streamlit_app.py

#Transformer codes was from : https://www.tensorflow.org/text/tutorials/transformer

import streamlit as st
import tensorflow as tf
import numpy as np
import pickle
import os

#os.environ['KMP_DUPLICATE_LIB_OK']='True'
st.header("Novel Generation by Transformer")
#placeholder2 = st.empty()
#disclaimer2 = "Model Initializing... (May take a few seconds.)"
#dis_style2 = '<p style="font-family:"Times New Roman"; font-size: 14px;">' + disclaimer2 + '</p>' + '<p style="font-family:"Times New Roman"; font-size: 14px;">' + "Generating..." + '</p>'
#placeholder2.markdown(dis_style2, unsafe_allow_html=True)
#st.write("System Initialize (may take a several time)")

inp_tokenizer = pickle.load(open('inp_tokenizer','rb'))
targ_tokenizer = pickle.load(open('out_tokenizer','rb'))
input_vocab = 3102
output_vocab = 4034

#st.write("Tokenizer Importing Finished.")
#st.write(os.getcwd())

def get_angles(pos, i, d_model):
  angle_rates = 1 / np.power(10000, (2 * (i//2)) / np.float32(d_model))
  return pos * angle_rates

def positional_encoding(position, d_model):
  angle_rads = get_angles(np.arange(position)[:, np.newaxis],
                          np.arange(d_model)[np.newaxis, :],
                          d_model)

  # apply sin to even indices in the array; 2i
  angle_rads[:, 0::2] = np.sin(angle_rads[:, 0::2])

  # apply cos to odd indices in the array; 2i+1
  angle_rads[:, 1::2] = np.cos(angle_rads[:, 1::2])

  pos_encoding = angle_rads[np.newaxis, ...]

  return tf.cast(pos_encoding, dtype=tf.float32)

def create_padding_mask(seq):
  seq = tf.cast(tf.math.equal(seq, 0), tf.float32)

  # add extra dimensions to add the padding
  # to the attention logits.
  return seq[:, tf.newaxis, tf.newaxis, :]  # (batch_size, 1, 1, seq_len)

def create_look_ahead_mask(size):
  mask = 1 - tf.linalg.band_part(tf.ones((size, size)), -1, 0)
  return mask  # (seq_len, seq_len)

def scaled_dot_product_attention(q, k, v, mask):
  """Calculate the attention weights.
  q, k, v must have matching leading dimensions.
  k, v must have matching penultimate dimension, i.e.: seq_len_k = seq_len_v.
  The mask has different shapes depending on its type(padding or look ahead)
  but it must be broadcastable for addition.

  Args:
    q: query shape == (..., seq_len_q, depth)
    k: key shape == (..., seq_len_k, depth)
    v: value shape == (..., seq_len_v, depth_v)
    mask: Float tensor with shape broadcastable
          to (..., seq_len_q, seq_len_k). Defaults to None.

  Returns:
    output, attention_weights
  """

  matmul_qk = tf.matmul(q, k, transpose_b=True)  # (..., seq_len_q, seq_len_k)

  # scale matmul_qk
  dk = tf.cast(tf.shape(k)[-1], tf.float32)
  scaled_attention_logits = matmul_qk / tf.math.sqrt(dk)

  # add the mask to the scaled tensor.
  if mask is not None:
    scaled_attention_logits += (mask * -1e9)

  # softmax is normalized on the last axis (seq_len_k) so that the scores
  # add up to 1.
  attention_weights = tf.nn.softmax(scaled_attention_logits, axis=-1)  # (..., seq_len_q, seq_len_k)

  output = tf.matmul(attention_weights, v)  # (..., seq_len_q, depth_v)

  return output, attention_weights

def print_out(q, k, v):
  temp_out, temp_attn = scaled_dot_product_attention(
      q, k, v, None)
  print('Attention weights are:')
  print(temp_attn)
  print('Output is:')
  print(temp_out)

