File size: 7,389 Bytes
2220c11
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
import requests
import streamlit as st
from streamlit_lottie import st_lottie
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
import re

# Page Config
st.set_page_config(
    page_title="๋…ธ๋ž˜ ๊ฐ€์‚ฌ nํ–‰์‹œ",
    page_icon="๐Ÿ’Œ",
    layout="wide"
)

### Model
tokenizer = AutoTokenizer.from_pretrained("wumusill/final_project_kogpt2")

@st.cache(show_spinner=False)
def load_model():
    model = AutoModelForCausalLM.from_pretrained("wumusill/final_project_kogpt2")
    return model

model = load_model()

# Class : Dict ์ค‘๋ณต ํ‚ค ์ถœ๋ ฅ
class poem(object):
    def __init__(self,letter):
        self.letter = letter

    def __str__(self):
        return self.letter

    def __repr__(self):
        return "'"+self.letter+"'"


def n_line_poem(input_letter):

    # ๋‘์Œ ๋ฒ•์น™ ์‚ฌ์ „
    dooeum = {"๋ผ":"๋‚˜", "๋ฝ":"๋‚™", "๋ž€":"๋‚œ", "๋ž„":"๋‚ ", "๋žŒ":"๋‚จ", "๋ž":"๋‚ฉ", "๋ž‘":"๋‚ญ", 
          "๋ž˜":"๋‚ด", "๋žญ":"๋ƒ‰", "๋ƒ‘":"์•ฝ", "๋žต":"์•ฝ", "๋ƒฅ":"์–‘", "๋Ÿ‰":"์–‘", "๋…€":"์—ฌ", 
          "๋ ค":"์—ฌ", "๋…":"์—ญ", "๋ ฅ":"์—ญ", "๋…„":"์—ฐ", "๋ จ":"์—ฐ", "๋…ˆ":"์—ด", "๋ ฌ":"์—ด", 
          "๋…":"์—ผ", "๋ ด":"์—ผ", "๋ ต":"์—ฝ", "๋…•":"์˜", "๋ น":"์˜", "๋…œ":"์˜ˆ", "๋ก€":"์˜ˆ", 
          "๋กœ":"๋…ธ", "๋ก":"๋…น", "๋ก ":"๋…ผ", "๋กฑ":"๋†", "๋ขฐ":"๋‡Œ", "๋‡จ":"์š”", "๋ฃŒ":"์š”", 
          "๋ฃก":"์šฉ", "๋ฃจ":"๋ˆ„", "๋‰ด":"์œ ", "๋ฅ˜":"์œ ", "๋‰ต":"์œก", "๋ฅ™":"์œก", "๋ฅœ":"์œค", 
          "๋ฅ ":"์œจ", "๋ฅญ":"์œต", "๋ฅต":"๋Š‘", "๋ฆ„":"๋Š ", "๋ฆ‰":"๋Šฅ", "๋‹ˆ":"์ด", "๋ฆฌ":"์ด", 
          "๋ฆฐ":'์ธ', '๋ฆผ':'์ž„', '๋ฆฝ':'์ž…'}
    # ๊ฒฐ๊ณผ๋ฌผ์„ ๋‹ด์„ list
    res_l = []

    # ํ•œ ๊ธ€์ž์”ฉ ์ธ๋ฑ์Šค์™€ ํ•จ๊ป˜ ๊ฐ€์ ธ์˜ด
    for idx, val in enumerate(input_letter):
        # ๋‘์Œ ๋ฒ•์น™ ์ ์šฉ
        if val in dooeum.keys():
            val = dooeum[val]


        while True:
            # ๋งŒ์•ฝ idx ๊ฐ€ 0 ์ด๋ผ๋ฉด == ์ฒซ ๊ธ€์ž
            if idx == 0:
                # ์ฒซ ๊ธ€์ž ์ธ์ฝ”๋”ฉ
                input_ids = tokenizer.encode(
                val, add_special_tokens=False, return_tensors="pt")
                # print(f"{idx}๋ฒˆ ์ธ์ฝ”๋”ฉ : {input_ids}\n") # 2์ฐจ์› ํ…์„œ

                # ์ฒซ ๊ธ€์ž ์ธ์ฝ”๋”ฉ ๊ฐ’์œผ๋กœ ๋ฌธ์žฅ ์ƒ์„ฑ
                output_sequence = model.generate(
                    input_ids=input_ids, 
                    do_sample=True, max_length=42,
                    min_length=5, temperature=0.9, repetition_penalty=1.5,
                    no_repeat_ngram_size=2)[0]
                # print("์ฒซ ๊ธ€์ž ์ธ์ฝ”๋”ฉ ํ›„ generate ๊ฒฐ๊ณผ:", output_sequence, "\n") # tensor

