New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

DEFAULT_CROP_RATIO wrong? #9

Open

ByungKwanLee opened this issue Apr 10, 2022 · 1 comment

ByungKwanLee commented Apr 10, 2022

You remarked below settings of image resolution as 500px.

# Required environmental variables for the script:
export IMAGENET_DIR=/path/to/pytorch/format/imagenet/directory/
export WRITE_DIR=/your/path/here/

# Starting in the root of the Git repo:
cd examples;

# Serialize images with:
# - 500px side length maximum
# - 50% JPEG encoded
# - quality=90 JPEGs
./write_imagenet.sh 500 0.50 90

However, train_imagenet.py has a below environment variable

ffcv-imagenet/train_imagenet.py

Line 94 in e97289f

DEFAULT_CROP_RATIO = 224/256

I think it may be 224/500. Is it right?

vchiley commented Jul 12, 2022 •

edited

Loading

Standard I1k training with a 224 img size input

resizes the image to 256
crops out a 224 resolution img

where 224/256 is the crop ratio.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment