demo_conlora.py

import argparse
import os
import random

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_conlora import Chat, CONV_VISION, Conversation

# 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 minigpt4.processors.utils.inference_util import get_image_with_bbox, unnorm_image

import torchvision.transforms as T
from PIL import Image
import re
import uuid

global_save_dic = {}




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("--continue-chat", type=bool, default=False, help="Where to continue chat when upload new image feature.")
    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
lora_name_list = list(model_config.lora_path.keys())
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')

# ========================================
#             Gradio Setting
# ========================================

def gradio_reset(chat_state, img_list):
    if chat_state is not None:
        chat_state.messages = []
    if img_list is not None:
        img_list = []
    return None, gr.update(value=None, interactive=True), gr.update(placeholder='Please upload your image first', interactive=False), gr.update(value=None, interactive=False), gr.update(value="Upload & Start Chat", interactive=True), chat_state, img_list

def upload_img(gr_img, text_input, chat_state, lora_choice, chatbot, img_list):
    if gr_img is None:
        return None, None, gr.update(interactive=True), chat_state, None
    
    # set lora before upload image
    chat.model.check_set_lora(lora_choice)

    model_state = getattr(chat.model, 'current_lora', 'default')
    chatbot.append([None, f'<mark>[***Add image feature with {model_state} state***]</mark>'])
    
    if not args.continue_chat or not isinstance(chat_state, Conversation):  # if not continue chat or chat_state is not initialized
        chat_state = CONV_VISION.copy()
        img_list = []
    llm_message, image_after_process = chat.upload_img(gr_img, chat_state, img_list)
    global_save_dic['image_after_process'] = image_after_process
    return gr.update(interactive=True), gr.update(interactive=True, placeholder='Type and press Enter'), gr.update(value="Insert image woth chosen mode", interactive=True), chat_state, img_list, chatbot

def gradio_ask(user_message, chatbot, chat_state):
    if len(user_message) == 0:
        return gr.update(interactive=True, placeholder='Input should not be empty!'), chatbot, chat_state
    chat.ask(user_message, chat_state)
    chatbot = chatbot + [[user_message, None]]
    return '', chatbot, chat_state


def gradio_answer(chatbot, chat_state, img_list, num_beams, temperature):
    llm_message = chat.answer(conv=chat_state,
                              img_list=img_list,
                              num_beams=num_beams,
                              temperature=temperature,
                              max_new_tokens=300,
                              max_length=2000)[0]
    model_state = getattr(chat.model, 'current_lora', 'default')

    chatbot[-1][1] = f'<mark>[***{model_state}***]</mark> <br />' + llm_message


    image_out_flag = False
    image_after_process = global_save_dic['image_after_process']
    if len(re.findall(r"<bin_(.+?)>", llm_message)) >= 2:
        image_unnorm = unnorm_image(image_after_process)
        image_box = get_image_with_bbox(image_unnorm, llm_message)
        image_out = T.ToPILImage()(image_box)
        image_out_flag = True

    if image_out_flag:
        image_filename = uuid.uuid4().hex + '.jpg'    
        image_save_path = os.path.join('./demo_tmp', image_filename)
        image_out.save(image_save_path)
        chatbot.append([None,(f'{image_save_path}', )])
        #print([None,(f'{image_save_path}', )"])


    return chatbot, chat_state, img_list  # gr.update(interactive=False) if image_out_flag else image_out

title = """<h1 align="center">Demo of Connect LoRA</h1>"""
# description = """<h3>This is the demo of MiniGPT-4. Upload your images and start chatting!</h3>"""
# article = """<p><a href='https://minigpt-4.github.io'><img src='https://img.shields.io/badge/Project-Page-Green'></a></p><p><a href='https://github.com/Vision-CAIR/MiniGPT-4'><img src='https://img.shields.io/badge/Github-Code-blue'></a></p><p><a href='https://raw.githubusercontent.com/Vision-CAIR/MiniGPT-4/main/MiniGPT_4.pdf'><img src='https://img.shields.io/badge/Paper-PDF-red'></a></p>
# """

#TODO show examples below

with gr.Blocks() as demo:
    gr.Markdown(title)
    # gr.Markdown(description)
    # gr.Markdown(article)

    with gr.Row():
        with gr.Column(scale=0.5):
            image = gr.Image(type="pil")
            
            # image_out = gr.Image(type="pil", interactive=False)
            lora_choice = gr.Radio(['original'] + lora_name_list, value='original', label="Choose a mode")

            upload_button = gr.Button(value="Upload & Start Chat", interactive=True, variant="primary")
            clear = gr.Button("Restart")
            
            num_beams = gr.Slider(
                minimum=1,
                maximum=10,
                value=1,
                step=1,
                interactive=True,
                label="beam search numbers)",
            )
            
            temperature = gr.Slider(
                minimum=0.1,
                maximum=2.0,
                value=1.0,
                step=0.1,
                interactive=True,
                label="Temperature",
            )

        with gr.Column():
            chat_state = gr.State()
            img_list = gr.State()
            chatbot = gr.Chatbot(label='ConLoRA', height=5000)
            text_input = gr.Textbox(label='User', placeholder='Please upload your image first', interactive=False)

    upload_button.click(upload_img, [image, text_input, chat_state, lora_choice, chatbot, img_list], 
                                    [image, text_input, upload_button, chat_state, img_list, chatbot])
    
    text_input.submit(gradio_ask, [text_input, chatbot, chat_state], [text_input, chatbot, chat_state]).then(
        gradio_answer, [chatbot, chat_state, img_list, num_beams, temperature], [chatbot, chat_state, img_list]
    )


    
    clear.click(gradio_reset, [chat_state, img_list], [chatbot, image, text_input, upload_button, chat_state, img_list], queue=False)

demo.launch(share=True, enable_queue=True)