            # ์ฒซ ๊ธ€์ž๊ฐ€ ์•„๋‹ˆ๋ผ๋ฉด
            else:
                # ํ•œ ์Œ์ ˆ
                input_ids = tokenizer.encode(
                val, add_special_tokens=False, return_tensors="pt")
                # print(f"{idx}๋ฒˆ ์งธ ๊ธ€์ž ์ธ์ฝ”๋”ฉ : {input_ids} \n")

                # ์ข€๋” ๋งค๋„๋Ÿฌ์šด ์‚ผํ–‰์‹œ๋ฅผ ์œ„ํ•ด ์ด์ „ ์ธ์ฝ”๋”ฉ๊ณผ ์ง€๊ธˆ ์ธ์ฝ”๋”ฉ ์—ฐ๊ฒฐ
                link_with_pre_sentence = torch.cat((generated_sequence, input_ids[0]), 0)
                link_with_pre_sentence = torch.reshape(link_with_pre_sentence, (1, len(link_with_pre_sentence)))
                # print(f"์ด์ „ ํ…์„œ์™€ ์—ฐ๊ฒฐ๋œ ํ…์„œ {link_with_pre_sentence} \n")

                # ์ธ์ฝ”๋”ฉ ๊ฐ’์œผ๋กœ ๋ฌธ์žฅ ์ƒ์„ฑ
                output_sequence = model.generate(
                    input_ids=link_with_pre_sentence, 
                    do_sample=True, max_length=42,
                    min_length=5, temperature=0.9, repetition_penalty=1.5,
                    no_repeat_ngram_size=2)[0]
                # print(f"{idx}๋ฒˆ ์ธ์ฝ”๋”ฉ ํ›„ generate : {output_sequence}")
        
            # ์ƒ์„ฑ๋œ ๋ฌธ์žฅ ๋ฆฌ์ŠคํŠธ๋กœ ๋ณ€ํ™˜ (์ธ์ฝ”๋”ฉ ๋˜์–ด์žˆ๊ณ , ์ƒ์„ฑ๋œ ๋ฌธ์žฅ ๋’ค๋กœ padding ์ด ์žˆ๋Š” ์ƒํƒœ)
            generated_sequence = output_sequence.tolist()
            # print(f"{idx}๋ฒˆ ์ธ์ฝ”๋”ฉ ๋ฆฌ์ŠคํŠธ : {generated_sequence} \n")

            # padding index ์•ž๊นŒ์ง€ slicing ํ•จ์œผ๋กœ์จ padding ์ œ๊ฑฐ, padding์ด ์—†์„ ์ˆ˜๋„ ์žˆ๊ธฐ ๋•Œ๋ฌธ์— ์กฐ๊ฑด๋ฌธ ํ™•์ธ ํ›„ ์ œ๊ฑฐ
            if tokenizer.pad_token_id in generated_sequence:
                generated_sequence = generated_sequence[:generated_sequence.index(tokenizer.pad_token_id)]
            
            generated_sequence = torch.tensor(generated_sequence) 
            # print(f"{idx}๋ฒˆ ์ธ์ฝ”๋”ฉ ๋ฆฌ์ŠคํŠธ ํŒจ๋”ฉ ์ œ๊ฑฐ ํ›„ ๋‹ค์‹œ ํ…์„œ : {generated_sequence} \n")

            # ์ฒซ ๊ธ€์ž๊ฐ€ ์•„๋‹ˆ๋ผ๋ฉด, generate ๋œ ์Œ์ ˆ๋งŒ ๊ฒฐ๊ณผ๋ฌผ list์— ๋“ค์–ด๊ฐˆ ์ˆ˜ ์žˆ๊ฒŒ ์•ž ๋ฌธ์žฅ์— ๋Œ€ํ•œ ์ธ์ฝ”๋”ฉ ๊ฐ’ ์ œ๊ฑฐ
            # print(generated_sequence)
            if idx != 0:
                # ์ด์ „ ๋ฌธ์žฅ์˜ ๊ธธ์ด ์ดํ›„๋กœ ์Šฌ๋ผ์ด์‹ฑํ•ด์„œ ์•ž ๋ฌธ์žฅ ์ œ๊ฑฐ
                generated_sequence = generated_sequence[len_sequence:]

            len_sequence = len(generated_sequence)
            # print("len_seq", len_sequence)

