A sample for tensorflow retraining
Switch branches/tags
Nothing to show
Clone or download
VikramTiwari Merge pull request #1 from lynnlangit/patch-1
added link to your demo presentation
Latest commit 9f4b6ea Jan 19, 2018
Permalink
Failed to load latest commit information.
categories init Sep 9, 2017
inception init Sep 9, 2017
test add more test images Oct 14, 2017
.gitignore init Sep 9, 2017
README.md added link to your demo presentation Jan 18, 2018
label_image.py init Sep 9, 2017
retrain.py init Sep 9, 2017

README.md

Tensorflow Retrain

About

This is an example on how to use pre-existing TensorFlow models to retrain on your data. In this example, we use Inception which is an image classifier. You can train it on the existing images of different noodles type and then use images in the test directory to get the predictions.

Setup

  • Install TensorFlow
  • Put directories with images in categories directory. The name of the directories will be the classifications

Training

python retrain.py \
  --bottleneck_dir=bottlenecks \
  --how_many_training_steps=500 \
  --model_dir=inception \
  --summaries_dir=training_summaries/basic \
  --output_graph=retrained_graph.pb \
  --output_labels=retrained_labels.txt \
  --image_dir=categories

Predicting

python label_image.py <insert_file_path_to_predict_here>

Visualize

See the model and progress in TensorBoard

tensorboard --logdir training_summaries

Demo

Credits