Tensorflow Precision / Recall / F1 score and Confusion matrix

by

You do not really need sklearn to calculate precision/recall/f1 score. You can easily express them in TF-ish way by looking at the formulas:

enter image description here

Now if you have your actual and predicted values as vectors of 0/1, you can calculate TP, TN, FP, FN using tf.count_nonzero:

TP = tf.count_nonzero(predicted * actual)
TN = tf.count_nonzero((predicted - 1) * (actual - 1))
FP = tf.count_nonzero(predicted * (actual - 1))
FN = tf.count_nonzero((predicted - 1) * actual)

Now your metrics are easy to calculate:

precision = TP / (TP + FP)
recall = TP / (TP + FN)
f1 = 2 * precision * recall / (precision + recall)

More Related Contents:

  1. How to extract the decision rules from scikit-learn decision-tree?
  2. What are logits? What is the difference between softmax and softmax_cross_entropy_with_logits?
  3. Keras Dense layer’s input is not flattened
  4. scikit-learn & statsmodels – which R-squared is correct?
  5. How to get most informative features for scikit-learn classifiers?
  6. Why is Random Forest with a single tree much better than a Decision Tree classifier?
  7. Proper way to feed time-series data to stateful LSTM?
  8. Recovering features names of explained_variance_ratio_ in PCA with sklearn
  9. ValueError at /image/ Tensor Tensor(“activation_5/Softmax:0”, shape=(?, 4), dtype=float32) is not an element of this graph
  10. What is exactly sklearn.pipeline.Pipeline?
  11. difference between StratifiedKFold and StratifiedShuffleSplit in sklearn
  12. error: (-2:Unspecified error) The function is not implemented. Rebuild the library with Windows, GTK+ 2.x or Cocoa support
  13. Scikit Learn OneHotEncoder fit and transform Error: ValueError: X has different shape than during fitting
  14. Unknown initializer: GlorotUniform when loading Keras model
  15. How to find the importance of the features for a logistic regression model?
  16. scikit-learn random state in splitting dataset
  17. Scikit Learn GridSearchCV without cross validation (unsupervised learning)
  18. How to create a keras layer with a custom gradient in TF2.0?
  19. How to compute precision, recall, accuracy and f1-score for the multiclass case with scikit learn?
  20. Tensorflow One Hot Encoder?
  21. scikit-learn: how to scale back the ‘y’ predicted result
  22. Using Smote with Gridsearchcv in Scikit-learn
  23. confused about random_state in decision tree of scikit learn
  24. ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer`
  25. Does GridSearchCV perform cross-validation?
  26. Can I send callbacks to a KerasClassifier?
  27. How to get most informative features for scikit-learn classifier for different class?
  28. scikit-learn .predict() default threshold
  29. TensorFlow, “‘module’ object has no attribute ‘placeholder'”
  30. How do you read Tensorboard files programmatically?

Leave a Comment