首页 > 解决方案 > 用于再训练示例中验证的 TensorFlow 混淆矩阵

问题描述

我一直在使用 github tensorflow hub 上的保留示例,在尝试添加这两件事时遇到了一些问题:

  1. 基于最终测试结果的混淆矩阵
  2. 一种记录测试集中每次评估时间的方法将其添加到数组中

这是重新训练示例的链接

混淆矩阵

对于混淆矩阵,我将运行评估函数更改为以下

def run_final_eval(train_session, module_spec, class_count, image_lists,
               jpeg_data_tensor, decoded_image_tensor,
               resized_image_tensor, bottleneck_tensor):
#Runs a final evaluation on an eval graph using the test data set.

Args:


   train_session: Session for the train graph with the tensors below.
    module_spec: The hub.ModuleSpec for the image module being used.
    class_count: Number of classes
    image_lists: OrderedDict of training images for each label.
    jpeg_data_tensor: The layer to feed jpeg image data into.
    decoded_image_tensor: The output of decoding and resizing the image.
    resized_image_tensor: The input node of the recognition graph.
    bottleneck_tensor: The bottleneck output layer of the CNN graph.

  test_bottlenecks, test_ground_truth, test_filenames = (
      get_random_cached_bottlenecks(train_session, image_lists,
                                    FLAGS.test_batch_size,
                                    'testing', FLAGS.bottleneck_dir,
                                    FLAGS.image_dir, jpeg_data_tensor,
                                    decoded_image_tensor, resized_image_tensor,
                                    bottleneck_tensor, FLAGS.tfhub_module))

  (eval_session, _, bottleneck_input, ground_truth_input, evaluation_step,
   prediction) = build_eval_session(module_spec, class_count)
  test_accuracy, predictions = eval_session.run(
      [evaluation_step, prediction],
      feed_dict={
          bottleneck_input: test_bottlenecks,
          ground_truth_input: test_ground_truth
      })
  tf.logging.info('Final test accuracy = %.1f%% (N=%d)' %
                  (test_accuracy * 100, len(test_bottlenecks)))

  confusion = tf.confusion_matrix(labels=test_ground_truth, predictions=predictions,num_classes=class_count)
  print(confusion)

  if FLAGS.print_misclassified_test_images:
    tf.logging.info('=== MISCLASSIFIED TEST IMAGES ===')
    for i, test_filename in enumerate(test_filenames):
      if predictions[i] != test_ground_truth[i]:
        tf.logging.info('%70s  %s' % (test_filename,
                                      list(image_lists.keys())[predictions[i]]))

输出是:

INFO:tensorflow:Final test accuracy = 88.5% (N=710)
INFO:tensorflow:=== CONwaka ===
Tensor("confusion_matrix/SparseTensorDenseAdd:0", shape=(5, 5), dtype=int32)

我也尝试使用 tf.logging.info 得到相同的结果。我想以数组形式打印出来。我找到了 MLninja 的这个答案,这似乎也是一个更好的解决方案,但我不知道如何在重新训练文件中实现它。

非常感谢任何帮助!

标签: pythontensorflowmachine-learningdeep-learning

解决方案


您需要评估混淆矩阵张量。现在您将混淆矩阵运算添加到图形并打印操作,但是您想要打印运算的结果,即矩阵。在代码中,它看起来像这样:

confusion_matrix_np = eval_session.run(
  confusion,
  feed_dict={
      bottleneck_input: test_bottlenecks,
      ground_truth_input: test_ground_truth
  })

print(confusion_matrix_np)

推荐阅读