8000 GitHub - LindseyB/not-pepe: Basic Pepe/Not-pepe image classifier
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

LindseyB/not-pepe

Repository files navigation

not-pepe

Get your tensorflow installed

follow one of the guides here

Train it

python retrain.py \
 --bottleneck_dir=bottlenecks \
 --model_dir=inception \
 --summaries_dir=training_summaries/long \
 --output_graph=retrained_graph.pb \
 --output_labels=retrained_labels.txt \
 --image_dir=images

Classify it

python label_image.py image.jpg

Example output

(tensorflow) $ python label_image.py test-image.jpg
PEPE
(tensorflow) $ python label_image.py catte.png
NOT PEPE

NOT-PEPE AS A SERVICE

Deploy

using cURL:

$ curl -X POST \
  https://starry-lattice-183618.appspot.com \
  -F url=http://i0.kym-cdn.com/photos/images/facebook/000/862/065/0e9.jpg

example response bodies:

{
  "results": "PEPE",
  "status": "OK"
}
{
  "results": "NOT_PEPE",
  "status": "OK"
}

I'm no hero. I put my bra on one boob at a time like everyone else.

About

Basic Pepe/Not-pepe image classifier

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •  

Languages

0