When will you find overfit condition of your model in TensorFlow?

When will you find overfit condition of your model in TensorFlow?

Add Comment


  • 1 Answer(s)
    NUM_WORDS = 10000
    
    (train_data, train_labels), (test_data, test_labels) = keras.datasets.imdb.load_data(num_words=NUM_WORDS)
    
    def multi_hot_sequences(sequences, dimension):
        # Create an all-zero matrix of shape (len(sequences), dimension)
        results = np.zeros((len(sequences), dimension))
        for i, word_indices in enumerate(sequences):
            results[i, word_indices] = 1.0  # set specific indices of results[i] to 1s
        return results
    
    
    train_data = multi_hot_sequences(train_data, dimension=NUM_WORDS)
    test_data = multi_hot_sequences(test_data, dimension=NUM_WORDS)
    
    Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/imdb.npz
    17465344/17464789 [==============================] - 0s 0us/step
    

    Let’s look at one of the resulting multi-hot vectors. The word indices are sorted by frequency, so it is expected that there are more 1-values near index zero, as we can see in this plot:

    plt.plot(train_data[0])
    
    [<matplotlib.lines.Line2D at 0x7f2a85ff6a20>]

    png

    Answered on March 5, 2019.
    Add Comment


  • Your Answer

    By posting your answer, you agree to the privacy policy and terms of service.