class MultiHeadAttention(tf.keras.layers.Layer):
  def __init__(self, d_model, num_heads):
    super(MultiHeadAttention, self).__init__()
    self.num_heads = num_heads
    self.d_model = d_model

    assert d_model % self.num_heads == 0

    self.depth = d_model // self.num_heads

    self.wq = tf.keras.layers.Dense(d_model)
    self.wk = tf.keras.layers.Dense(d_model)
    self.wv = tf.keras.layers.Dense(d_model)

    self.dense = tf.keras.layers.Dense(d_model)

  def split_heads(self, x, batch_size):
    """Split the last dimension into (num_heads, depth).
    Transpose the result such that the shape is (batch_size, num_heads, seq_len, depth)
    """
    x = tf.reshape(x, (batch_size, -1, self.num_heads, self.depth))
    return tf.transpose(x, perm=[0, 2, 1, 3])

  def call(self, v, k, q, mask):
    batch_size = tf.shape(q)[0]

    q = self.wq(q)  # (batch_size, seq_len, d_model)
    k = self.wk(k)  # (batch_size, seq_len, d_model)
    v = self.wv(v)  # (batch_size, seq_len, d_model)

    q = self.split_heads(q, batch_size)  # (batch_size, num_heads, seq_len_q, depth)
    k = self.split_heads(k, batch_size)  # (batch_size, num_heads, seq_len_k, depth)
    v = self.split_heads(v, batch_size)  # (batch_size, num_heads, seq_len_v, depth)

    # scaled_attention.shape == (batch_size, num_heads, seq_len_q, depth)
    # attention_weights.shape == (batch_size, num_heads, seq_len_q, seq_len_k)
    scaled_attention, attention_weights = scaled_dot_product_attention(
        q, k, v, mask)

    scaled_attention = tf.transpose(scaled_attention, perm=[0, 2, 1, 3])  # (batch_size, seq_len_q, num_heads, depth)

    concat_attention = tf.reshape(scaled_attention,
                                  (batch_size, -1, self.d_model))  # (batch_size, seq_len_q, d_model)

    output = self.dense(concat_attention)  # (batch_size, seq_len_q, d_model)

    return output, attention_weights

def point_wise_feed_forward_network(d_model, dff):
  return tf.keras.Sequential([
      tf.keras.layers.Dense(dff, activation='relu'),  # (batch_size, seq_len, dff)
      tf.keras.layers.Dense(d_model)  # (batch_size, seq_len, d_model)
  ])

class EncoderLayer(tf.keras.layers.Layer):
  def __init__(self, d_model, num_heads, dff, rate=0.1):
    super(EncoderLayer, self).__init__()

    self.mha = MultiHeadAttention(d_model, num_heads)
    self.ffn = point_wise_feed_forward_network(d_model, dff)

    self.layernorm1 = tf.keras.layers.LayerNormalization(epsilon=1e-6)
    self.layernorm2 = tf.keras.layers.LayerNormalization(epsilon=1e-6)

    self.dropout1 = tf.keras.layers.Dropout(rate)
    self.dropout2 = tf.keras.layers.Dropout(rate)

  def call(self, x, training, mask):

    attn_output, _ = self.mha(x, x, x, mask)  # (batch_size, input_seq_len, d_model)
    attn_output = self.dropout1(attn_output, training=training)
    out1 = self.layernorm1(x + attn_output)  # (batch_size, input_seq_len, d_model)

    ffn_output = self.ffn(out1)  # (batch_size, input_seq_len, d_model)
    ffn_output = self.dropout2(ffn_output, training=training)
    out2 = self.layernorm2(out1 + ffn_output)  # (batch_size, input_seq_len, d_model)

    return out2

class DecoderLayer(tf.keras.layers.Layer):
  def __init__(self, d_model, num_heads, dff, rate=0.1):
    super(DecoderLayer, self).__init__()

    self.mha1 = MultiHeadAttention(d_model, num_heads)
    self.mha2 = MultiHeadAttention(d_model, num_heads)

