Spaces:
Runtime error
Runtime error
File size: 6,873 Bytes
140efa3 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 |
import argparse
import os
import random
import numpy as np
import torch
import torch.backends.cudnn as cudnn
import gradio as gr
import argparse
import torch
from llava.constants import (
IMAGE_TOKEN_INDEX,
DEFAULT_IMAGE_TOKEN,
DEFAULT_IM_START_TOKEN,
DEFAULT_IM_END_TOKEN,
IMAGE_PLACEHOLDER,
)
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 (
process_images,
tokenizer_image_token,
get_model_name_from_path,
)
from PIL import Image
import requests
from PIL import Image
from io import BytesIO
import re
from .conversation import Chat, conv_llava_v1
# imports modules for registration
def parse_args():
parser = argparse.ArgumentParser(description="Demo")
parser.add_argument("--model-path", type=str, default="mqt_llava_weight")
parser.add_argument("--model-base", type=str, default=None)
# parser.add_argument("--image-file", type=str, required=True)
# parser.add_argument("--query", type=str, required=True)
parser.add_argument("--conv-mode", type=str, default='llava_v1')
parser.add_argument("--sep", type=str, default=",")
parser.add_argument("--temperature", type=float, default=0)
parser.add_argument("--top_p", type=float, default=None)
parser.add_argument("--num_beams", type=int, default=1)
parser.add_argument("--max_new_tokens", type=int, default=512)
parser.add_argument("--num-visual-tokens", type=int, default=256)
args = parser.parse_args()
return args
# ========================================
# Model Initialization
# ========================================
print('Initializing Chat')
args = parse_args()
if torch.cuda.is_available():
device='cuda:{}'.format(args.gpu_id)
else:
device=torch.device('cpu')
disable_torch_init()
model_name = get_model_name_from_path(args.model_path)
tokenizer, model, image_processor, context_len = load_pretrained_model(
args.model_path, args.model_base, model_name
)
# 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, tokenizer, image_processor, args, device=device)
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="Upload & Start Chat", interactive=True), chat_state, img_list
def upload_img(gr_img, text_input, chat_state):
if gr_img is None:
return None, None, gr.update(interactive=True), chat_state, None
chat_state = conv_llava_v1.copy() #CONV_VISION.copy()
img_list = []
llm_message = chat.upload_img(gr_img, chat_state, img_list)
return gr.update(interactive=False), gr.update(interactive=True, placeholder='Type and press Enter'), gr.update(value="Start Chatting", interactive=False), chat_state, img_list
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, num_visual_tokens):
llm_message = chat.answer(conv=chat_state,
img_list=img_list,
num_beams=num_beams,
temperature=temperature,
num_visual_tokens=num_visual_tokens,
)[0]
chatbot[-1][1] = llm_message[0]
return chatbot, chat_state, img_list
title = """<h1 align="center">Demo of MQT-LLaVA</h1>"""
description = """<h3>This is the demo of MQT-LLaVA. Upload your images and start chatting!. <br> To use
example questions, click example image, hit upload, and press enter in the chatbox.</h3>"""
article = """<p><a href='https://github.com/gordonhu608/MQT-LLaVA'><img src='https://img.shields.io/badge/Github-Code-blue'></a></p><p><a href='https://arxiv.org/abs/'><img src='https://img.shields.io/badge/Paper-ArXiv-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")
upload_button = gr.Button(value="Upload & Start Chat", interactive=True, variant="primary")
clear = gr.Button("Restart 🔄")
num_visual_tokens = gr.Slider(
minimum=1,
maximum=256,
value=256,
step=1,
interactive=True,
label="Number of visual tokens",
)
temperature = gr.Slider(
minimum=0.1,
maximum=2.0,
value=1.0,
step=0.1,
interactive=True,
label="Temperature",
)
num_beams = gr.Slider(
minimum=1,
maximum=10,
value=5,
step=1,
interactive=True,
label="beam search numbers",
)
with gr.Column():
chat_state = gr.State()
img_list = gr.State()
chatbot = gr.Chatbot(label='MQT-LLaVA')
text_input = gr.Textbox(label='User', placeholder='Please upload your image first', interactive=False)
gr.Examples(examples=[
[f"images/extreme_ironing.jpg", "What is unusual about this image?"],
[f"images/waterview.jpg", "What are the things I should be cautious about when I visit here?"],
], inputs=[image, text_input])
upload_button.click(upload_img, [image, text_input, chat_state], [image, text_input, upload_button, chat_state, img_list])
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, num_visual_tokens], [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(enable_queue=True) |