Vision model evaluation metrics

136. Vision model evaluation metrics

easy

General

senior

Evaluate a computer vision model using common metrics so you can compare predictions against ground-truth labels.

You’ll implement accuracy, precision, recall, and F1-score for a binary image classifier given lists of predicted labels and true labels.

Implement the function

python

Rules:

Use the confusion-matrix counts: TP, TN, FP, FN.
Compute metrics using: $\text{Accuracy}=\frac{TP+TN}{TP+TN+FP+FN},\quad \text{Precision}=\frac{TP}{TP+FP},\quad \text{Recall}=\frac{TP}{TP+FN},\quad F1=\frac{2\cdot \text{Precision}\cdot \text{Recall}}{\text{Precision}+\text{Recall}}$
Return a Python dict with the four metrics.
Don’t call any prebuilt metric functions (no sklearn.metrics).
Key considerations (keep it simple):
- Compute TP/TN/FP/FN via boolean masks and sums.
- Return floats (not NumPy scalar types).
- Keep everything inside this single function.
- Assume denominators are non-zero (no need for special-case handling).

python

Output:

python

Input Signature

Argument	Type
y_pred	np.ndarray
y_true	np.ndarray

Output Signature

Return Name	Type
value	dict

Hint 1

Inputs are NumPy arrays, so you can compare all elements at once.

Hint 2

Compute confusion-matrix counts with boolean masks, e.g. tp = np.sum((y_true==1) & (y_pred==1)), similarly for TN/FP/FN.

Hint 3

Plug TP/TN/FP/FN into the given formulas, then return a dict with Python floats (wrap results with float(...)).

Roles

ML Engineer

AI Engineer

Companies

General

Levels

senior

entry

Edit values below to test with custom inputs

You need tolog in/sign upto run or submit