What is the difference between MAE and MSE in regression?

Mean Absolute Error (MAE) averages the absolute differences between predictions and ground truth, so every error contributes proportionally. Mean Squared Error (MSE) squares each error before averaging, which penalises large outliers far more heavily. Use MAE when all errors matter equally; use MSE when large mistakes are especially costly. Both are computed in TensorFlow with tf.keras.losses.mae and tf.keras.losses.mse (the older functional tf.metrics.mean_absolute_error / mean_squared_error aliases were removed in Keras 3).

How do you evaluate a regression model in TensorFlow?

Call model.evaluate(X_test, y_test) on a held-out test set after training, or compute metrics manually from model.predict(X_test) . The test set must not be seen during training; reporting metrics on training data overstates performance. Lower MAE and MSE indicate better predictions.

Why use a separate test set instead of training-set metrics?

Training-set metrics measure memorisation, not generalisation. A model can fit training data almost perfectly while failing on unseen inputs. Splitting the data (here, 80% train / 20% test) and evaluating on the test partition reveals the model’s true predictive performance.

TensorFlow: Evaluating the Regression Model

25 Jan 2022 (updated: 18 Jul 2026) / 12 minutes to read

Elena Daehnhardt

Regression Model Evaluation in TensorFlow: MAE and MSE

Model evaluation is the process that measures how well a trained model predicts on data it has never seen. In my previous post, I built several simple regression models with TensorFlow’s Sequential API. Here I go in-depth on evaluating those models using a held-out testing dataset and the Mean Absolute Error (MAE) and Mean Squared Error (MSE) metrics.

Preparing the data, calculating MAE and MSE, and comparing models follow below.

Data Preparation: Train/Test Split with tf.range()

🔒 Subscribe to keep reading.

Calculating MAE and MSE Error Metrics

🔒 Subscribe to keep reading.

Creating Sequential Models with Tunable Hyperparameters

🔒 Subscribe to keep reading.

Evaluating Models with model.predict() and Error Metrics

🔒 Subscribe to keep reading.

Final Thoughts

🔒 Subscribe to keep reading.

References

🔒 Subscribe to keep reading.

You've hit a Deep Dive tutorial.

I spend dozens of hours researching, coding, and breaking things to write these guides. This content is free, but reserved for my subscriber community. Drop your email below to unlock this guide (and all past/future deep dives):

Already a subscriber? Use the magic link from your last newsletter, or reset your password.

New subscribers get an inbox mail: Set a password to unlock articles. The form does not log you in — use the same email afterwards.

TensorFlow: Evaluating the Regression Model

📚 This post is part of the "Machine Learning" series

Regression Model Evaluation in TensorFlow: MAE and MSE

Data Preparation: Train/Test Split with tf.range()

Calculating MAE and MSE Error Metrics

Creating Sequential Models with Tunable Hyperparameters

Evaluating Models with model.predict() and Error Metrics

Final Thoughts

References

References

Citation

TensorFlow: Evaluating the Regression Model

📚 This post is part of the "Machine Learning" series

Regression Model Evaluation in TensorFlow: MAE and MSE

Data Preparation: Train/Test Split with tf.range()

Calculating MAE and MSE Error Metrics

Creating Sequential Models with Tunable Hyperparameters

Evaluating Models with model.predict() and Error Metrics

Final Thoughts

References

You're in

References

Citation