Implement a simple **image classification inference** step that turns a model’s raw scores (logits) into a predicted class and confidence for a single image. You’ll compute probabilities with softmax and return the top prediction in a beginner-friendly way.

The softmax formula is:
$$
p_i = \frac{e^{z_i}}{\sum_{j=1}^{C} e^{z_j}}
$$

## Requirements

Implement the function
```python
def classify_image(logits, class_names):
    \"""
    Converts model logits into a predicted class and confidence.

    Args:
        logits (np.ndarray): Raw model outputs for C classes (higher means more likely).
        class_names (list[str]): Class name for each logit index.

    Returns:
        tuple[str, float, np.ndarray]:
            - predicted_class: the class name with highest probability
            - confidence: the highest probability value
            - probabilities: array of softmax probabilities (length C, sums to 1)
    \"""
    # Your solution below
```

**Rules:**
- Compute a numerically stable softmax (subtract `max(logits)` before exponentiating).
- Return the class with the highest probability and its probability as `confidence`.
- Return probabilities as a **NumPy array**.
- Do not use any prebuilt softmax helpers (e.g., `scipy.special.softmax`).
- Use only **NumPy**.

## Example

```python
logits = np.array([2.0, 1.0, 0.1])
class_names = ["cat", "dog", "car"]

classify_image(logits, class_names)
```

Output:
```python
("cat", 0.6590, array([0.6590, 0.2424, 0.0986]))
```

Subdomain Visit Count

Paid and Free Downloads

Image classification inference

Solve this easy level ML coding question from General. The premier LeetCode for ML platform to master Python, SQL, and Machine Learning algorithms.

1470. Image classification inference

Examples

Constraints

Similar Questions

Argument	Type
logits	np.ndarray
class_names	list