    self.ffn = point_wise_feed_forward_network(d_model, dff)

    self.layernorm1 = tf.keras.layers.LayerNormalization(epsilon=1e-6)
    self.layernorm2 = tf.keras.layers.LayerNormalization(epsilon=1e-6)
    self.layernorm3 = tf.keras.layers.LayerNormalization(epsilon=1e-6)

    self.dropout1 = tf.keras.layers.Dropout(rate)
    self.dropout2 = tf.keras.layers.Dropout(rate)
    self.dropout3 = tf.keras.layers.Dropout(rate)

  def call(self, x, enc_output, training,
           look_ahead_mask, padding_mask):
    # enc_output.shape == (batch_size, input_seq_len, d_model)

    attn1, attn_weights_block1 = self.mha1(x, x, x, look_ahead_mask)  # (batch_size, target_seq_len, d_model)
    attn1 = self.dropout1(attn1, training=training)
    out1 = self.layernorm1(attn1 + x)

    attn2, attn_weights_block2 = self.mha2(
        enc_output, enc_output, out1, padding_mask)  # (batch_size, target_seq_len, d_model)
    attn2 = self.dropout2(attn2, training=training)
    out2 = self.layernorm2(attn2 + out1)  # (batch_size, target_seq_len, d_model)

    ffn_output = self.ffn(out2)  # (batch_size, target_seq_len, d_model)
    ffn_output = self.dropout3(ffn_output, training=training)
    out3 = self.layernorm3(ffn_output + out2)  # (batch_size, target_seq_len, d_model)

    return out3, attn_weights_block1, attn_weights_block2

class Encoder(tf.keras.layers.Layer):
  def __init__(self, num_layers, d_model, num_heads, dff, input_vocab_size,
               maximum_position_encoding, rate=0.1):
    super(Encoder, self).__init__()

    self.d_model = d_model
    self.num_layers = num_layers

    self.embedding = tf.keras.layers.Embedding(input_vocab_size, d_model)
    self.pos_encoding = positional_encoding(maximum_position_encoding,
                                            self.d_model)

    self.enc_layers = [EncoderLayer(d_model, num_heads, dff, rate)
                       for _ in range(num_layers)]

    self.dropout = tf.keras.layers.Dropout(rate)

  def call(self, x, training, mask):

    seq_len = tf.shape(x)[1]

    # adding embedding and position encoding.
    x = self.embedding(x)  # (batch_size, input_seq_len, d_model)
    x *= tf.math.sqrt(tf.cast(self.d_model, tf.float32))
    x += self.pos_encoding[:, :seq_len, :]

    x = self.dropout(x, training=training)

    for i in range(self.num_layers):
      x = self.enc_layers[i](x, training, mask)

    return x  # (batch_size, input_seq_len, d_model)

class Decoder(tf.keras.layers.Layer):
  def __init__(self, num_layers, d_model, num_heads, dff, target_vocab_size,
               maximum_position_encoding, rate=0.1):
    super(Decoder, self).__init__()

    self.d_model = d_model
    self.num_layers = num_layers

    self.embedding = tf.keras.layers.Embedding(target_vocab_size, d_model)
    self.pos_encoding = positional_encoding(maximum_position_encoding, d_model)

    self.dec_layers = [DecoderLayer(d_model, num_heads, dff, rate)
                       for _ in range(num_layers)]
    self.dropout = tf.keras.layers.Dropout(rate)

  def call(self, x, enc_output, training,
           look_ahead_mask, padding_mask):

    seq_len = tf.shape(x)[1]
    attention_weights = {}

    x = self.embedding(x)  # (batch_size, target_seq_len, d_model)
    x *= tf.math.sqrt(tf.cast(self.d_model, tf.float32))
    x += self.pos_encoding[:, :seq_len, :]

    x = self.dropout(x, training=training)

    for i in range(self.num_layers):
      x, block1, block2 = self.dec_layers[i](x, enc_output, training,
                                             look_ahead_mask, padding_mask)

      attention_weights[f'decoder_layer{i+1}_block1'] = block1
      attention_weights[f'decoder_layer{i+1}_block2'] = block2

