Tensorflow 尝试使用未初始化的值 AUC/AUC/auc/false_positives [英] Tensorflow Attempting to use uninitialized value AUC/AUC/auc/false_positives

问题描述

我正在训练一个用于图像分类的 CNN.由于我的数据集大小有限，我正在使用迁移学习.基本上，我使用的是 Google 在其重新训练示例中证明的预训练网络 (https://www.tensorflow.org/tutorials/image_retraining).

I'm training a CNN using for image classification. Due to the limited size of my data set I'm using transfer learning. Basically, I'm using the pre-trained network Google is proving in its retrain example (https://www.tensorflow.org/tutorials/image_retraining).

该模型效果很好，并提供了非常好的准确性.但是我的数据集高度不平衡，这意味着准确性不是判断模型性能的最佳指标.

The model works great and gives a very good accuracy. But my dataset is highly imbalance which mean accuracy is not the best metric to judge the performance of the model.

通过研究不同的解决方案，一些人建议更改采样方法或使用的性能指标.我选择和后者一起去.

By looking into different solutions, some suggested changing the sampling method or the performance metric used. I'm choosing to go with the later.

Tensorflow 提供了很好的指标，包括 AUC、精度、召回率等.

Tensorflow provides a good verity of metrics including, AUC, precision, recall, etc.

现在，这里是重新训练模型的代码:https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/image_retraining/retrain.py

Now, here is the code of the retraing model: https://github.com/tensorflow/tensorflow/blob/master/tensorflow/examples/image_retraining/retrain.py

我将以下内容添加到 add_evaluation_step(result_tensor, ground_truth_tensor) 函数:

I'm adding the following to add_evaluation_step(result_tensor, ground_truth_tensor) function:

  with tf.name_scope('AUC'):
    with tf.name_scope('prediction'):
        prediction = tf.argmax(result_tensor, 1)
    with tf.name_scope('AUC'):
        auc_value = tf.metrics.auc(tf.argmax(ground_truth_tensor, 1), prediction, curve='ROC')


  tf.summary.scalar('accuracy', evaluation_step)
  tf.summary.scalar('AUC', auc_value)

但我收到此错误:

回溯(最近一次调用):文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/examples/image_retraining/retrain.py"，第 1135 行，在tf.app.run(main=main, argv=[sys.argv[0]] + 未解析) 文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/平台/app.py",第 44 行，运行中_sys.exit(main(_sys.argv[:1] + flags_passthrough)) 文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/examples/image_retraining/retrain.py",911线，主要ground_truth_input: train_ground_truth}) 文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/client/session.py"，第 767 行，运行中run_metadata_ptr) 文件 "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/client/session.py",第 965 行，在 _run 中feed_dict_string, options, run_metadata) 文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/client/session.py"，第 1015 行，在 _do_run 中target_list, options, run_metadata) 文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/client/session.py"，第 1035 行，在 _do_call 中引发类型(e)(node_def，op，消息)tensorflow.python.framework.errors_impl.FailedPreconditionError:尝试使用未初始化的值 AUC/AUC/auc/false_positives
[[节点:AUC/AUC/auc/false_positives/read = IdentityT=DT_FLOAT，_class=["loc:@AUC/AUC/auc/false_positives"], _device="/job:localhost/replica:0/task:0/cpu:0"]]

Traceback (most recent call last): File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/examples/image_retraining/retrain.py", line 1135, in tf.app.run(main=main, argv=[sys.argv[0]] + unparsed) File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/platform/app.py", line 44, in run _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/examples/image_retraining/retrain.py", line 911, in main ground_truth_input: train_ground_truth}) File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/client/session.py", line 767, in run run_metadata_ptr) File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/client/session.py", line 965, in _run feed_dict_string, options, run_metadata) File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/client/session.py", line 1015, in _do_run target_list, options, run_metadata) File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/client/session.py", line 1035, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.FailedPreconditionError: Attempting to use uninitialized value AUC/AUC/auc/false_positives
[[Node: AUC/AUC/auc/false_positives/read = IdentityT=DT_FLOAT, _class=["loc:@AUC/AUC/auc/false_positives"], _device="/job:localhost/replica:0/task:0/cpu:0"]]

