132 lines
4.1 KiB
Python
132 lines
4.1 KiB
Python
import tensorflow as tf
|
|
from tensorflow.keras.layers.experimental import preprocessing
|
|
|
|
import numpy as np
|
|
import os
|
|
import time
|
|
|
|
import discord
|
|
import re
|
|
|
|
path_to_file = "/Users/frank/Documents/Code/tensorflow/messages.txt"
|
|
|
|
text = open(path_to_file, 'rb').read().decode('utf-8')
|
|
print(f'Length of text: {len(text)} characters')
|
|
print()
|
|
|
|
print('First 250 characters:')
|
|
print(text[:250])
|
|
|
|
print()
|
|
vocab = sorted(set(text))
|
|
print(f'{len(vocab)} unique characters.')
|
|
|
|
example_texts = ['abcdefg', 'xyz']
|
|
chars = tf.strings.unicode_split(example_texts, input_encoding='UTF-8')
|
|
print()
|
|
print(chars)
|
|
|
|
ids_from_chars = preprocessing.StringLookup(vocabulary=list(vocab))
|
|
ids = ids_from_chars(chars)
|
|
print(ids)
|
|
|
|
chars_from_ids = tf.keras.layers.experimental.preprocessing.StringLookup(vocabulary=ids_from_chars.get_vocabulary(), invert=True)
|
|
|
|
chars = chars_from_ids(ids)
|
|
print(chars)
|
|
|
|
def text_from_ids(ids):
|
|
return tf.strings.reduce_join(chars_from_ids(ids), axis=-1)
|
|
|
|
all_ids = ids_from_chars(tf.strings.unicode_split(text, 'UTF-8'))
|
|
print(all_ids)
|
|
|
|
ids_dataset = tf.data.Dataset.from_tensor_slices(all_ids)
|
|
for ids in ids_dataset.take(10):
|
|
print(chars_from_ids(ids).numpy().decode('utf-8'))
|
|
|
|
seq_length = 100
|
|
examples_per_epoch = len(text)
|
|
|
|
sequences = ids_dataset.batch(seq_length+1, drop_remainder=True)
|
|
|
|
for seq in sequences.take(1):
|
|
print(chars_from_ids(seq))
|
|
|
|
for seq in sequences.take(5):
|
|
print(text_from_ids(seq).numpy())
|
|
|
|
def split_input_target(sequence):
|
|
input_text = sequence[:-1]
|
|
target_text = sequence[1:]
|
|
return input_text, target_text
|
|
|
|
split_input_target(list("Tensorflow"))
|
|
|
|
class OneStep(tf.keras.Model):
|
|
def __init__(self, model, chars_from_ids, ids_from_chars, temperature=1.0):
|
|
super().__init__()
|
|
self.temperature = temperature
|
|
self.model = model
|
|
self.chars_from_ids = chars_from_ids
|
|
self.ids_from_chars = ids_from_chars
|
|
|
|
# Create a mask to prevent "" or "[UNK]" from being generated
|
|
skip_ids = self.ids_from_chars(['', '[UNK]'])[:, None]
|
|
sparse_mask = tf.SparseTensor(values=[-float('inf')]*len(skip_ids), indices=skip_ids, dense_shape=[len(ids_from_chars.get_vocabulary())])
|
|
self.prediction_mask = tf.sparse.to_dense(sparse_mask)
|
|
|
|
@tf.function
|
|
def generate_one_step(self, inputs, states=None):
|
|
input_chars = tf.strings.unicode_split(inputs, 'UTF-8')
|
|
input_ids = self.ids_from_chars(input_chars).to_tensor()
|
|
|
|
predicted_logits, states = self.model(inputs=input_ids, states=states, return_state=True)
|
|
|
|
predicted_logits = predicted_logits[:, -1, :]
|
|
predicted_logits = predicted_logits/self.temperature
|
|
|
|
predicted_logits = predicted_logits + self.prediction_mask
|
|
|
|
predicted_ids = tf.random.categorical(predicted_logits, num_samples=1)
|
|
predicted_ids = tf.squeeze(predicted_ids, axis=-1)
|
|
|
|
predicted_chars = self.chars_from_ids(predicted_ids)
|
|
|
|
|
|
one_step_reloaded = tf.saved_model.load('one_step')
|
|
|
|
states = None
|
|
next_char = tf.constant(['Hey '])
|
|
result = [next_char]
|
|
|
|
for n in range(256):
|
|
next_char, states = one_step_reloaded.generate_one_step(next_char, states=states)
|
|
result.append(next_char)
|
|
|
|
print(tf.strings.join(result)[0].numpy().decode('utf-8'))
|
|
|
|
class MyClient(discord.Client):
|
|
async def on_ready(self):
|
|
print("Loaded!")
|
|
|
|
|
|
async def on_message(self, message):
|
|
if (message.content.startswith('$frank ')):
|
|
print("Invoked!")
|
|
msg = message.content
|
|
msg = re.sub('\$frank ', '', msg)
|
|
msg = msg + ' '
|
|
print('Sent message:', msg)
|
|
states = None
|
|
next_char = tf.constant([msg])
|
|
result = [next_char]
|
|
|
|
for n in range(100):
|
|
next_char, states = one_step_reloaded.generate_one_step(next_char, states=states)
|
|
result.append(next_char)
|
|
await message.channel.send(tf.strings.join(result)[0].numpy().decode('utf-8'))
|
|
|
|
client = MyClient()
|
|
client.run('ODI5NDU2MDg0NjgzMDYzMzE3.YG4ZLQ.mGX2ZfR4GOEfQs76yXtlx3KqrhM')
|