Intro

Transposed-Conv Output Size

~8 mincode completion

Implement conv_transpose_out_size(h_in, stride, pad, kernel) returning the integer .

Examples

4, stride 2, pad 1, kernel 4 grows to 8

Input
conv_transpose_out_size(4, 2, 1, 4)
Output
8

A 1x1 latent with stride 1, pad 0, kernel 1 stays 1

Input
conv_transpose_out_size(1, 1, 0, 1)
Output
1

8, stride 2, pad 0, kernel 3

Input
conv_transpose_out_size(8, 2, 0, 3)
Output
17

Hints

Hint 1

Work directly with the arguments h_in, stride, pad, and return the result rather than printing it.

Hint 2

Watch for this: used the forward conv formula.

Requirements

  • Return integer

Constraints

  • Standard library only, no imports required

  • Time limit: 200 ms, Memory: 64 MB

Try similar problems(4)
Intro
Reparameterize a Gaussian

Generative Image Models · ~8 min

Intro
U-Net Skip Concatenation

Generative Image Models · ~8 min

Easy
GAN Discriminator BCE

Generative Image Models · ~10 min

Easy
DDPM Closed-Form Noising

Generative Image Models · ~10 min

Where this shows up

~8 min

8 employers weight this skill

4 autonomy companies, 1 enterprise vendor, 1 defense company, 1 health and bio company, 1 AI product company. Top match scores 87.

Python
def conv_transpose_out_size(h_in, stride, pad, kernel):
    """
    Spatial size after a transposed conv with output_padding=0.

    Args:
        h_in, stride, pad, kernel: integers

    Returns:
        integer
    """
    # YOUR CODE HERE
    pass
Loading docs…

The AI Mentor needs an account

It reads your code and the failing tests and nudges you toward the fix without handing you the answer. Free accounts get it on every problem you're working on today.