AI Project #4: Image Classifier
https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/
Implement
Implement the “TensorFlow for Poets” guide by following the steps of the training guide with
the following modifications:
REQUIREMENTS:
1. Use the inception architecture
2. Do not restrict the training steps or specify additional training steps (Use the tensorflow default only)
3. Download domestic rabbits training images instead of flowers: http://c322.wirsz.com/1/8rabbits.
zip
4. Train the model, find 3 rabbit pictures and 1 “unknown” picture on the Internet and analyze them
(suggestion: look for images of those 8 rabbit breeds but do not use pictures from the training set)
5. Figure out how make the system return a certain percentage for “unknown” when given images that
don’t fall into the 8 rabbit categories (see screenshots for examples)
6. Tweak the settings to achieve better numbers for the rabbit pictures. Increasing the number of training
steps or downloading/removing training images are NOT valid options. Tell me what you did and
provide screenshots from analyzing your same 4 pictures
Submit the 3 rabbit pictures you chose, a short document describing the Python commands
you used for training/analysis and how you overcame the challenges in this assignment, and
multiple screenshots of the statistics (at steps #4, #5, and #6)
Last Revised: February 21, 2018
1