由 op u'AUC/AUC/auc/false_positives/read'引起，定义于:文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/examples/image_retraining/retrain.py"，第 1135 行，在tf.app.run(main=main, argv=[sys.argv[0]] + 未解析) 文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/平台/app.py",第 44 行，运行中_sys.exit(main(_sys.argv[:1] + flags_passthrough)) 文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/examples/image_retraining/retrain.py",第 874 行，主要final_tensor, ground_truth_input) 文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/examples/image_retraining/retrain.py"，第 806 行，在 add_evaluation_step 中auc_value, update_op = tf.metrics.auc(tf.argmax(ground_truth_tensor, 1), 预测,曲线='ROC') 文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/ops/metrics_impl.py"，线 555, 在 auc标签、预测、阈值、权重)文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/ops/metrics_impl.py"，第 473 行，在 _confusion_matrix_at_thresholds 中false_p = _create_local('false_positives', shape=[num_thresholds]) 文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/ops/metrics_impl.py"，第 177 行，在 _create_local 中validate_shape=validate_shape) 文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/ops/variables.py"，第 226 行，在 init 中expected_shape=expected_shape) 文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/ops/variables.py"，第 344 行，在 _init_from_args 中self._snapshot = array_ops.identity(self._variable, name="read") 文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/ops/gen_array_ops.py"，第 1490 行，身份result = _op_def_lib.apply_op("身份", input=input, name=name) 文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/framework/op_def_library.py"，第 768 行，在 apply_op 中op_def=op_def) 文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/framework/ops.py"，第 2402 行，在 create_op 中original_op=self._default_original_op, op_def=op_def) 文件/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/framework/ops.py"，第 1264 行，在 init 中self._traceback = _extract_stack()

Caused by op u'AUC/AUC/auc/false_positives/read', defined at: File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/examples/image_retraining/retrain.py", line 1135, in tf.app.run(main=main, argv=[sys.argv[0]] + unparsed) File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/platform/app.py", line 44, in run _sys.exit(main(_sys.argv[:1] + flags_passthrough)) File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/examples/image_retraining/retrain.py", line 874, in main final_tensor, ground_truth_input) File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/examples/image_retraining/retrain.py", line 806, in add_evaluation_step auc_value, update_op = tf.metrics.auc(tf.argmax(ground_truth_tensor, 1), prediction, curve='ROC') File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/ops/metrics_impl.py", line 555, in auc labels, predictions, thresholds, weights) File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/ops/metrics_impl.py", line 473, in _confusion_matrix_at_thresholds false_p = _create_local('false_positives', shape=[num_thresholds]) File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/ops/metrics_impl.py", line 177, in _create_local validate_shape=validate_shape) File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/ops/variables.py", line 226, in init expected_shape=expected_shape) File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/ops/variables.py", line 344, in _init_from_args self._snapshot = array_ops.identity(self._variable, name="read") File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/ops/gen_array_ops.py", line 1490, in identity result = _op_def_lib.apply_op("Identity", input=input, name=name) File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/framework/op_def_library.py", line 768, in apply_op op_def=op_def) File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/framework/ops.py", line 2402, in create_op original_op=self._default_original_op, op_def=op_def) File "/home/user_2/tensorflow/bazel-bin/tensorflow/examples/image_retraining/retrain.runfiles/org_tensorflow/tensorflow/python/framework/ops.py", line 1264, in init self._traceback = _extract_stack()

FailedPreconditionError(回溯见上文):尝试使用未初始化的值 AUC/AUC/auc/false_positives [[节点:AUC/AUC/auc/false_positives/read = IdentityT=DT_FLOAT，_class=["loc:@AUC/AUC/auc/false_positives"], _device="/job:localhost/replica:0/task:0/cpu:0"]]

FailedPreconditionError (see above for traceback): Attempting to use uninitialized value AUC/AUC/auc/false_positives [[Node: AUC/AUC/auc/false_positives/read = IdentityT=DT_FLOAT, _class=["loc:@AUC/AUC/auc/false_positives"], _device="/job:localhost/replica:0/task:0/cpu:0"]]

但我不明白为什么会这样，因为主要我有这个:

But I don't understand why is this because in the main I have this:

init = tf.global_variables_initializer()
sess.run(init)

推荐答案

试试这个:

init = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer())
sess.run(init)

这篇关于Tensorflow 尝试使用未初始化的值 AUC/AUC/auc/false_positives的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！