            # ์Œ์ ˆ ๊ทธ๋Œ€๋กœ ๋ฑ‰์œผ๋ฉด ๋‹ค์‹œ ํ•ด์™€, ์•„๋‹ˆ๋ฉด while๋ฌธ ํƒˆ์ถœ
            if len_sequence > 1:
                break

        # ๊ฒฐ๊ณผ๋ฌผ ๋ฆฌ์ŠคํŠธ์— ๋‹ด๊ธฐ
        res_l.append(generated_sequence)

    poem_dict = {}

    for letter, res in zip(input_letter, res_l):
        decode_res = tokenizer.decode(res, clean_up_tokenization_spaces=True, skip_special_tokens=True)
        poem_dict[poem(letter)] = decode_res

    return poem_dict

###

# Image(.gif)
@st.cache(show_spinner=False)
def load_lottieurl(url: str):
    r = requests.get(url)
    if r.status_code != 200:
        return None
    return r.json()

lottie_url = "https://assets7.lottiefiles.com/private_files/lf30_fjln45y5.json"

lottie_json = load_lottieurl(lottie_url)
st_lottie(lottie_json, speed=1, height=200, key="initial")


# Title
row0_spacer1, row0_1, row0_spacer2, row0_2, row0_spacer3 = st.columns(
    (0.01, 2, 0.05, 0.5, 0.01)
)

with row0_1:
    st.markdown("# ํ•œ๊ธ€ ๋…ธ๋ž˜ ๊ฐ€์‚ฌ nํ–‰์‹œโœ")
    st.markdown("### ๐Ÿฆ๋ฉ‹์Ÿ์ด์‚ฌ์ž์ฒ˜๋Ÿผ AIS7๐Ÿฆ - ํŒŒ์ด๋„ ํ”„๋กœ์ ํŠธ")

with row0_2:
    st.write("")
    st.write("")
    st.write("")
    st.subheader("1์กฐ - ํ•ดํŒŒ๋ฆฌ")
    st.write("์ด์ง€ํ˜œ, ์ตœ์ง€์˜, ๊ถŒ์†Œํฌ, ๋ฌธ์ข…ํ˜„, ๊ตฌ์žํ˜„, ๊น€์˜์ค€")

st.write('---')

# Explanation
row1_spacer1, row1_1, row1_spacer2 = st.columns((0.01, 0.01, 0.01))

with row1_1:
    st.markdown("### nํ–‰์‹œ ๊ฐ€์ด๋“œ๋ผ์ธ")
    st.markdown("1. ํ•˜๋‹จ์— ์žˆ๋Š” ํ…์ŠคํŠธ๋ฐ”์— 5์ž ์ดํ•˜ ํ•œ๊ธ€ ๋‹จ์–ด๋ฅผ ๋„ฃ์–ด์ฃผ์„ธ์š”")
    st.markdown("2. 'nํ–‰์‹œ ์ œ์ž‘ํ•˜๊ธฐ' ๋ฒ„ํŠผ์„ ํด๋ฆญํ•ด์ฃผ์„ธ์š”")

st.write('---')

# Model & Input
row2_spacer1, row2_1, row2_spacer2= st.columns((0.01, 0.01, 0.01))

# Word Input
with row2_1:
    word_input = st.text_input(
            "nํ–‰์‹œ์— ์‚ฌ์šฉํ•  ํ•œ๊ธ€ ๋‹จ์–ด๋ฅผ ์ ๊ณ  ๋ฒ„ํŠผ์„ ๋ˆŒ๋Ÿฌ์ฃผ์„ธ์š”.(์ตœ๋Œ€ 5์ž) ๐Ÿ‘‡",
            placeholder='ํ•œ๊ธ€ ๋‹จ์–ด๋ฅผ ์ž…๋ ฅํ•ด์ฃผ์„ธ์š”',
            max_chars=5
    )
    word_input = re.sub("[^๊ฐ€-ํžฃ]", "", word_input)
        
    if st.button('nํ–‰์‹œ ์ œ์ž‘ํ•˜๊ธฐ'):
        if word_input == "":
            st.error("์˜จ์ „ํ•œ ํ•œ๊ธ€ ๋‹จ์–ด๋ฅผ ์‚ฌ์šฉํ•ด์ฃผ์„ธ์š”!")

        else:
            st.write("nํ–‰์‹œ ๋‹จ์–ด :  ", word_input)
            with st.spinner('์ž ์‹œ ๊ธฐ๋‹ค๋ ค์ฃผ์„ธ์š”...'):
                result = n_line_poem(word_input)
            st.success('์™„๋ฃŒ๋์Šต๋‹ˆ๋‹ค!')
            for r in result:
                st.write(f'{r} : {result[r]}')