this classifier classifies flower from 5 categories. Daisy, Dandelion, Roses, Sunflowers and Tulip
- Docker
- Run Docker Quick Start Terminal
- Install TensorFlow using "docker run -it gcr.io/tensorflow/tensorflow:latest-devel"
- run "git pull https://github.com/googlecodelabs/tensorflow-for-poets-2"
- cd cd tensorflow-for-poets-2
- run IMAGE_SIZE=224 ARCHITECTURE="mobilenet_0.50_${IMAGE_SIZE}"
- run below script to train your model
python -m scripts.retrain
--bottleneck_dir=tf_files/bottlenecks
--how_many_training_steps=500
--model_dir=tf_files/models/
--summaries_dir=tf_files/training_summaries/"${ARCHITECTURE}"
--output_graph=tf_files/retrained_graph.pb
--output_labels=tf_files/retrained_labels.txt
--architecture="${ARCHITECTURE}"
--image_dir=tf_files/flower_photos
/* It may take while depending upon your hardware */
- its time to test our model run this script in docker shell !
python -m scripts.label_image
--graph=tf_files/retrained_graph.pb
--image=tf_files/flower_photos/daisy/21652746_cc379e0eea_m.jpg