Public | Automated Build

Last pushed: a year ago
Short Description
Docker image to simplify classification of images with tensorflow
Full Description


this project is just an helper with docker images based on tutorial from


  • docker !
  • git clone this project in a directory


You just need to make a "classifier" directory with a directory "data" inside it with all your images
For example


and then put your image on it.
This "classifier" directory will have your samples but also trained classifier after execution of "".

##Train process

Just type

 ./ [any_path]/my_own_classifier

And it will do anything for you !

##Guess process

Just type for a single guess

 ./ [any_path]/my_own_classifier /yourfile.jpg

To guess an entire directory

./ [any_path]/classifier [any_path]/srcDir [any_path]/destDir

Example of result

# ./ /synced/tensor-lib/moto-classifier/ /synced/imagesToTest/moto21.jpg
moto (score = 0.88331)
car (score = 0.11669)


Use absolute file path for classifier and images because for the moment my script do not support relative path (volume mounting)

Docker Pull Command
Source Repository