|
import gradio as gr |
|
from transformers import AutoModelForSequenceClassification |
|
from transformers import AutoTokenizer |
|
import pandas as pd |
|
import random |
|
import torch |
|
|
|
|
|
README = """ |
|
# Movie Review Score Discriminator |
|
It is a program that classifies whether it is positive or negative by entering movie reviews. |
|
You can choose between the Korean version and the English version. |
|
## Usage |
|
|
|
""" |
|
|
|
|
|
|
|
|
|
id2label = {0: "NEGATIVE", 1: "POSITIVE"} |
|
label2id = {"NEGATIVE": 0, "POSITIVE": 1} |
|
|
|
|
|
title = "Movie Review Score Discriminator" |
|
description = "It is a program that classifies whether it is positive or negative by entering movie reviews. You can choose between the Korean version and the English version." |
|
|
|
|
|
|
|
|
|
def tokenized_data(tokenizer, inputs): |
|
return tokenizer.batch_encode_plus( |
|
[inputs], |
|
return_tensors="pt", |
|
padding="max_length", |
|
max_length=64, |
|
truncation=True) |
|
|
|
|
|
|
|
|
|
examples_eng = ["the greatest musicians ", "cold movie "] |
|
examples_kor = ["๊ธ์ ", "๋ถ์ "] |
|
|
|
examples = [] |
|
df = pd.read_csv('examples.csv', sep='\t', index_col='Unnamed: 0') |
|
for i in range(2): |
|
idx = random.randint(0, 50) |
|
examples.append(['Eng', df.iloc[idx, 0]]) |
|
examples.append(['Kor', df.iloc[idx, 1]]) |
|
|
|
|
|
eng_model_name = "roberta-base" |
|
eng_step = 1900 |
|
eng_tokenizer = AutoTokenizer.from_pretrained(eng_model_name) |
|
eng_file_name = "{}-{}.pt".format(eng_model_name, eng_step) |
|
eng_state_dict = torch.load(eng_file_name) |
|
eng_model = AutoModelForSequenceClassification.from_pretrained( |
|
eng_model_name, num_labels=2, id2label=id2label, label2id=label2id, |
|
state_dict=eng_state_dict |
|
) |
|
|
|
|
|
kor_model_name = "klue_roberta-small" |
|
kor_step = 2400 |
|
kor_tokenizer = AutoTokenizer.from_pretrained(kor_model_name.replace('_', '/')) |
|
kor_file_name = "{}-{}.pt".format(kor_model_name, kor_step) |
|
kor_state_dict = torch.load(kor_file_name) |
|
kor_model = AutoModelForSequenceClassification.from_pretrained( |
|
kor_model_name.replace('_', '/'), num_labels=2, id2label=id2label, label2id=label2id, |
|
state_dict=kor_state_dict |
|
) |
|
|
|
|
|
def builder(lang, text): |
|
if lang == 'Eng': |
|
model = eng_model |
|
tokenizer = eng_tokenizer |
|
else: |
|
model = kor_model |
|
tokenizer = kor_tokenizer |
|
|
|
inputs = tokenized_data(tokenizer, text) |
|
|
|
model.eval() |
|
with torch.no_grad(): |
|
logits = model(input_ids=inputs['input_ids'], |
|
attention_mask=inputs['attention_mask']).logits |
|
|
|
prediction = torch.argmax(logits, axis=1) |
|
|
|
return id2label[prediction.item()] |
|
|
|
|
|
def builder2(inputs): |
|
return eng_model(inputs) |
|
|
|
|
|
demo = gr.Interface(builder, inputs=[gr.inputs.Dropdown(['Eng', 'Kor']), "text"], outputs="text", |
|
title=title, description=description, examples=examples) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == "__main__": |
|
|
|
demo.launch() |
|
|
