SponsorBlock/model.py at main · ZachChuba/SponsorBlock · GitHub

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
import matplotlib.pyplot as plt
import os
import re
import shutil
import string
import pickle
import tensorflow as tf

from tensorflow.keras import layers
from tensorflow.keras import losses

def custom_standardization(input_data):
    lowercase = tf.strings.lower(input_data)
    # stripped_html = tf.strings.regex_replace(lowercase, '<br />', ' ')
    return tf.strings.regex_replace(lowercase,
                                    '[%s]' % re.escape(string.punctuation),
                                    '')

def main():
  easy_test_url = 'https://ai.stanford.edu/~amaas/data/sentiment/aclImdb_v1.tar.gz'
  print('Made it to fetch stage')
  my_file = os.path.abspath('./' + 'training_data')
  data_for_processing = tf.keras.utils.get_file('training_data',
                        f'file://{my_file}', cache_dir='.',
                        cache_subdir='')
  dataset_dir = os.path.join(os.path.dirname(data_for_processing), 'training_data')
  # os.listdir(dataset_dir)
  train_dir = os.path.join(dataset_dir, 'training_files')
  # os.listdir(train_dir)

  print ('Got to the processing stage')

  #remove_dir = os.path.join(train_dir, 'unsup')
  #shutil.rmtree(remove_dir)

  batch_size = 32
  seed = 42

  raw_train_ds = tf.keras.utils.text_dataset_from_directory(
      'training_data/training_files',
      batch_size=batch_size,
      validation_split=0.2,
      subset='training',
      seed=seed)

  raw_val_ds = tf.keras.utils.text_dataset_from_directory(
      'training_data/training_files',
      batch_size=batch_size,
      validation_split=0.2,
      subset='validation',
      seed=seed)

  raw_test_ds = tf.keras.utils.text_dataset_from_directory(
      'training_data/training_files',
      batch_size=batch_size)

  max_features = 10000
  sequence_length = 250

  vectorize_layer = layers.TextVectorization(
      standardize=custom_standardization,
      max_tokens=max_features,
      output_mode='int',
      output_sequence_length=sequence_length)

  # Make a text-only dataset (without labels), then call adapt
  train_text = raw_train_ds.map(lambda x, y: x)
  vectorize_layer.adapt(train_text)

  pickle.dump({'config': vectorize_layer.get_config(),
              'weights': vectorize_layer.get_weights(),},
              open('vectorize_config.pkl', 'wb'))

  def vectorize_text(text, label):
    text = tf.expand_dims(text, -1)
    return vectorize_layer(text), label

  '''
  text_batch, label_batch = next(iter(raw_train_ds))
  first_review, first_label = text_batch[0], label_batch[0]
  print("Review", first_review)
  print("Label", raw_train_ds.class_names[first_label])
  print("Vectorized review", vectorize_text(first_review, first_label))
  '''

  train_ds = raw_train_ds.map(vectorize_text)
  val_ds = raw_val_ds.map(vectorize_text)
  test_ds = raw_test_ds.map(vectorize_text)

  AUTOTUNE = tf.data.AUTOTUNE

  train_ds = train_ds.cache().prefetch(buffer_size=AUTOTUNE)
  val_ds = val_ds.cache().prefetch(buffer_size=AUTOTUNE)
  test_ds = test_ds.cache().prefetch(buffer_size=AUTOTUNE)

  embedding_dim = 16

  model = tf.keras.Sequential([
    layers.Embedding(max_features + 1, embedding_dim),
    layers.Dropout(0.2),
    layers.GlobalAveragePooling1D(),
    layers.Dropout(0.2),
    layers.Dense(1)])

  model.compile(loss=losses.BinaryCrossentropy(from_logits=True),
                optimizer='adam',
                metrics=tf.metrics.BinaryAccuracy(threshold=0.0))
  '''
  checkpoint_path = "training_1/cp.ckpt"
  checkpoint_dir = os.path.dirname(checkpoint_path)

  # Create a callback that saves the model's weights
  cp_callback = tf.keras.callbacks.ModelCheckpoint(filepath=checkpoint_path,
                                                  save_weights_only=True,
                                                  verbose=1)
  '''
  epochs = 10
  history = model.fit(
      train_ds,
      validation_data=val_ds,
      epochs=epochs,
      #callbacks=[cp_callback]
      )

  model.save('model.h5')

  # Load the saved weights
  '''
  # Loads the weights
  model.load_weights(checkpoint_path)

  # Re-evaluate the model
  loss, acc = model.evaluate(test_images, test_labels, verbose=2)
  print("Restored model, accuracy: {:5.2f}%".format(100 * acc))
  '''

  loss, accuracy = model.evaluate(test_ds)

  print("Loss: ", loss)
  print("Accuracy: ", accuracy)

if __name__ == '__main__':
  main()