Notice that there are a few metrics will be helpful when evaluating the performance of ML/DL models:

**False**negatives and**false**positives are samples that were**incorrectly**classified**True**negatives and**true**positives are samples that were**correctly**classified**Accuracy**is the percentage of examples correctly classified >**Precision**is the percentage of**predicted**positives that were correctly classified >**Recall**is the percentage of**actual**positives that were correctly classified >**AUC**refers to the Area Under the Curve of a Receiver Operating Characteristic curve (ROC-AUC). This metric is equal to the probability that a classifier will rank a random positive sample higher than a random negative sample.**AUPRC**refers to Area Under the Curve of the Precision-Recall Curve. This metric computes precision-recall pairs for different probability thresholds.

```
import tensorflow as tf
from tensorflow import keras
METRICS = [
keras.metrics.TruePositives(name='tp'),
keras.metrics.FalsePositives(name='fp'),
keras.metrics.TrueNegatives(name='tn'),
keras.metrics.FalseNegatives(name='fn'),
keras.metrics.BinaryAccuracy(name='accuracy'),
keras.metrics.Precision(name='precision'),
keras.metrics.Recall(name='recall'),
keras.metrics.AUC(name='auc'),
keras.metrics.AUC(name='prc', curve='PR'), # precision-recall curve
]
```

Refer this example where Accuracy is not a right measure

https://www.tensorflow.org/tutorials/structured_data/imbalanced_data