="specify the gpu to load the model.")
    parser.add_argument(
        "--options",
        nargs="+",
        help="override some settings in the used config, the key-value pair "
        "in xxx=yyy format will be merged into config file (deprecate), "
        "change to --cfg-options instead.",
    )
    args = parser.parse_args()
    return args


def setup_seeds(config):
    seed = config.run_cfg.seed + get_rank()

    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)

    cudnn.benchmark = False
    cudnn.deterministic = True



# ========================================
#             Model Initialization
# ========================================

print('Initializing Chat')
args = parse_args()
cfg = Config(args)

model_config = cfg.model_cfg
model_config.device_8bit = args.gpu_id
model_cls = registry.get_model_class(model_config.arch)
model = model_cls.from_config(model_config).to('cuda:{}'.format(args.gpu_id))

vis_processor_cfg = cfg.datasets_cfg.cc_sbu_align.vis_processor.train
vis_processor = registry.get_processor_class(vis_processor_cfg.name).from_config(vis_processor_cfg)
chat = Chat(model, vis_processor, device='cuda:{}'.format(args.gpu_id))
print('Initialization Finished')


# 

# curl -X POST -H "Content-Type: application/x-www-form-urlencoded"  -d "user_message=Response in json format with keys image_description, name, objects, object_name, object_color. " http://127.0.0.1:5000
# curl -X POST -H "Content-Type: application/x-www-form-urlencoded"  -d "user_message=describe the image" http://127.0.0.1:5000

#curl -X POST -H "Content-Type: application/x-www-form-urlencoded"  -d "user_message=Response in json format with keys image_description, name, objects, object_name, object_color. " http://127.0.0.1:5000

app = Flask(__name__)
app.config["DEBUG"] = False


@app.route('/', methods = ['POST', 'GET'])
def home():
    user_message = request.form['user_message']
    image = Image.open(requests.get(request.form['image'], stream=True).raw)

    print(user_message)
    chat_state = CONV_VISION.copy()
    chat_state.messages = []
    img_list = []
    llm_message = chat.upload_img(image, chat_state, img_list)
    chat.ask(user_message, chat_state)

    llm_message = chat.answer(conv=chat_state,
                                  img_list=img_list,
                                  num_beams=5,
                                  temperature=1,
                                  max_new_tokens=600,
                                  max_length=2000)[0]
    return llm_message

app.run(host='0.0.0.0')