pytorch/examples

Changes needed to run DCGAN 32x32

Open

#486 opened on Dec 29, 2018

View on GitHub
 (1 comment) (4 reactions) (0 assignees)Python (9,429 forks)batch import
good first issuevision

Repository metrics

Stars
 (21,634 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

I'm trying to run the DCGAN on Imagenet 32x32, but am running into problems.

If I just change the --imageSize to 32, then the convolutional layers break and I get the error RuntimeError: sizes must be non-negative. I changed the kernel size of the final Generator layer to 1 and the kernel size of the final Discriminator layer to 2 (as per @rajaswa in this related isssue) but then I get a size mismatch error ValueError: Target and input must have the same number of elements. target nelement (64) != input nelement (256). I haven't made any other changes to main.py as I want to establish a baseline model.

What other changes to the parameters/Generator/Discriminator do I need?

Contributor guide

Research direction
Investigate the DCGAN implementation in pytorch/examples, specifically the generator and discriminator layers. Verify the correct architecture for 32x32 inputs by adjusting kernel sizes, strides, and padding to ensure the output tensors match the expected dimensions. Trace the forward pass to identify the exact source of the size mismatch errors.
Tech stack
pythonpytorch
Domain
machine learningcomputer vision
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
PythonPyTorchGit
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
50