app.py

import gradio as gr

from pythainlp import  word_tokenize
import numpy as np
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.preprocessing.text import Tokenizer
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, Embedding, Conv1D, MaxPooling1D, Dense, Flatten, Concatenate, Dropout, Dot, Activation, Reshape, Permute, Multiply
from keras import backend as K
import pandas as pd
from transformers import TFAutoModel, AutoTokenizer
from sklearn.model_selection import train_test_split

# load the tokenizer and transformer model
tokenizer = AutoTokenizer.from_pretrained("xlm-roberta-base",max_length=60) #xlm-roberta-base bert-base-multilingual-cased
transformer_model = TFAutoModel.from_pretrained("xlm-roberta-base") #philschmid/tiny-bert-sst2-distilled
max_seq_length = 32

def create_model():
  # input_layer = Input(shape=(input_ids.shape[1],))
  # embedding_layer = Embedding(max_seq_length+ 1, 200, input_length=max_seq_length)(input_layer)

  inputs = tf.keras.layers.Input(shape=(max_seq_length,), dtype=tf.int32)
  embedding_layer = transformer_model(inputs)[0]

  flatten_layer = Flatten()(embedding_layer)
  x1 = Dense(64, activation='relu')(flatten_layer)
  x1 = Dense(32, activation='relu')(x1)
  x1 = Dense(16, activation='relu')(x1)


  x2 = Dense(64, activation='relu')(flatten_layer)
  x2 = Dense(32, activation='relu')(x2)
  x2 = Dense(16, activation='relu')(x2)

  x3 = Dense(64, activation='relu')(flatten_layer)
  x3 = Dense(32, activation='relu')(x3)
  x3 = Dense(16, activation='relu')(x3)

  x4 = Dense(64, activation='relu')(flatten_layer)
  x4 = Dense(32, activation='relu')(x4)
  x4 = Dense(16, activation='relu')(x4)


  x5 = Dense(64, activation='relu')(flatten_layer)
  x5 = Dense(32, activation='relu')(x5)
  x5 = Dense(16, activation='relu')(x5)

  x6 = Dense(512, activation='relu')(flatten_layer)
  x6 = Dense(256, activation='relu')(x6)
  x6 = Dense(128, activation='relu')(x6)

  x7 = Dense(128, activation='relu')(flatten_layer)
  x7 = Dense(64, activation='relu')(x7)
  x7 = Dense(32, activation='relu')(x7)

  x8 = Dense(256, activation='relu')(flatten_layer)
  x8 = Dense(128, activation='relu')(x8)
  x8 = Dense(64, activation='relu')(x8)


  output_layer1 = Dense(1, activation='sigmoid', name='output1')(x1)
  output_layer2 = Dense(1, activation='sigmoid', name='output2')(x2) 
  output_layer3 = Dense(1, activation='sigmoid', name='output3')(x3) 
  output_layer4 = Dense(1, activation='sigmoid', name='output4')(x4) 
  output_layer5 = Dense(1, activation='sigmoid', name='output5')(x5) 
  output_layer6 = Dense(num_class_label_6, activation='softmax', name='output6')(x6) 
  output_layer7 = Dense(num_class_label_7, activation='softmax', name='output7')(x7) 
  output_layer8 = Dense(num_class_label_8, activation='softmax', name='output8')(x8) 

  model = Model(inputs=inputs , outputs=[output_layer1, output_layer2, output_layer3,output_layer4,output_layer5,output_layer6,output_layer7,output_layer8])
  model.load_weights("t1_m1.h5")
  return model


model =create_model()



def predict(text):
  test_texts = [text]
  spilt_thai_text = [word_tokenize(x) for x in test_texts]
  new_input_ids = tokenizer(spilt_thai_text, padding=True, truncation=True, return_tensors="tf",is_split_into_words=True)["input_ids"]
  test_padded_sequences = pad_sequences(new_input_ids, maxlen=max_seq_length,padding='post',truncating='post',value=1) #post pre
  print(test_padded_sequences.shape)
  predicted_labels = model.predict(test_padded_sequences)
  output = []

  for i in range(len(test_texts)):
    print(test_texts[i])
    valid = 1 if predicted_labels[0][i] > 0.5 else 0
    is_scene = 1 if predicted_labels[1][i] > 0.5 else 0
    has_num = 1 if predicted_labels[2][i] > 0.5 else 0
    print(f'is_valid : {valid}')
    print(f'is_scene : {is_scene}')
    print(f'has_num : {has_num}')

    turn = 1 if predicted_labels[3][i] > 0.5 else 0
    print(f'turn_on_off : {turn}')
    print(f'device : ไฟ')

    env_id = np.argmax(predicted_labels[5][i])
    env_label = env_decode[env_id]

    hour_id = np.argmax(predicted_labels[6][i])
    hour_label = hour_decode[hour_id]

    minute_id = np.argmax(predicted_labels[7][i])
    minute_label = minute_decode[minute_id]
    print(f'env : {env_label}')
    print(f'hour : {hour_label}')
    print(f'minute : {minute_label}')
    print('----')
    tmp = {
      'valid' : valid,
      'is_scene' : is_scene,
      'has_num' : has_num,
      'turn_on_off' : turn,
      'device' : 'ไฟ',
      'env' : env_label,
      'hour' : hour,
      'minute' : minute,
    }
  output.append(tmp)
  return output

iface = gr.Interface(
  fn=predict, 
  inputs='text',
  outputs='text',
  examples=[["Hello! My name is Omar"]]
)

iface.launch()