將多個softmax分類器添加到TensorFlow示例中

Question

我以通用TensorFlow示例開始。因爲我的數據攜帶多個獨立標籤（概率之和不是1），所以要對我的數據進行分類，我需要在最後一個圖層上使用多個標籤（理想情況下爲多個softmax分類器）。

具體表現在retrain.py在add_final_training_ops()這些線路在最後加上張

final_tensor = tf.nn.softmax(logits, name=final_tensor_name) 

這裏

cross_entropy = tf.nn.softmax_cross_entropy_with_logits(
     logits, ground_truth_input) 

有已經TensorFlow一個通用的分類？如果不是，如何實現多級分類？

add_final_training_ops()從tensorflow/examples/image_retraining/retrain.py：

def add_final_training_ops(class_count, final_tensor_name, bottleneck_tensor): 

    with tf.name_scope('input'): 
    bottleneck_input = tf.placeholder_with_default(
     bottleneck_tensor, shape=[None, BOTTLENECK_TENSOR_SIZE], 
     name='BottleneckInputPlaceholder') 

    ground_truth_input = tf.placeholder(tf.float32, 
             [None, class_count], 
             name='GroundTruthInput') 

    layer_name = 'final_training_ops' 
    with tf.name_scope(layer_name): 
    with tf.name_scope('weights'): 
     layer_weights = tf.Variable(tf.truncated_normal([BOTTLENECK_TENSOR_SIZE, class_count], stddev=0.001), name='final_weights') 
     variable_summaries(layer_weights) 
    with tf.name_scope('biases'): 
     layer_biases = tf.Variable(tf.zeros([class_count]), name='final_biases') 
     variable_summaries(layer_biases) 
    with tf.name_scope('Wx_plus_b'): 
     logits = tf.matmul(bottleneck_input, layer_weights) + layer_biases 
     tf.summary.histogram('pre_activations', logits) 

    final_tensor = tf.nn.softmax(logits, name=final_tensor_name) 
    tf.summary.histogram('activations', final_tensor) 

    with tf.name_scope('cross_entropy'): 
    cross_entropy = tf.nn.softmax_cross_entropy_with_logits(
     logits, ground_truth_input) 
    with tf.name_scope('total'): 
     cross_entropy_mean = tf.reduce_mean(cross_entropy) 
    tf.summary.scalar('cross_entropy', cross_entropy_mean) 

    with tf.name_scope('train'): 
    train_step = tf.train.GradientDescentOptimizer(FLAGS.learning_rate).minimize(
     cross_entropy_mean) 

    return (train_step, cross_entropy_mean, bottleneck_input, ground_truth_input, 
      final_tensor) 

即使添加了sigmoid分類和再培訓後，Tensorboard仍顯示softmax：

Answer 1

TensorFlow具有tf.nn.sigmoid_cross_entropy_with_logits獨立，多標籤分類。