    # x.shape == (batch_size, target_seq_len, d_model)
    return x, attention_weights

class Transformer(tf.keras.Model):
  def __init__(self, num_layers, d_model, num_heads, dff, input_vocab_size,
               target_vocab_size, pe_input, pe_target, rate=0.1):
    super().__init__()
    self.encoder = Encoder(num_layers, d_model, num_heads, dff,
                             input_vocab_size, pe_input, rate)

    self.decoder = Decoder(num_layers, d_model, num_heads, dff,
                           target_vocab_size, pe_target, rate)

    self.final_layer = tf.keras.layers.Dense(target_vocab_size)

  def call(self, inputs, training):
    # Keras models prefer if you pass all your inputs in the first argument
    inp, tar = inputs

    enc_padding_mask, look_ahead_mask, dec_padding_mask = self.create_masks(inp, tar)

    enc_output = self.encoder(inp, training, enc_padding_mask)  # (batch_size, inp_seq_len, d_model)

    # dec_output.shape == (batch_size, tar_seq_len, d_model)
    dec_output, attention_weights = self.decoder(
        tar, enc_output, training, look_ahead_mask, dec_padding_mask)

    final_output = self.final_layer(dec_output)  # (batch_size, tar_seq_len, target_vocab_size)

    return final_output, attention_weights

  def create_masks(self, inp, tar):
    # Encoder padding mask
    enc_padding_mask = create_padding_mask(inp)

    # Used in the 2nd attention block in the decoder.
    # This padding mask is used to mask the encoder outputs.
    dec_padding_mask = create_padding_mask(inp)

    # Used in the 1st attention block in the decoder.
    # It is used to pad and mask future tokens in the input received by
    # the decoder.
    look_ahead_mask = create_look_ahead_mask(tf.shape(tar)[1])
    dec_target_padding_mask = create_padding_mask(tar)
    look_ahead_mask = tf.maximum(dec_target_padding_mask, look_ahead_mask)

    return enc_padding_mask, look_ahead_mask, dec_padding_mask

#st.write("Model Initialization Finished.")

num_layers = 4
d_model = 256
dff = 512
num_heads = 8
dropout_rate = 0.15


#@st.cache(suppress_st_warning=True,allow_output_mutation = True,ttl=60*60*2)
def model_load():
  transformer = Transformer(
    num_layers=num_layers,
    d_model=d_model,
    num_heads=num_heads,
    dff=dff,
    input_vocab_size=input_vocab,
    target_vocab_size=output_vocab,
    pe_input=1000,
    pe_target=1000,
    rate=dropout_rate)

  ckpt = tf.train.Checkpoint(transformer=transformer)
  ckpt.restore("/app/transformer-text-generation/checkpoint/ckpt-3")
  return transformer

transformer = model_load()

#st.write("Checkpoint Recalling Finished.")

class Generator(tf.Module):
  def __init__(self, inp_tokenizers, target_tokenizers, transformer):
    self.inp_tokenizers = inp_tokenizers
    self.target_tokenizers = target_tokenizers
    self.transformer = transformer

  def __call__(self, sentence, max_length=20):
    # input sentence is portuguese, hence adding the start and end token
    sentence = tf.convert_to_tensor(self.inp_tokenizers.texts_to_sequences([sentence]), dtype=tf.int64)

    encoder_input = sentence

    # as the target is english, the first token to the transformer should be the
    # english start token.
    start_end = tf.convert_to_tensor(self.target_tokenizers.texts_to_sequences(['<start> <end>'])[0], dtype=tf.int64)
    start = start_end[0][tf.newaxis]
    end = start_end[1][tf.newaxis]

