| # Install tensorflow for macOS from https://github.com/apple/tensorflow_macos | |
| import argparse | |
| import tensorflow as tf | |
| from tensorflow.keras import datasets, layers, models | |
| from tensorflow.python.compiler.mlcompute import mlcompute | |
| def get_dataset(hparams): | |
| (train_images, train_labels), (test_images, |
It is much simpler and faster to access the various school's servers when connected to the School of Informatics OpenVPN.
| def evaluate(sentence): | |
| sentence = preprocess_sentence(sentence) | |
| sentence = tf.expand_dims( | |
| START_TOKEN + tokenizer.encode(sentence) + END_TOKEN, axis=0) | |
| output = tf.expand_dims(START_TOKEN, 0) | |
| for i in range(MAX_LENGTH): | |
| predictions = model(inputs=[sentence, output], training=False) |
| def loss_function(y_true, y_pred): | |
| y_true = tf.reshape(y_true, shape=(-1, MAX_LENGTH - 1)) | |
| loss = tf.keras.losses.SparseCategoricalCrossentropy( | |
| from_logits=True, reduction='none')(y_true, y_pred) | |
| mask = tf.cast(tf.not_equal(y_true, 0), tf.float32) | |
| loss = tf.multiply(loss, mask) | |
| return tf.reduce_mean(loss) |
| NUM_LAYERS = 2 | |
| D_MODEL = 256 | |
| NUM_HEADS = 8 | |
| UNITS = 512 | |
| DROPOUT = 0.1 | |
| model = transformer( | |
| vocab_size=VOCAB_SIZE, | |
| num_layers=NUM_LAYERS, | |
| units=UNITS, |
| def transformer(vocab_size, | |
| num_layers, | |
| units, | |
| d_model, | |
| num_heads, | |
| dropout, | |
| name="transformer"): | |
| inputs = tf.keras.Input(shape=(None,), name="inputs") | |
| dec_inputs = tf.keras.Input(shape=(None,), name="dec_inputs") |
| def decoder(vocab_size, | |
| num_layers, | |
| units, | |
| d_model, | |
| num_heads, | |
| dropout, | |
| name='decoder'): | |
| inputs = tf.keras.Input(shape=(None,), name='inputs') | |
| enc_outputs = tf.keras.Input(shape=(None, d_model), name='encoder_outputs') | |
| look_ahead_mask = tf.keras.Input( |
| def decoder_layer(units, d_model, num_heads, dropout, name="decoder_layer"): | |
| inputs = tf.keras.Input(shape=(None, d_model), name="inputs") | |
| enc_outputs = tf.keras.Input(shape=(None, d_model), name="encoder_outputs") | |
| look_ahead_mask = tf.keras.Input( | |
| shape=(1, None, None), name="look_ahead_mask") | |
| padding_mask = tf.keras.Input(shape=(1, 1, None), name='padding_mask') | |
| attention1 = MultiHeadAttention( | |
| d_model, num_heads, name="attention_1")(inputs={ | |
| 'query': inputs, |
| def encoder(vocab_size, | |
| num_layers, | |
| units, | |
| d_model, | |
| num_heads, | |
| dropout, | |
| name="encoder"): | |
| inputs = tf.keras.Input(shape=(None,), name="inputs") | |
| padding_mask = tf.keras.Input(shape=(1, 1, None), name="padding_mask") |