Skip to content

aryandeshwal/NeuralCompression

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 

Repository files navigation

Three main steps

  1. Conversion from Keras .h5 file to tensorflow .pb file; courtesy of here
    Use following command : python3 keras_to_tensorflow.py -input_model_file <name of the .h5 file>

  2. Conversion to tensorflow .tflite file; courtesy of (here)
    Use following command : toco --input_file=<path to generated .pb file>
    --input_format=TENSORFLOW_GRAPHDEF
    --output_format=TFLITE
    --output_file=
    --inference_type=FLOAT
    --input_type=FLOAT
    --input_arrays=<name of your input layer (according to tensorflow naming)> \
    --output_arrays=<name of your output layer (according to tensorflow naming)>
    --input_shapes=1,224,224,3

  3. Inference on mobile; courtesy of here

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published