Padding and stride effects

129. Padding and stride effects

easy

General

senior

Padding and stride are two simple knobs in convolutional layers that control output size and how much neighboring pixels influence each other. In this task, you’ll compute the output height/width of a 2D convolution given an input image size and conv settings.

Requirements

Implement the function

python

Rules:

Use $\text{out} = \left\lfloor \frac{\text{in} + 2p - k}{s} \right\rfloor + 1$ for both height and width.
Return the output shape as a NumPy array: np.array([out_h, out_w]).
Do not simulate convolution over pixels; just compute the shape.
Use only NumPy and Python built-in libraries.
Keep it in a single Python function.

Example

python

Output:

python

Input Signature

Argument	Type
h	int
w	int
k_h	int
k_w	int
stride	int
padding	int

Output Signature

Return Name	Type
value	np.ndarray

Constraints

Return NumPy array [out_h, out_w].
Use integer floor division (//), no convolution simulation.
Only NumPy and Python built-ins allowed.

Hint 1

Use the standard output-size formula separately for height and width: \n(\text{out} = \left\lfloor\frac{\text{in} + 2p - k}{s}\right\rfloor + 1).

Hint 2

In Python, floor division for non-negative integers is //, so compute:
out_h = (h + 2*padding - k_h) // stride + 1 and similarly for width.

Hint 3

Return as a NumPy array np.array([out_h, out_w]).

Roles

ML Engineer

AI Engineer

Companies

General

Levels

senior

entry

Input Arguments

Edit values below to test with custom inputs

You need tolog in/sign upto run or submit