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)
Success #stdin #stdout #stderr 4.1s 259768KB
comments (?)
stdin
copy 
Standard input is empty
stdout
copy 
Train on 800 samples, validate on 200 samples
Epoch 1/10

 32/800 [>.............................] - ETA: 6s - loss: 0.6930 - acc: 0.5000
320/800 [===========>..................] - ETA: 0s - loss: 0.6871 - acc: 0.5437
576/800 [====================>.........] - ETA: 0s - loss: 0.6911 - acc: 0.5087
768/800 [===========================>..] - ETA: 0s - loss: 0.6932 - acc: 0.5026
800/800 [==============================] - 1s 669us/sample - loss: 0.6941 - acc: 0.5013 - val_loss: 0.6927 - val_acc: 0.5250
Epoch 2/10

 32/800 [>.............................] - ETA: 0s - loss: 0.6171 - acc: 0.7812
288/800 [=========>....................] - ETA: 0s - loss: 0.5742 - acc: 0.9201
608/800 [=====================>........] - ETA: 0s - loss: 0.4966 - acc: 0.9391
800/800 [==============================] - 0s 215us/sample - loss: 0.4343 - acc: 0.9413 - val_loss: 0.9552 - val_acc: 0.5400
Epoch 3/10

 32/800 [>.............................] - ETA: 0s - loss: 0.0512 - acc: 1.0000
256/800 [========>.....................] - ETA: 0s - loss: 0.0356 - acc: 0.9922
512/800 [==================>...........] - ETA: 0s - loss: 0.0270 - acc: 0.9941
768/800 [===========================>..] - ETA: 0s - loss: 0.0202 - acc: 0.9961
800/800 [==============================] - 0s 227us/sample - loss: 0.0199 - acc: 0.9962 - val_loss: 1.3446 - val_acc: 0.5600
Epoch 4/10

 32/800 [>.............................] - ETA: 0s - loss: 0.0015 - acc: 1.0000
320/800 [===========>..................] - ETA: 0s - loss: 0.0014 - acc: 1.0000
576/800 [====================>.........] - ETA: 0s - loss: 0.0013 - acc: 1.0000
800/800 [==============================] - 0s 226us/sample - loss: 0.0013 - acc: 1.0000 - val_loss: 1.3533 - val_acc: 0.5500
Epoch 5/10

 32/800 [>.............................] - ETA: 0s - loss: 0.0010 - acc: 1.0000
288/800 [=========>....................] - ETA: 0s - loss: 7.9911e-04 - acc: 1.0000
544/800 [===================>..........] - ETA: 0s - loss: 7.7099e-04 - acc: 1.0000
800/800 [==============================] - 0s 202us/sample - loss: 7.1322e-04 - acc: 1.0000 - val_loss: 1.4214 - val_acc: 0.5500
Epoch 6/10

 32/800 [>.............................] - ETA: 0s - loss: 5.0569e-04 - acc: 1.0000
256/800 [========>.....................] - ETA: 0s - loss: 5.4215e-04 - acc: 1.0000
480/800 [=================>............] - ETA: 0s - loss: 5.4389e-04 - acc: 1.0000
736/800 [==========================>...] - ETA: 0s - loss: 5.3328e-04 - acc: 1.0000
800/800 [==============================] - 0s 249us/sample - loss: 5.2692e-04 - acc: 1.0000 - val_loss: 1.4784 - val_acc: 0.5650
Epoch 7/10

 32/800 [>.............................] - ETA: 0s - loss: 5.6823e-04 - acc: 1.0000
352/800 [============>.................] - ETA: 0s - loss: 4.6431e-04 - acc: 1.0000
608/800 [=====================>........] - ETA: 0s - loss: 4.4039e-04 - acc: 1.0000
800/800 [==============================] - 0s 218us/sample - loss: 4.3248e-04 - acc: 1.0000 - val_loss: 1.5269 - val_acc: 0.5750
Epoch 8/10

 32/800 [>.............................] - ETA: 0s - loss: 3.9590e-04 - acc: 1.0000
256/800 [========>.....................] - ETA: 0s - loss: 3.9544e-04 - acc: 1.0000
480/800 [=================>............] - ETA: 0s - loss: 3.6483e-04 - acc: 1.0000
768/800 [===========================>..] - ETA: 0s - loss: 3.6551e-04 - acc: 1.0000
800/800 [==============================] - 0s 219us/sample - loss: 3.6599e-04 - acc: 1.0000 - val_loss: 1.5677 - val_acc: 0.5700
Epoch 9/10

 32/800 [>.............................] - ETA: 0s - loss: 2.8223e-04 - acc: 1.0000
288/800 [=========>....................] - ETA: 0s - loss: 3.3945e-04 - acc: 1.0000
512/800 [==================>...........] - ETA: 0s - loss: 3.2262e-04 - acc: 1.0000
768/800 [===========================>..] - ETA: 0s - loss: 3.1685e-04 - acc: 1.0000
800/800 [==============================] - 0s 239us/sample - loss: 3.1742e-04 - acc: 1.0000 - val_loss: 1.6062 - val_acc: 0.5750
Epoch 10/10

 32/800 [>.............................] - ETA: 0s - loss: 2.8345e-04 - acc: 1.0000
320/800 [===========>..................] - ETA: 0s - loss: 2.8331e-04 - acc: 1.0000
608/800 [=====================>........] - ETA: 0s - loss: 2.8075e-04 - acc: 1.0000
800/800 [==============================] - 0s 208us/sample - loss: 2.7884e-04 - acc: 1.0000 - val_loss: 1.6409 - val_acc: 0.5700
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/L0kUOc
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!