-
Notifications
You must be signed in to change notification settings - Fork 2
/
demo_video.py
162 lines (131 loc) · 5.63 KB
/
demo_video.py
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
"""
Adapted from: https://github.com/Vision-CAIR/MiniGPT-4/blob/main/demo.py
"""
import argparse
import os
import random
import numpy as np
import torch
import torch.backends.cudnn as cudnn
import gradio as gr
from video_llama.common.config import Config
from video_llama.common.dist_utils import get_rank
from video_llama.common.registry import registry
from video_llama.conversation.conversation_video import Chat, default_conversation
import decord
decord.bridge.set_bridge('torch')
#%%
# imports modules for registration
from video_llama.datasets.builders import *
from video_llama.models import *
from video_llama.processors import *
from video_llama.runners import *
from video_llama.tasks import *
#%%
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.webvid.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 video/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 = default_conversation.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):
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]
chatbot[-1][1] = llm_message
print(chat_state.get_prompt())
print(chat_state)
return chatbot, chat_state, img_list
title = """<h1 align="center">Demo of Video-LLaMA</h1>"""
description = """<h3>This is the demo of Video-LLaMA. Upload your images/videos and start chatting!</h3>"""
#TODO show examples below
with gr.Blocks() as demo:
gr.Markdown(title)
gr.Markdown(description)
with gr.Row():
with gr.Column(scale=0.5):
image = gr.Video()
print(image)
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='Video-LLaMA')
text_input = gr.Textbox(label='User', placeholder='Please upload your image/video first', interactive=False)
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], [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=False, enable_queue=True)
# %%