    # `tf.TensorArray` is required here (instead of a python list) so that the
    # dynamic-loop can be traced by `tf.function`.
    output_array = tf.TensorArray(dtype=tf.int64, size=0, dynamic_size=True)
    output_array = output_array.write(0, start)

    for i in tf.range(max_length):
      output = tf.transpose(output_array.stack())
      predictions, _ = self.transformer([encoder_input, output], training=False)

      # select the last token from the seq_len dimension
      predictions = predictions[:, -1:, :]  # (batch_size, 1, vocab_size)

      predicted_id = tf.argmax(predictions, axis=-1)

      # concatentate the predicted_id to the output which is given to the decoder
      # as its input.
      output_array = output_array.write(i + 1, predicted_id[0])

      if predicted_id == end:
        break

    output = tf.transpose(output_array.stack())
    # output.shape (1, tokens)
    text = self.target_tokenizers.sequences_to_texts(output.numpy())[0]  # shape: ()

    # `tf.function` prevents us from using the attention_weights that were
    # calculated on the last iteration of the loop. So recalculate them outside
    # the loop.
    _, attention_weights = self.transformer([encoder_input, output[:, :-1]], training=False)

    return text, attention_weights

generator = Generator(inp_tokenizer, targ_tokenizer, transformer)


def Generate(sentence, length):
  if sentence[-1] == ' ':
    sentence = sentence[:-1:]
  if sentence[0] == ' ':
    sentence = sentence[1:]
  sentence = "<start>" + ' ' + sentence + ' ' + "<end>"
  sentence_list = []
  sentence_list.append(sentence)
  for i in range(length):
    if i == 0:
      generated_text, attention_weights = generator(sentence_list[i])
      sentence_list[i] = sentence_list[i].replace('<start> ', "")
      sentence_list[i] = sentence_list[i].replace(' <end>', "")
      if sentence_list[i][-1] == ' ':
        sentence_list[i] = sentence_list[i][:-1:]
      if sentence_list[i][0] == ' ':
        sentence_list[i] = sentence_list[i][1:]
      # print(sentence_list[i])
    else:
      generated_text, attention_weights = generator(
        "<start> " + sentence_list[i - 1] + " " + sentence_list[i] + " <end>")
    generated_text = generated_text.replace('<start> ', "")
    generated_text = generated_text.replace(' <end>', "")
    if generated_text[-1] == ' ':
      generated_text = generated_text[:-1:]
    if generated_text[0] == ' ':
      generated_text = generated_text[1:]
    sentence_list.append(generated_text)
    # print(generated_text)
  output = ""

  for i in sentence_list:
    output = output + ' ' + i
  return output

#placeholder2.empty()
#st.write("Generator initilization Finished.")

input_text = st.text_input("Enter Initial text","")
strlength = st.text_input("Please input times of the model to run (1 or 2 is recommended)","")
if st.button('Generate'):
  if not(strlength.strip().isdigit()):
    disclaimer2 = "Please input times of the model to run in positive integer."
    st.write(disclaimer2)
    st.write("Please try again.")
  elif int(strlength) > 6 or int(strlength) <= 0:
    disclaimer3 = "Please input times of the model to run in positive integer in range of 1-5."
    st.write(disclaimer3)
    st.write("Please try again.")
  else :
    length = int(strlength)
    placeholder = st.empty()
    disclaimer = "Disclaimer : Generation may take a minute (can be up to 1-2 minutes) "
    dis_style = '<p style="font-family:"Times New Roman"; font-size: 14px;">' + disclaimer + '</p>' + '<p style="font-family:"Times New Roman"; font-size: 14px;">' + "Generating..." + '</p>'
    placeholder.markdown(dis_style, unsafe_allow_html=True)
    output = Generate(input_text, length)
    placeholder.empty()
    st.write("Result:")
    output_Text = '<p style="font-family:"Times New Roman"; font-size: 14px;">' + output + '</p>'
    st.markdown(output_Text, unsafe_allow_html=True)