My computer almost stalls whenever I try to use a Bidirectional layer. I'm using Macos M1 with tensorflow-macos 2.5 tensorflow-metal 0.1.2, tensorflow-deps 2.5.0.
Bellow I show 2 short snippets of demo code: one working (without Bidirectional), one not-working (with Bidirectional).
import tensorflow as tf
from tensorflow.keras.datasets import imdb
from tensorflow.keras.layers import Embedding, Dense, LSTM
from tensorflow.keras.losses import BinaryCrossentropy
from tensorflow.keras.models import Sequential
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.layers import SimpleRNN, Bidirectional, Masking
import tensorflow_addons as tfa
additional_metrics = ['accuracy']
batch_size = 128
embedding_output_dims = 15
loss_function = BinaryCrossentropy()
max_sequence_length = 300
num_distinct_words = 5000
number_of_epochs = 5
optimizer = Adam()
optimizer = tfa.optimizers.RectifiedAdam(learning_rate=0.01, clipnorm=0.5)
validation_split = 0.20
verbosity_mode = 1
def working_demo_LSTM():
# Load dataset
(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=num_distinct_words)
print(x_train.shape)
print(x_test.shape)
# Pad all sequences
padded_inputs = pad_sequences(x_train, maxlen=max_sequence_length,
value=0.0) # 0.0 because it corresponds with <PAD>
padded_inputs_test = pad_sequences(x_test, maxlen=max_sequence_length,
value=0.0) # 0.0 because it corresponds with <PAD>
# Define the Keras model
model = Sequential()
model.add(Embedding(num_distinct_words, embedding_output_dims, input_length=max_sequence_length))
model.add(LSTM(10))
model.add(Dense(1, activation='sigmoid'))
# Compile the model
model.compile(optimizer=optimizer, loss=loss_function, metrics=additional_metrics)
# Give a summary
model.summary()
history = model.fit(padded_inputs, y_train, batch_size=batch_size, epochs=number_of_epochs,
verbose=verbosity_mode, validation_split=validation_split)
# Test the model after training
test_results = model.evaluate(padded_inputs_test, y_test, verbose=False)
print(f'Test results - Loss: {test_results[0]} - Accuracy: {100*test_results[1]}%')
return True
def nonworking_demo():
# Load dataset
(x_train, y_train), (x_test, y_test) = imdb.load_data(num_words=num_distinct_words)
print(x_train.shape)
print(x_test.shape)
# Pad all sequences
padded_inputs = pad_sequences(x_train, maxlen=max_sequence_length,
value=0.0) # 0.0 because it corresponds with <PAD>
padded_inputs_test = pad_sequences(x_test, maxlen=max_sequence_length,
value=0.0) # 0.0 because it corresponds with <PAD>
# Define the Keras model
model = Sequential()
model.add(Embedding(num_distinct_words, embedding_output_dims, input_length=max_sequence_length))
model.add(Bidirectional(SimpleRNN(units=10, return_sequences=True)))
model.add(Dense(1, activation='sigmoid'))
# Compile the model
model.compile(optimizer=optimizer, loss=loss_function, metrics=additional_metrics)
# Give a summary
# model.summary()
history = model.fit(padded_inputs, y_train, batch_size=batch_size, epochs=number_of_epochs,
verbose=verbosity_mode, validation_split=validation_split)
# Test the model after training
test_results = model.evaluate(padded_inputs_test, y_test, verbose=False)
print(f'Test results - Loss: {test_results[0]} - Accuracy: {100*test_results[1]}%')
return True
def main():
# working_demo_LSTM()
nonworking_demo_BLSTM()
if __name__ == "__main__":
main()
I'm getting the following warnings and the computer stalls whenever I run nonworking_demo_BLSTM() with
with tf.device('/cpu:0'): I get 7secs per epoch. If I don't explicitly select CPU, I get a ETA of 05:44:30 just for the 1st epoch!
Are these values normal?
