Skip to content
This repository has been archived by the owner on Jan 7, 2025. It is now read-only.

Improvements to examples/classification/ #559

Merged

Conversation

lukeyeager
Copy link
Member

This lets you classify multiple images without needing to edit the example at all. I found it useful while investigating #536.

  • Allow multiple input image files
  • Expose batch_size as an option

Allow multiple image files
Add batch_size
@lukeyeager
Copy link
Member Author

FYI, you can use a command like this to:

  1. Read a list of images from a text file
  2. Strip off any label information at the end of each line
  3. Pass the image files as command-line arguments to use_archive.py:
cat list-of-images.txt | awk '{print $1}' | \
    xargs ./use_archive.py 20160129-133556-a640_epoch_3.0.tar.gz --batch-size=10

lukeyeager added a commit that referenced this pull request Feb 1, 2016
…ements

Improvements to examples/classification/
@lukeyeager lukeyeager merged commit fbd2903 into NVIDIA:master Feb 1, 2016
@lukeyeager lukeyeager deleted the classification-example-improvements branch February 1, 2016 18:07
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant