fork download
copy 
  1. import numpy as np
  2. from tensorflow.keras.models import Sequential
  3. from tensorflow.keras.layers import Embedding, SimpleRNN, Dense
  4. # Generate some example data
  5. num_samples = 1000
  6. sequence_length = 10
  7. vocab_size = 10000
  8. X = np.random.randint(vocab_size,size=(num_samples,sequence_length))
  9. y = np.random.randint(2, size=num_samples)
  10. # Build the RNN model
  11. model = Sequential()
  12. model.add(Embedding(vocab_size, 32, input_length=sequence_length))
  13. model.add(SimpleRNN(64))
  14. model.add(Dense(1, activation='sigmoid'))
  15. model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
  16. # Train the model
  17. model.fit(X, y, epochs=10, batch_size=32, validation_split=0.2)
  18.  
Success #stdin #stdout #stderr 3.6s 257924KB
comments (?)
stdin
copy 
Standard input is empty
stdout
copy 
Train on 800 samples, validate on 200 samples
Epoch 1/10

 32/800 [>.............................] - ETA: 12s - loss: 0.6876 - acc: 0.6250
288/800 [=========>....................] - ETA: 1s - loss: 0.6936 - acc: 0.5069 
576/800 [====================>.........] - ETA: 0s - loss: 0.6925 - acc: 0.4931
800/800 [==============================] - 1s 925us/sample - loss: 0.6911 - acc: 0.5200 - val_loss: 0.6958 - val_acc: 0.4850
Epoch 2/10

 32/800 [>.............................] - ETA: 0s - loss: 0.5925 - acc: 0.9062
288/800 [=========>....................] - ETA: 0s - loss: 0.5567 - acc: 0.9514
544/800 [===================>..........] - ETA: 0s - loss: 0.4807 - acc: 0.9449
800/800 [==============================] - 0s 209us/sample - loss: 0.3929 - acc: 0.9475 - val_loss: 1.1414 - val_acc: 0.4900
Epoch 3/10

 32/800 [>.............................] - ETA: 0s - loss: 0.0218 - acc: 1.0000
288/800 [=========>....................] - ETA: 0s - loss: 0.0185 - acc: 0.9931
576/800 [====================>.........] - ETA: 0s - loss: 0.0125 - acc: 0.9965
800/800 [==============================] - 0s 213us/sample - loss: 0.0100 - acc: 0.9975 - val_loss: 1.8613 - val_acc: 0.5050
Epoch 4/10

 32/800 [>.............................] - ETA: 0s - loss: 0.0016 - acc: 1.0000
288/800 [=========>....................] - ETA: 0s - loss: 0.0011 - acc: 1.0000
544/800 [===================>..........] - ETA: 0s - loss: 0.0012 - acc: 1.0000
800/800 [==============================] - 0s 209us/sample - loss: 0.0010 - acc: 1.0000 - val_loss: 1.9508 - val_acc: 0.5000
Epoch 5/10

 32/800 [>.............................] - ETA: 0s - loss: 7.2196e-04 - acc: 1.0000
288/800 [=========>....................] - ETA: 0s - loss: 6.8007e-04 - acc: 1.0000
544/800 [===================>..........] - ETA: 0s - loss: 6.7829e-04 - acc: 1.0000
800/800 [==============================] - 0s 218us/sample - loss: 6.6577e-04 - acc: 1.0000 - val_loss: 1.9890 - val_acc: 0.5050
Epoch 6/10

 32/800 [>.............................] - ETA: 0s - loss: 6.4435e-04 - acc: 1.0000
288/800 [=========>....................] - ETA: 0s - loss: 5.7625e-04 - acc: 1.0000
544/800 [===================>..........] - ETA: 0s - loss: 5.7409e-04 - acc: 1.0000
800/800 [==============================] - 0s 206us/sample - loss: 5.6187e-04 - acc: 1.0000 - val_loss: 2.0264 - val_acc: 0.4950
Epoch 7/10

 32/800 [>.............................] - ETA: 0s - loss: 4.9777e-04 - acc: 1.0000
288/800 [=========>....................] - ETA: 0s - loss: 4.9924e-04 - acc: 1.0000
576/800 [====================>.........] - ETA: 0s - loss: 5.0001e-04 - acc: 1.0000
800/800 [==============================] - 0s 210us/sample - loss: 4.8474e-04 - acc: 1.0000 - val_loss: 2.0616 - val_acc: 0.4950
Epoch 8/10

 32/800 [>.............................] - ETA: 0s - loss: 3.8722e-04 - acc: 1.0000
320/800 [===========>..................] - ETA: 0s - loss: 4.3908e-04 - acc: 1.0000
576/800 [====================>.........] - ETA: 0s - loss: 4.2555e-04 - acc: 1.0000
800/800 [==============================] - 0s 206us/sample - loss: 4.2353e-04 - acc: 1.0000 - val_loss: 2.0946 - val_acc: 0.4950
Epoch 9/10

 32/800 [>.............................] - ETA: 0s - loss: 3.7789e-04 - acc: 1.0000
288/800 [=========>....................] - ETA: 0s - loss: 3.8296e-04 - acc: 1.0000
544/800 [===================>..........] - ETA: 0s - loss: 3.7374e-04 - acc: 1.0000
800/800 [==============================] - 0s 209us/sample - loss: 3.7394e-04 - acc: 1.0000 - val_loss: 2.1265 - val_acc: 0.4950
Epoch 10/10

 32/800 [>.............................] - ETA: 0s - loss: 3.1559e-04 - acc: 1.0000
288/800 [=========>....................] - ETA: 0s - loss: 3.3319e-04 - acc: 1.0000
544/800 [===================>..........] - ETA: 0s - loss: 3.3761e-04 - acc: 1.0000
800/800 [==============================] - 0s 208us/sample - loss: 3.3285e-04 - acc: 1.0000 - val_loss: 2.1576 - val_acc: 0.4950
stderr
copy 
WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/resource_variable_ops.py:435: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version.
Instructions for updating:
Colocations handled automatically by placer.
WARNING:tensorflow:From /usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.cast instead.
https://ideone.com/JhV2n5
language:
Python (cpython 2.7.16)
created:
2 days ago
visibility:
public

Share or Embed source code

Discover > Sphere Engine API

The brand new service which powers Ideone!

Discover > IDE Widget

Widget for compiling and running the source code in a web browser!