在tfhub重新训练脚本中计算F1分数、精度和召回率

下面我提供了一个使用 scikit学习

您可以使用 precision_recall_fscore_support confusion_matrix 方法:

from sklearn.metrics import precision_recall_fscore_support, confusion_matrix

这两种方法都采用了两个一维数组对象,分别存储地面真值和预测标签。

train_ground_truth 行中定义的变量 1054 和 1060 validation_ground_truth 1087 .

计算预测类标签的张量由 add_evaluation_step 功能。可以修改线条 1034

evaluation_step, prediction = add_evaluation_step(final_tensor, ground_truth_input)
# now prediction stores the tensor object that 
# calculates predicted class labels

1076 为了评估 prediction sess.run() :

train_accuracy, cross_entropy_value, train_predictions = sess.run(
    [evaluation_step, cross_entropy, prediction],
    feed_dict={bottleneck_input: train_bottlenecks,
               ground_truth_input: train_ground_truth})

# train_predictions now stores class labels predicted by model

# calculate precision, recall and F1 score
(train_precision,
 train_recall,
 train_f1_score, _) = precision_recall_fscore_support(y_true=train_ground_truth,
                                                      y_pred=train_predictions,
                                                      average='micro')
# calculate confusion matrix
train_confusion_matrix = confusion_matrix(y_true=train_ground_truth,
                                          y_pred=train_predictions)

类似地,您可以通过修改行来计算验证子集的度量 1095 :

validation_summary, validation_accuracy, validation_predictions = sess.run(
    [merged, evaluation_step, prediction],
    feed_dict={bottleneck_input: validation_bottlenecks,
               ground_truth_input: validation_ground_truth})

# validation_predictions now stores class labels predicted by model

# calculate precision, recall and F1 score
(validation_precision,
 validation_recall,
 validation_f1_score, _) = precision_recall_fscore_support(y_true=validation_ground_truth,
                                                           y_pred=validation_predictions,
                                                           average='micro')
# calculate confusion matrix
validation_confusion_matrix = confusion_matrix(y_true=validation_ground_truth,
                                               y_pred=validation_predictions)

run_final_eval 根据测试数据评估训练模型。在这个函数中, 预测 test_ground_truth 已定义,因此您只需包含代码即可计算所需的度量:

test_accuracy, predictions = eval_session.run(
    [evaluation_step, prediction],
    feed_dict={
        bottleneck_input: test_bottlenecks,
        ground_truth_input: test_ground_truth
    })

# calculate precision, recall and F1 score
(test_precision,
 test_recall,
 test_f1_score, _) = precision_recall_fscore_support(y_true=test_ground_truth,
                                                     y_pred=predictions,
                                                     average='micro')
# calculate confusion matrix
test_confusion_matrix = confusion_matrix(y_true=test_ground_truth,
                                         y_pred=predictions)

全球的 average='micro' . scikit学习包支持的不同平均方法如中所述 User Guide .