Tensor flow for poets guide

Links.md

• https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/#0
• https://www.tensorflow.org/tutorials/keras/basic_text_classification

tensor flow for poets.md

https://codelabs.developers.google.com/codelabs/tensorflow-for-poets/#0

Setup

export IMAGE_SIZE=224
export ARCHITECTURE="mobilenet_0.50_${IMAGE_SIZE}"

pip install --upgrade  "tensorflow==1.7.*"
pip install PILLOW

To create 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

To Test:

python -m scripts.label_image \
  --graph=tf_files/retrained_graph.pb  \
  --image=tf_files/flower_photos/daisy/3475870145_685a19116d.jpg

Transform to mobile

pip3 install tf-nightly

tflite_convert \
--graph_def_file=tf_files/retrained_graph.pb \
--output_file=tf_files/optimized_graph.lite \
--input_format=TENSORFLOW_GRAPHDEF \
--output_format=TFLITE \
--input_shape=1,${IMAGE_SIZE},${IMAGE_SIZE},3 \
--input_array=input \
--output_array=final_result \
--inference_type=FLOAT \
--input_data_type=FLOAT

cp tf_files/optimized_graph.lite android/tflite/app/src/main/assets/graph.lite 
cp tf_files/retrained_labels.txt android/tflite/app/src/main/assets/labels.txt